modelId
string | author
string | last_modified
timestamp[us, tz=UTC] | downloads
int64 | likes
int64 | library_name
string | tags
list | pipeline_tag
string | createdAt
timestamp[us, tz=UTC] | card
string |
|---|---|---|---|---|---|---|---|---|---|
ihanif/whisper-tiny-minds-en
|
ihanif
| 2023-07-01T00:30:48Z | 88 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:PolyAI/minds14",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-30T23:08:45Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-minds-en
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
config: en-US
split: train[450:]
args: en-US
metrics:
- name: Wer
type: wer
value: 0.33766233766233766
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-tiny-minds-en
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6503
- Wer Ortho: 0.3418
- Wer: 0.3377
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 0.0007 | 17.86 | 500 | 0.6503 | 0.3418 | 0.3377 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
poojakp/output
|
poojakp
| 2023-06-30T23:30:26Z | 57 | 0 |
transformers
|
[
"transformers",
"pytorch",
"RefinedWebModel",
"text-generation",
"generated_from_trainer",
"custom_code",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"region:us"
] |
text-generation
| 2023-06-30T23:01:15Z |
---
tags:
- generated_from_trainer
model-index:
- name: output
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# output
This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 10
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
psymon/QLoRa-polyglot-12.8b-translate
|
psymon
| 2023-06-30T17:53:44Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T15:33:36Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
chaowu/rl_course_vizdoom_health_gathering_supreme
|
chaowu
| 2023-06-30T17:24:35Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T17:24:26Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 8.88 +/- 3.17
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r chaowu/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
davanstrien/autotrain-color-image-dating-55447129537
|
davanstrien
| 2023-06-30T15:00:05Z | 190 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"swin",
"image-classification",
"autotrain",
"vision",
"dataset:biglam/dating-historical-color-images",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-05-05T09:01:46Z |
---
tags:
- autotrain
- vision
- image-classification
datasets:
- biglam/dating-historical-color-images
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 1.602513246354456
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 55447129537
- CO2 Emissions (in grams): 1.6025
## Validation Metrics
- Loss: 0.958
- Accuracy: 0.615
- Macro F1: 0.615
- Micro F1: 0.615
- Weighted F1: 0.615
- Macro Precision: 0.618
- Micro Precision: 0.615
- Weighted Precision: 0.618
- Macro Recall: 0.615
- Micro Recall: 0.615
- Weighted Recall: 0.615
|
paorph/sentiment_analysis_amazon_echo_reviews
|
paorph
| 2023-06-30T13:52:53Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T12:15:13Z |
---
license: apache-2.0
---
## Sentimen_analysis amazon_echo model
This is a Naive Bayes classifier trained on 32 thousand amazon echo reviews for sentiment analysis. This model is suitable for English.
Labels: 0 -> Negative; 1 -> Positive
### Model training
```
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from jupyterthemes import jtplot
jtplot.style(theme='monokai', context='notebook', ticks=True, grid=False)
# Load the data
amazon_df = pd.read_csv('amazon_reviews.csv')
# Drop the unnecessary columns
amazon_df = amazon_df.drop(['date'], axis=1)
amazon_df = amazon_df.drop(['rating'], axis=1)
amazon_df = amazon_df.drop(['variation'], axis=1)
# Let's define a pipeline to clean up all the messages
# The pipeline performs the following: (1) remove punctuation, (2) remove stopwords
def message_cleaning(message):
Test_punc_removed = [char for char in message if char not in string.punctuation]
Test_punc_removed_join = ''.join(Test_punc_removed)
Test_punc_removed_join_clean = [word for word in Test_punc_removed_join.split() if word.lower() not in stopwords.words('english')]
return Test_punc_removed_join_clean
# Let's test the newly added function
amazon_df_clean = amazon_df['verified_reviews'].apply(message_cleaning)
from sklearn.feature_extraction.text import CountVectorizer
# Define the cleaning pipeline we defined earlier
vectorizer = CountVectorizer(analyzer = message_cleaning, dtype = np.uint8)
amazon_countvectorizer = vectorizer.fit_transform(amazon_df['verified_reviews'])
X = pd.DataFrame(amazon_countvectorizer.toarray())
##TRAIN A NAIVE BAYES CLASSIFIER MODEL
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2)
from sklearn.naive_bayes import MultinomialNB
NB_classifier = MultinomialNB()
NB_classifier.fit(X_train,y_train)
```
### Evaluating the model
```
from sklearn.metrics import classification_report, confusion_matrix
# Predicting the Test set results
y_predict_test = NB_classifier.predict(X_test)
cm = confusion_matrix(y_test, y_predict_test)
sns.heatmap(cm, annot=True)
```
! [Confusion_Matrix](https://huggingface.co/paorph/sentiment_analysis_amazon_echo_reviews/blob/main/confusion_matrix.png)
```
print(classification_report(y_test, y_predict_test))
```
### Output:
```
precision recall f1-score support
0 0.70 0.49 0.58 57
1 0.95 0.98 0.96 573
accuracy 0.93 630
macro avg 0.83 0.74 0.77 630
weighted avg 0.93 0.93 0.93 630
```
|
jondurbin/airoboros-7b-gpt4-1.4.1-qlora
|
jondurbin
| 2023-06-30T12:36:11Z | 1,427 | 2 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-30T11:27:44Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-7b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
Leszekasdfff/legal-bert-swift
|
Leszekasdfff
| 2023-06-30T12:16:46Z | 0 | 0 | null |
[
"coreml",
"en",
"license:cc-by-4.0",
"region:us"
] | null | 2023-06-30T11:15:19Z |
---
license: cc-by-4.0
language:
- en
---
|
heka-ai/e5-10k
|
heka-ai
| 2023-06-30T12:04:58Z | 1 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-30T12:04:53Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# heka-ai/e5-10k
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('heka-ai/e5-10k')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=heka-ai/e5-10k)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 10000 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`gpl.toolkit.loss.MarginDistillationLoss`
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 10000,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
ckpt/controlavideo-hed
|
ckpt
| 2023-06-30T11:56:41Z | 4 | 0 |
diffusers
|
[
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T11:55:27Z |
---
license: gpl-3.0
---
- Hed control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
halffried/gyre_zitspp
|
halffried
| 2023-06-30T11:54:12Z | 0 | 1 | null |
[
"region:us"
] | null | 2023-06-30T11:49:49Z |
# ZITS-PlusPlus models for Gyre
Models from https://github.com/ewrfcas/ZITS-PlusPlus
Distributed under the Apache-2.0 license
Changes:
- Converted to safetensors
- lsm_hawp config converted to yaml
|
anonymousparrot01/SubmissionModel
|
anonymousparrot01
| 2023-06-30T09:19:28Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"business",
"finance",
"en",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | null | 2023-06-30T09:18:41Z |
---
language: en
tags:
- bert
- business
- finance
license: cc-by-4.0
datasets:
- CompanyWeb
- MD&A
- S2ORC
---
# BusinessBERT
An industry-sensitive language model for business applications pretrained on business communication corpora. The model incorporates industry classification (IC) as a pretraining objective besides masked language modeling (MLM).
It was introduced in
[this paper]() and released in
[this repository]().
## Model description
We introduce BusinessBERT, an industry-sensitive language model for business applications. The advantage of the model is the training approach focused on incorporating industry information relevant for business related natural language processing (NLP) tasks.
We compile three large-scale textual corpora consisting of annual disclosures, company website content and scientific literature representing business communication. In total, the corpora include 2.23 billion token.
BusinessBERT builds upon the bidirectional encoder representations from transformer architecture (BERT) and embeds industry information during pretraining in two ways: (1) The business communication corpora contain a variety of industry-specific terminology; (2) We employ industry classification (IC) as an additional pretraining objective for text documents originating from companies.
## Intended uses & limitations
The model is intended to be fine-tuned on business related NLP tasks, i.e. sequence classification, named entity recognition, sentiment analysis or question answering.
### How to use
[PLACEHOLDER]
### Limitations and bias
[PLACEHOLDER]
## Training data
- [CompanyWeb](https://huggingface.co/datasets/anonymousparrot01/CompanyWeb): 0.77 billion token, 3.5 GB raw text file
- [MD&A Disclosures](https://data.caltech.edu/records/1249): 1.06 billion token, 5.1 GB raw text file
- [Semantic Scholar Open Research Corpus](https://api.semanticscholar.org/corpus): 0.40 billion token, 1.9 GB raw text file
## Evaluation results
[PLACEHOLDER]
<!-- When fine-tuned on downstream tasks, this model achieves the following results:
Glue test results:
| Task | MNLI-(m/mm) | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE | Average |
|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
| | 84.6/83.4 | 71.2 | 90.5 | 93.5 | 52.1 | 85.8 | 88.9 | 66.4 | 79.6 | -->
### BibTeX entry and citation info
```bibtex
@misc{title_year,
title={TITLE},
author={AUTHORS},
year={YEAR},
}
```
|
dhorbach/hfc_rl_course_vizdoom_health_gathering_supreme
|
dhorbach
| 2023-06-30T09:08:29Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-01T13:18:13Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 12.32 +/- 5.92
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r dhorbach/hfc_rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=hfc_rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=hfc_rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
TheBloke/UltraLM-13B-fp16
|
TheBloke
| 2023-06-30T08:49:01Z | 1,549 | 4 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:stingning/ultrachat",
"arxiv:2305.14233",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-29T21:21:38Z |
---
inference: false
license: other
datasets:
- stingning/ultrachat
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Open BMB's UltraLM 13B fp16
These files are pytorch format fp16 model files for [Open BMB's UltraLM 13B](https://huggingface.co/openbmb/UltraLM-13b).
It is the result of merging and/or converting the source repository to float16.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/UltraLM-13B-fp16)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/UltraLM-13B-GGML)
* [Merged, unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/UltraLM-13B-fp16)
## Prompt template: Vicuna 1.1
```
USER: prompt
ASSISTANT:
```
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Open BMB's UltraLM 13B
# UltraLM-13b
<!-- Provide a quick summary of what the model is/does. -->
This is UltraLM-13b delta weights, a chat language model trained upon [UltraChat](https://github.com/thunlp/UltraChat)
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
The model is fine-tuned based on LLaMA-13b with a multi-turn chat-format template as below
```
User: instruction 1<eos_token>
Assistant: response 1<eos_token>
User: instruction 2<eos_token>
Assistant: response 2<eos_token>
...
```
- **License:** UltraLM is based on LLaMA and should be used under LLaMA's [model license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
- **Finetuned from model:** LLaMA-13b
- **Finetuned on data:** [UltraChat](https://github.com/thunlp/UltraChat)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** [UltraChat](https://github.com/thunlp/UltraChat)
- **Paper:** [arxiv](https://arxiv.org/abs/2305.14233)
- **Demo:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
To use this model, you need to [recover](https://github.com/thunlp/UltraChat/tree/main/UltraLM) the full model from the delta weights and perform inference following the template below:
```
[Optional]User: system prompt<eos_token>
User: user input<eos_token>
Assistant:
```
|
Juardo/bsc_ai_thesis_torgo_model-1
|
Juardo
| 2023-06-30T08:15:45Z | 160 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-06-30T00:27:24Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bsc_ai_thesis_torgo_model-1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bsc_ai_thesis_torgo_model-1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3532
- Accuracy: 0.8625
- Precision: 0.8349
- Recall: 0.9055
- F1: 0.8687
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6855 | 0.96 | 12 | 0.6603 | 0.6225 | 0.5772 | 0.9303 | 0.7124 |
| 0.5875 | 2.0 | 25 | 0.5249 | 0.785 | 0.7533 | 0.8507 | 0.7991 |
| 0.4858 | 2.96 | 37 | 0.5584 | 0.7575 | 0.6940 | 0.9254 | 0.7932 |
| 0.3951 | 4.0 | 50 | 0.5366 | 0.785 | 0.7220 | 0.9303 | 0.8130 |
| 0.3962 | 4.96 | 62 | 0.4707 | 0.805 | 0.7450 | 0.9303 | 0.8274 |
| 0.3069 | 6.0 | 75 | 0.4032 | 0.8325 | 0.8190 | 0.8557 | 0.8370 |
| 0.2973 | 6.96 | 87 | 0.3753 | 0.855 | 0.8593 | 0.8507 | 0.855 |
| 0.2585 | 8.0 | 100 | 0.3719 | 0.8625 | 0.8259 | 0.9204 | 0.8706 |
| 0.2365 | 8.96 | 112 | 0.3503 | 0.855 | 0.8357 | 0.8856 | 0.8599 |
| 0.2244 | 9.6 | 120 | 0.3532 | 0.8625 | 0.8349 | 0.9055 | 0.8687 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
notillus47/test-1
|
notillus47
| 2023-06-30T06:47:54Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T06:41:55Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
YIMMYCRUZ/Jun30_03-18-57_2565635c8aeb
|
YIMMYCRUZ
| 2023-06-30T03:24:30Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T03:21:20Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: Jun30_03-18-57_2565635c8aeb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8308823529411765
- name: F1
type: f1
value: 0.8715083798882681
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Jun30_03-18-57_2565635c8aeb
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6492
- Accuracy: 0.8309
- F1: 0.8715
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.5006 | 1.09 | 500 | 0.8053 | 0.8064 | 0.8650 |
| 0.3529 | 2.18 | 1000 | 0.6492 | 0.8309 | 0.8715 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
alitair/dqn-SpaceInvadersNoFrameskip-v4
|
alitair
| 2023-06-29T21:02:18Z | 4 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T21:01:33Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 818.50 +/- 321.08
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga alitair -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga alitair -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga alitair
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
jmgonzal/gpt2-wikitext2
|
jmgonzal
| 2023-06-29T18:51:54Z | 16 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-28T19:19:01Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-wikitext2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-wikitext2
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 6.1994
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.7945 | 1.0 | 1123 | 6.6595 |
| 6.4338 | 2.0 | 2246 | 6.3846 |
| 6.2303 | 3.0 | 3369 | 6.2465 |
| 6.1113 | 4.0 | 4492 | 6.1994 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
jcnecio/rl_course_vizdoom_health_gathering_supreme
|
jcnecio
| 2023-06-29T13:55:20Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T13:55:15Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 12.93 +/- 5.92
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r jcnecio/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
p120/paul
|
p120
| 2023-06-29T08:22:40Z | 30 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-29T08:19:03Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### paul Dreambooth model trained by p120 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
johacbeg/distilbert-base-multilingual-cased-finetuned-MeIA-AnalisisDeSentimientos
|
johacbeg
| 2023-06-29T06:13:07Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T15:50:29Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: distilbert-base-multilingual-cased-finetuned-MeIA-AnalisisDeSentimientos
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-multilingual-cased-finetuned-MeIA-AnalisisDeSentimientos
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0243
- F1: 0.5441
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.8871 | 1.0 | 766 | 1.0243 | 0.5441 |
| 0.9119 | 2.0 | 1532 | 1.0243 | 0.5441 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
taeminlee/kogpt2
|
taeminlee
| 2023-06-29T05:17:27Z | 460 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
# KoGPT2-Transformers
KoGPT2 on Huggingface Transformers
### KoGPT2-Transformers
- [SKT-AI 에서 공개한 KoGPT2 (ver 1.0)](https://github.com/SKT-AI/KoGPT2)를 [Transformers](https://github.com/huggingface/transformers)에서 사용하도록 하였습니다.
- **SKT-AI 에서 KoGPT2 2.0을 공개하였습니다. https://huggingface.co/skt/kogpt2-base-v2/**
### Demo
- 일상 대화 챗봇 : http://demo.tmkor.com:36200/dialo
- 화장품 리뷰 생성 : http://demo.tmkor.com:36200/ctrl
### Example
```python
from transformers import GPT2LMHeadModel, PreTrainedTokenizerFast
model = GPT2LMHeadModel.from_pretrained("taeminlee/kogpt2")
tokenizer = PreTrainedTokenizerFast.from_pretrained("taeminlee/kogpt2")
input_ids = tokenizer.encode("안녕", add_special_tokens=False, return_tensors="pt")
output_sequences = model.generate(input_ids=input_ids, do_sample=True, max_length=100, num_return_sequences=3)
for generated_sequence in output_sequences:
generated_sequence = generated_sequence.tolist()
print("GENERATED SEQUENCE : {0}".format(tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)))
```
|
chaowu/a2c-AntBulletEnv-v0
|
chaowu
| 2023-06-29T03:45:43Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"AntBulletEnv-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T00:50:29Z |
---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: AntBulletEnv-v0
type: AntBulletEnv-v0
metrics:
- type: mean_reward
value: 1660.92 +/- 74.15
name: mean_reward
verified: false
---
# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Ahmed007/Dr.Smart_v2
|
Ahmed007
| 2023-06-29T03:29:37Z | 63 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"vit",
"image-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-06-29T02:37:11Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Ahmed007/Dr.Smart_v2
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Ahmed007/Dr.Smart_v2
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2290
- Train Accuracy: 0.9618
- Train Top-3-accuracy: 0.9950
- Validation Loss: 0.7078
- Validation Accuracy: 0.7866
- Validation Top-3-accuracy: 0.9473
- Epoch: 4
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2198, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
### Training results
| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
| 1.5647 | 0.5528 | 0.8140 | 1.2034 | 0.6545 | 0.8955 | 0 |
| 0.9375 | 0.7526 | 0.9398 | 0.9144 | 0.7330 | 0.9277 | 1 |
| 0.5873 | 0.8659 | 0.9756 | 0.7693 | 0.7777 | 0.9464 | 2 |
| 0.3585 | 0.9294 | 0.9891 | 0.7194 | 0.7902 | 0.9473 | 3 |
| 0.2290 | 0.9618 | 0.9950 | 0.7078 | 0.7866 | 0.9473 | 4 |
### Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
Mozzipa/qlora-koalpaca-polyglot-12.8b-50step
|
Mozzipa
| 2023-06-28T23:43:40Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T23:43:37Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
Alyss97/bert-base-multilingual-uncased-sentiment-finetuned-MeIA-AnalisisDeSentimientos
|
Alyss97
| 2023-06-28T23:17:00Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T16:34:21Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert-base-multilingual-uncased-sentiment-finetuned-MeIA-AnalisisDeSentimientos
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-multilingual-uncased-sentiment-finetuned-MeIA-AnalisisDeSentimientos
This model is a fine-tuned version of [nlptown/bert-base-multilingual-uncased-sentiment](https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9405
- F1: 0.5939
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.9441 | 1.0 | 766 | 0.9419 | 0.5604 |
| 0.7769 | 2.0 | 1532 | 0.9405 | 0.5939 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
rvrtdta/roberta-base-bne-finetuned-MeIA-AnalisisDeSentimientos
|
rvrtdta
| 2023-06-28T22:22:16Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-26T18:21:10Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: roberta-base-bne-finetuned-MeIA-AnalisisDeSentimientos
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base-bne-finetuned-MeIA-AnalisisDeSentimientos
This model is a fine-tuned version of [BSC-TeMU/roberta-base-bne](https://huggingface.co/BSC-TeMU/roberta-base-bne) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9624
- F1: 0.5881
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.9506 | 1.0 | 657 | 0.9264 | 0.5792 |
| 0.6835 | 2.0 | 1314 | 0.9624 | 0.5881 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
klamerE/ppo-Huggy
|
klamerE
| 2023-06-28T22:11:12Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-28T22:11:07Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: klamerE/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
NasimB/bert-dp-4
|
NasimB
| 2023-06-28T21:01:05Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"dataset:generator",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-26T01:24:27Z |
---
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: bert-dp-4
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-dp-4
This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4611
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 180
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 6.3492 | 1.89 | 1000 | 5.9327 |
| 5.8333 | 3.78 | 2000 | 5.8515 |
| 5.7604 | 5.67 | 3000 | 5.8483 |
| 5.7137 | 7.56 | 4000 | 5.7914 |
| 5.6597 | 9.45 | 5000 | 5.7672 |
| 5.6213 | 11.34 | 6000 | 5.7594 |
| 5.5798 | 13.23 | 7000 | 5.7352 |
| 5.5482 | 15.12 | 8000 | 5.7275 |
| 5.513 | 17.01 | 9000 | 5.7203 |
| 5.485 | 18.9 | 10000 | 5.7211 |
| 5.4498 | 20.79 | 11000 | 5.6947 |
| 5.4175 | 22.68 | 12000 | 5.6923 |
| 5.3877 | 24.57 | 13000 | 5.6879 |
| 5.3635 | 26.47 | 14000 | 5.6776 |
| 5.3389 | 28.36 | 15000 | 5.6757 |
| 5.3166 | 30.25 | 16000 | 5.6758 |
| 5.2951 | 32.14 | 17000 | 5.6676 |
| 5.2793 | 34.03 | 18000 | 5.6711 |
| 5.2684 | 35.92 | 19000 | 5.6687 |
| 5.2609 | 37.81 | 20000 | 5.6684 |
| 5.2606 | 39.7 | 21000 | 5.6719 |
| 5.2624 | 41.59 | 22000 | 5.6697 |
| 5.2551 | 43.48 | 23000 | 5.6718 |
| 5.2461 | 45.37 | 24000 | 5.6699 |
| 5.2431 | 47.26 | 25000 | 5.6692 |
| 5.2414 | 49.15 | 26000 | 5.6691 |
| 5.2856 | 51.04 | 27000 | 5.6823 |
| 5.2753 | 52.93 | 28000 | 5.6860 |
| 5.2549 | 54.82 | 29000 | 5.6877 |
| 5.2276 | 56.71 | 30000 | 5.6285 |
| 5.1674 | 58.6 | 31000 | 5.5439 |
| 5.0894 | 60.49 | 32000 | 5.4082 |
| 4.9508 | 62.38 | 33000 | 5.1598 |
| 4.7453 | 64.27 | 34000 | 4.9274 |
| 4.5898 | 66.16 | 35000 | 4.7884 |
| 4.4656 | 68.05 | 36000 | 4.6531 |
| 4.35 | 69.94 | 37000 | 4.5123 |
| 4.2378 | 71.83 | 38000 | 4.4012 |
| 4.1496 | 73.72 | 39000 | 4.3240 |
| 4.0891 | 75.61 | 40000 | 4.2763 |
| 4.0538 | 77.5 | 41000 | 4.2520 |
| 4.0448 | 79.4 | 42000 | 4.2485 |
| 3.9724 | 81.29 | 43000 | 3.9940 |
| 3.6527 | 83.18 | 44000 | 3.7442 |
| 3.4172 | 85.07 | 45000 | 3.5713 |
| 3.2446 | 86.96 | 46000 | 3.4403 |
| 3.4764 | 88.85 | 47000 | 3.3796 |
| 3.0543 | 90.74 | 48000 | 3.2884 |
| 2.9549 | 92.63 | 49000 | 3.2107 |
| 2.8785 | 94.52 | 50000 | 3.1466 |
| 2.8143 | 96.41 | 51000 | 3.0788 |
| 2.7605 | 98.3 | 52000 | 3.0230 |
| 2.7111 | 100.19 | 53000 | 2.9802 |
| 2.6727 | 102.08 | 54000 | 2.9414 |
| 2.6417 | 103.97 | 55000 | 2.9167 |
| 2.612 | 105.86 | 56000 | 2.8927 |
| 2.5918 | 107.75 | 57000 | 2.8769 |
| 2.5769 | 109.64 | 58000 | 2.8637 |
| 2.566 | 111.53 | 59000 | 2.8551 |
| 2.556 | 113.42 | 60000 | 2.8458 |
| 2.548 | 115.31 | 61000 | 2.8488 |
| 2.5468 | 117.2 | 62000 | 2.8412 |
| 2.5453 | 119.09 | 63000 | 2.8383 |
| 2.7567 | 120.98 | 64000 | 2.8857 |
| 2.6017 | 122.87 | 65000 | 2.8382 |
| 2.5416 | 124.76 | 66000 | 2.7862 |
| 2.484 | 126.65 | 67000 | 2.7415 |
| 2.4361 | 128.54 | 68000 | 2.7079 |
| 2.3925 | 130.43 | 69000 | 2.6771 |
| 2.3512 | 132.33 | 70000 | 2.6542 |
| 2.3146 | 134.22 | 71000 | 2.6327 |
| 2.2805 | 136.11 | 72000 | 2.6119 |
| 2.2494 | 138.0 | 73000 | 2.5903 |
| 2.2218 | 139.89 | 74000 | 2.5734 |
| 2.1955 | 141.78 | 75000 | 2.5584 |
| 2.1739 | 143.67 | 76000 | 2.5459 |
| 2.154 | 145.56 | 77000 | 2.5337 |
| 2.1324 | 147.45 | 78000 | 2.5260 |
| 2.1149 | 149.34 | 79000 | 2.5169 |
| 2.096 | 151.23 | 80000 | 2.5095 |
| 2.083 | 153.12 | 81000 | 2.5045 |
| 2.0666 | 155.01 | 82000 | 2.4911 |
| 2.0562 | 156.9 | 83000 | 2.4907 |
| 2.0437 | 158.79 | 84000 | 2.4808 |
| 2.0356 | 160.68 | 85000 | 2.4816 |
| 2.0317 | 162.57 | 86000 | 2.4758 |
| 2.0201 | 164.46 | 87000 | 2.4724 |
| 2.0138 | 166.35 | 88000 | 2.4723 |
| 2.0095 | 168.24 | 89000 | 2.4651 |
| 2.0056 | 170.13 | 90000 | 2.4651 |
| 2.0021 | 172.02 | 91000 | 2.4616 |
| 1.9974 | 173.91 | 92000 | 2.4611 |
| 1.9985 | 175.8 | 93000 | 2.4613 |
| 1.9954 | 177.69 | 94000 | 2.4579 |
| 1.9979 | 179.58 | 95000 | 2.4611 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
ahishamm/vit-base-isic-patch-16
|
ahishamm
| 2023-06-28T19:41:07Z | 191 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-06-28T19:35:26Z |
---
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
- recall
- f1
- precision
model-index:
- name: vit-base-isic-patch-16
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vit-base-isic-patch-16
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ahishamm/isic_db dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6220
- Accuracy: 0.7917
- Recall: 0.7917
- F1: 0.7917
- Precision: 0.7917
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
trevorj/ppo-lunarlander1
|
trevorj
| 2023-06-28T17:41:35Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T17:41:10Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 265.85 +/- 14.14
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
paust/pko-t5-large
|
paust
| 2023-06-28T17:03:42Z | 751 | 20 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"ko",
"arxiv:2105.09680",
"license:cc-by-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2022-05-16T11:59:52Z |
---
language: ko
license: cc-by-4.0
---
# pko-t5-large
[Source Code](https://github.com/paust-team/pko-t5)
pko-t5 는 한국어 전용 데이터로 학습한 [t5 v1.1 모델](https://github.com/google-research/text-to-text-transfer-transformer/blob/84f8bcc14b5f2c03de51bd3587609ba8f6bbd1cd/released_checkpoints.md)입니다.
한국어를 tokenize 하기 위해서 sentencepiece 대신 OOV 가 없는 BBPE 를 사용했으며 한국어 데이터 (나무위키, 위키피디아, 모두의말뭉치 등..) 를 T5 의 span corruption task 를 사용해서 unsupervised learning 만 적용하여 학습을 진행했습니다.
pko-t5 를 사용하실 때는 대상 task 에 파인튜닝하여 사용하시기 바랍니다.
## Usage
transformers 의 API 를 사용하여 접근 가능합니다. tokenizer 를 사용할때는 `T5Tokenizer` 가 아니라 `T5TokenizerFast` 를 사용해주십시오. model 은 T5ForConditionalGeneration 를 그대로 활용하시면 됩니다.
### Example
```python
from transformers import T5TokenizerFast, T5ForConditionalGeneration
tokenizer = T5TokenizerFast.from_pretrained('paust/pko-t5-large')
model = T5ForConditionalGeneration.from_pretrained('paust/pko-t5-large')
input_ids = tokenizer(["qa question: 당신의 이름은 무엇인가요?"]).input_ids
labels = tokenizer(["T5 입니다."]).input_ids
outputs = model(input_ids=input_ids, labels=labels)
print(f"loss={outputs.loss} logits={outputs.logits}")
```
## Klue 평가 (dev)
| | Model | ynat (macro F1) | sts (pearsonr/F1) | nli (acc) | ner (entity-level F1) | re (micro F1) | dp (LAS) | mrc (EM/F1) |
|-----|------------------------------------------------------------------|-----------------|-------------------|-----------|-----------------------|---------------|-----------|-------------|
| | Baseline | **87.30** | **93.20/86.13** | **89.50** | 86.06 | 71.06 | 87.93 | **75.26/-** |
| FT | [pko-t5-small](https://huggingface.co/paust/pko-t5-small) (77M) | 86.21 | 77.99/77.01 | 69.20 | 82.60 | 66.46 | 93.15 | 43.81/46.58 |
| FT | [pko-t5-base](https://huggingface.co/paust/pko-t5-base) (250M) | 87.29 | 90.25/83.43 | 79.73 | 87.80 | 67.23 | 97.28 | 61.53/64.74 |
| FT | [pko-t5-large](https://huggingface.co/paust/pko-t5-large) (800M) | 87.12 | 92.05/85.24 | 84.96 | **88.18** | **75.17** | **97.60** | 68.01/71.44 |
| MT | pko-t5-small | 84.54 | 68.50/72/02 | 51.16 | 74.69 | 66.11 | 80.40 | 43.60/46.28 |
| MT | pko-t5-base | 86.89 | 83.96/80.30 | 72.03 | 85.27 | 66.59 | 95.05 | 61.11/63.94 |
| MT | pko-t5-large | 87.57 | 91.93/86.29 | 83.63 | 87.41 | 71.34 | 96.99 | 70.70/73.72 |
- FT: 싱글태스크 파인튜닝 / MT: 멀티태스크 파인튜닝
- [Baseline](https://arxiv.org/abs/2105.09680): KLUE 논문에서 소개된 dev set 에 대한 SOTA 점수
## License
[PAUST](https://paust.io)에서 만든 pko-t5는 [MIT license](https://github.com/paust-team/pko-t5/blob/main/LICENSE) 하에 공개되어 있습니다.
|
sharpbai/open_llama_13b
|
sharpbai
| 2023-06-28T16:14:25Z | 25 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:togethercomputer/RedPajama-Data-1T",
"arxiv:2302.13971",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-22T05:07:23Z |
---
license: apache-2.0
datasets:
- togethercomputer/RedPajama-Data-1T
---
# open_llama_13b
*The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads*
A 650MB split weight version of [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)
The original model card is down below
-----------------------------------------
# OpenLLaMA: An Open Reproduction of LLaMA
In this repo, we present a permissively licensed open source reproduction of Meta AI's [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) large language model. We are releasing 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA models, as well as evaluation results and comparison against the original LLaMA models. Please see the [project homepage of OpenLLaMA](https://github.com/openlm-research/open_llama) for more details.
## Weights Release, License and Usage
We release the weights in two formats: an EasyLM format to be use with our [EasyLM framework](https://github.com/young-geng/EasyLM), and a PyTorch format to be used with the [Hugging Face transformers](https://huggingface.co/docs/transformers/index) library. Both our training framework EasyLM and the checkpoint weights are licensed permissively under the Apache 2.0 license.
### Loading the Weights with Hugging Face Transformers
Preview checkpoints can be directly loaded from Hugging Face Hub. **Please note that it is advised to avoid using the Hugging Face fast tokenizer for now, as we’ve observed that the auto-converted fast tokenizer sometimes gives incorrect tokenizations.** This can be achieved by directly using the `LlamaTokenizer` class, or passing in the `use_fast=False` option for the `AutoTokenizer` class. See the following example for usage.
```python
import torch
from transformers import LlamaTokenizer, LlamaForCausalLM
# model_path = 'openlm-research/open_llama_3b'
# model_path = 'openlm-research/open_llama_7b'
model_path = 'openlm-research/open_llama_13b'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',
)
prompt = 'Q: What is the largest animal?\nA:'
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=32
)
print(tokenizer.decode(generation_output[0]))
```
For more advanced usage, please follow the [transformers LLaMA documentation](https://huggingface.co/docs/transformers/main/model_doc/llama).
### Evaluating with LM-Eval-Harness
The model can be evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness). However, due to the aforementioned tokenizer issue, we need to avoid using the fast tokenizer to obtain the correct results. This can be achieved by passing in `use_fast=False` to [this part of lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness/blob/4b701e228768052cfae9043dca13e82052ca5eea/lm_eval/models/huggingface.py#LL313C9-L316C10), as shown in the example below:
```python
tokenizer = self.AUTO_TOKENIZER_CLASS.from_pretrained(
pretrained if tokenizer is None else tokenizer,
revision=revision + ("/" + subfolder if subfolder is not None else ""),
use_fast=False
)
```
### Loading the Weights with EasyLM
For using the weights in our EasyLM framework, please refer to the [LLaMA documentation of EasyLM](https://github.com/young-geng/EasyLM/blob/main/docs/llama.md). Note that unlike the original LLaMA model, our OpenLLaMA tokenizer and weights are trained completely from scratch so it is no longer needed to obtain the original LLaMA tokenizer and weights. Note that we use BOS (beginning of sentence) token (id=1) during training, so it is best to prepend this token for best performance during few-shot evaluation.
## Dataset and Training
We train our models on the [RedPajama](https://www.together.xyz/blog/redpajama) dataset released by [Together](https://www.together.xyz/), which is a reproduction of the LLaMA training dataset containing over 1.2 trillion tokens. We follow the exactly same preprocessing steps and training hyperparameters as the original LLaMA paper, including model architecture, context length, training steps, learning rate schedule, and optimizer. The only difference between our setting and the original one is the dataset used: OpenLLaMA employs the RedPajama dataset rather than the one utilized by the original LLaMA.
We train the models on cloud TPU-v4s using [EasyLM](https://github.com/young-geng/EasyLM), a JAX based training pipeline we developed for training and fine-tuning large language models. We employ a combination of normal data parallelism and [fully sharded data parallelism (also know as ZeRO stage 3)](https://engineering.fb.com/2021/07/15/open-source/fsdp/) to balance the training throughput and memory usage. Overall we reach a throughput of over 2200 tokens / second / TPU-v4 chip for our 7B model.
## Evaluation
We evaluated OpenLLaMA on a wide range of tasks using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). The LLaMA results are generated by running the original LLaMA model on the same evaluation metrics. We note that our results for the LLaMA model differ slightly from the original LLaMA paper, which we believe is a result of different evaluation protocols. Similar differences have been reported in [this issue of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/issues/443). Additionally, we present the results of GPT-J, a 6B parameter model trained on the [Pile](https://pile.eleuther.ai/) dataset by [EleutherAI](https://www.eleuther.ai/).
The original LLaMA model was trained for 1 trillion tokens and GPT-J was trained for 500 billion tokens. We present the results in the table below. OpenLLaMA exhibits comparable performance to the original LLaMA and GPT-J across a majority of tasks, and outperforms them in some tasks.
| **Task/Metric** | GPT-J 6B | LLaMA 7B | LLaMA 13B | OpenLLaMA 7B | OpenLLaMA 3B | OpenLLaMA 13B |
| ---------------------- | -------- | -------- | --------- | ------------ | ------------ | ------------- |
| anli_r1/acc | 0.32 | 0.35 | 0.35 | 0.33 | 0.33 | 0.33 |
| anli_r2/acc | 0.34 | 0.34 | 0.36 | 0.36 | 0.32 | 0.33 |
| anli_r3/acc | 0.35 | 0.37 | 0.39 | 0.38 | 0.35 | 0.40 |
| arc_challenge/acc | 0.34 | 0.39 | 0.44 | 0.37 | 0.34 | 0.41 |
| arc_challenge/acc_norm | 0.37 | 0.41 | 0.44 | 0.38 | 0.37 | 0.44 |
| arc_easy/acc | 0.67 | 0.68 | 0.75 | 0.72 | 0.69 | 0.75 |
| arc_easy/acc_norm | 0.62 | 0.52 | 0.59 | 0.68 | 0.65 | 0.70 |
| boolq/acc | 0.66 | 0.75 | 0.71 | 0.71 | 0.68 | 0.75 |
| hellaswag/acc | 0.50 | 0.56 | 0.59 | 0.53 | 0.49 | 0.56 |
| hellaswag/acc_norm | 0.66 | 0.73 | 0.76 | 0.72 | 0.67 | 0.76 |
| openbookqa/acc | 0.29 | 0.29 | 0.31 | 0.30 | 0.27 | 0.31 |
| openbookqa/acc_norm | 0.38 | 0.41 | 0.42 | 0.40 | 0.40 | 0.43 |
| piqa/acc | 0.75 | 0.78 | 0.79 | 0.76 | 0.75 | 0.77 |
| piqa/acc_norm | 0.76 | 0.78 | 0.79 | 0.77 | 0.76 | 0.79 |
| record/em | 0.88 | 0.91 | 0.92 | 0.89 | 0.88 | 0.91 |
| record/f1 | 0.89 | 0.91 | 0.92 | 0.90 | 0.89 | 0.91 |
| rte/acc | 0.54 | 0.56 | 0.69 | 0.60 | 0.58 | 0.64 |
| truthfulqa_mc/mc1 | 0.20 | 0.21 | 0.25 | 0.23 | 0.22 | 0.25 |
| truthfulqa_mc/mc2 | 0.36 | 0.34 | 0.40 | 0.35 | 0.35 | 0.38 |
| wic/acc | 0.50 | 0.50 | 0.50 | 0.51 | 0.48 | 0.47 |
| winogrande/acc | 0.64 | 0.68 | 0.70 | 0.67 | 0.62 | 0.70 |
| Average | 0.52 | 0.55 | 0.57 | 0.55 | 0.53 | 0.57 |
We removed the task CB and WSC from our benchmark, as our model performs suspiciously well on these two tasks. We hypothesize that there could be a benchmark data contamination in the training set.
## Contact
We would love to get feedback from the community. If you have any questions, please open an issue or contact us.
OpenLLaMA is developed by:
[Xinyang Geng](https://young-geng.xyz/)* and [Hao Liu](https://www.haoliu.site/)* from Berkeley AI Research.
*Equal Contribution
## Acknowledgment
We thank the [Google TPU Research Cloud](https://sites.research.google/trc/about/) program for providing part of the computation resources. We’d like to specially thank Jonathan Caton from TPU Research Cloud for helping us organizing compute resources, Rafi Witten from the Google Cloud team and James Bradbury from the Google JAX team for helping us optimizing our training throughput. We’d also want to thank Charlie Snell, Gautier Izacard, Eric Wallace, Lianmin Zheng and our user community for the discussions and feedback.
The OpenLLaMA 13B model is trained in collaboration with [Stability AI](https://stability.ai/), and we thank Stability AI for providing the computation resources. We’d like to especially thank David Ha and Shivanshu Purohit for the coordinating the logistics and providing engineering support.
## Reference
If you found OpenLLaMA useful in your research or applications, please cite using the following BibTeX:
```
@software{openlm2023openllama,
author = {Geng, Xinyang and Liu, Hao},
title = {OpenLLaMA: An Open Reproduction of LLaMA},
month = May,
year = 2023,
url = {https://github.com/openlm-research/open_llama}
}
```
```
@software{together2023redpajama,
author = {Together Computer},
title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset},
month = April,
year = 2023,
url = {https://github.com/togethercomputer/RedPajama-Data}
}
```
```
@article{touvron2023llama,
title={Llama: Open and efficient foundation language models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
```
|
YakovElm/IntelDAOS_15_BERT_Over_Sampling
|
YakovElm
| 2023-06-28T15:55:27Z | 62 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T15:54:45Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: IntelDAOS_15_BERT_Over_Sampling
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# IntelDAOS_15_BERT_Over_Sampling
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0704
- Train Accuracy: 0.9820
- Validation Loss: 0.7296
- Validation Accuracy: 0.8108
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5199 | 0.7373 | 0.5990 | 0.6517 | 0 |
| 0.2247 | 0.9276 | 0.8030 | 0.7357 | 1 |
| 0.0704 | 0.9820 | 0.7296 | 0.8108 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
AbhilashGanji/distilbert-base-uncased-finetuned-squad-d5716d28
|
AbhilashGanji
| 2023-06-28T15:54:44Z | 0 | 0 | null |
[
"pytorch",
"question-answering",
"en",
"dataset:squad",
"arxiv:1910.01108",
"license:apache-2.0",
"region:us"
] |
question-answering
| 2023-06-28T15:50:07Z |
---
language:
- en
thumbnail: https://github.com/karanchahal/distiller/blob/master/distiller.jpg
tags:
- question-answering
license: apache-2.0
datasets:
- squad
metrics:
- squad
---
# DistilBERT with a second step of distillation
## Model description
This model replicates the "DistilBERT (D)" model from Table 2 of the [DistilBERT paper](https://arxiv.org/pdf/1910.01108.pdf). In this approach, a DistilBERT student is fine-tuned on SQuAD v1.1, but with a BERT model (also fine-tuned on SQuAD v1.1) acting as a teacher for a second step of task-specific distillation.
In this version, the following pre-trained models were used:
* Student: `distilbert-base-uncased`
* Teacher: `lewtun/bert-base-uncased-finetuned-squad-v1`
## Training data
This model was trained on the SQuAD v1.1 dataset which can be obtained from the `datasets` library as follows:
```python
from datasets import load_dataset
squad = load_dataset('squad')
```
## Training procedure
## Eval results
| | Exact Match | F1 |
|------------------|-------------|------|
| DistilBERT paper | 79.1 | 86.9 |
| Ours | 78.4 | 86.5 |
The scores were calculated using the `squad` metric from `datasets`.
### BibTeX entry and citation info
```bibtex
@misc{sanh2020distilbert,
title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
year={2020},
eprint={1910.01108},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
amm297/my_awesome_peft_model
|
amm297
| 2023-06-28T14:48:41Z | 24 | 0 |
peft
|
[
"peft",
"RefinedWebModel",
"generated_from_trainer",
"text-generation",
"custom_code",
"license:other",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-28T10:55:56Z |
---
license: other
library_name: peft
pipeline_tag: text-generation
tags:
- generated_from_trainer
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
- Transformers 4.31.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.0
- Tokenizers 0.13.3
|
RayTracerGC/RVCModels
|
RayTracerGC
| 2023-06-28T11:46:11Z | 0 | 1 | null |
[
"license:openrail",
"region:us"
] | null | 2023-06-27T15:56:50Z |
---
license: openrail
---
RVC models:
- Hal Jordan Green Lantern (From Injustice 2) (RVC v2) (76 Epochs)
- Trained on `mangio-crepe` using 6 minutes of audio
- Batch size: 16
- Crepe hop length: 64
- File: GreenLantern.zip
- Wonder Woman (From Injustice 2) (RVC v2) (150 Epochs)
- Trained on `mangio-crepe` using 9 minutes of audio
- Batch size: 16
- Crepe hop length: 64
- File: WonderWoman.zip
|
amittian/setfit_ds_version_0_0_1
|
amittian
| 2023-06-28T10:23:28Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-28T10:23:07Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# amittian/setfit_ds_version_0_0_1
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("amittian/setfit_ds_version_0_0_1")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
joydeeph/ppo-LunarLander-v2
|
joydeeph
| 2023-06-28T08:42:25Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T08:41:59Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 253.93 +/- 21.40
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
yihyeji/hanbok_q
|
yihyeji
| 2023-06-28T04:33:59Z | 0 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-06-28T04:06:26Z |
---
license: creativeml-openrail-m
base_model: /workspace/data3/model_checkpoints/DIFFUSION_DB/Diffusion_models/diffusers/v15/chilloutmix_NiPrunedFp16Fix/
instance_prompt: a photo of 1 girl wearing hanbok_q
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - yihyeji/hanbok_q
These are LoRA adaption weights for /workspace/data3/model_checkpoints/DIFFUSION_DB/Diffusion_models/diffusers/v15/chilloutmix_NiPrunedFp16Fix/. The weights were trained on a photo of 1 girl wearing hanbok_q using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
eluzhnica/mpt-30b-peft-compatible
|
eluzhnica
| 2023-06-27T18:08:52Z | 11 | 8 |
transformers
|
[
"transformers",
"pytorch",
"mpt",
"text-generation",
"Composer",
"MosaicML",
"llm-foundry",
"StreamingDatasets",
"custom_code",
"dataset:allenai/c4",
"dataset:mc4",
"dataset:togethercomputer/RedPajama-Data-1T",
"dataset:bigcode/the-stack-dedup",
"dataset:allenai/s2orc",
"arxiv:2108.12409",
"arxiv:2302.13971",
"arxiv:2205.14135",
"arxiv:2010.04245",
"arxiv:1909.08053",
"arxiv:2302.06675",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-26T20:51:20Z |
---
license: apache-2.0
tags:
- Composer
- MosaicML
- llm-foundry
- StreamingDatasets
datasets:
- allenai/c4
- mc4
- togethercomputer/RedPajama-Data-1T
- bigcode/the-stack-dedup
- allenai/s2orc
inference: false
---
# MPT-30B
This is the MPT-30B but with added support to finetune using peft (tested with qlora). It is not finetuned further, the weights are the same as the original MPT-30b.
I have not traced through the whole huggingface stack to see if this is working correctly but it does finetune with qlora and outputs are reasonable.
Inspired by implementations here https://huggingface.co/cekal/mpt-7b-peft-compatible/commits/main
https://huggingface.co/mosaicml/mpt-7b/discussions/42.
The original description for MosaicML team below:
MPT-30B is a decoder-style transformer pretrained from scratch on 1T tokens of English text and code.
This model was trained by [MosaicML](https://www.mosaicml.com).
MPT-30B is part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
MPT-30B comes with special features that differentiate it from other LLMs, including an 8k token context window (which can be further extended via finetuning; see [MPT-7B-StoryWriter](https://huggingface.co/mosaicml/mpt-7b-storywriter)), support for context-length extrapolation via [ALiBi](https://arxiv.org/abs/2108.12409), and efficient inference + training via FlashAttention. It also has strong coding abilities thanks to its pretraining mix. MPT models can also be served efficiently with both standard HuggingFace pipelines and NVIDIA's [FasterTransformer](https://github.com/NVIDIA/FasterTransformer).
The size of MPT-30B was also specifically chosen to make it easy to deploy on a single GPU—either 1xA100-80GB in 16-bit precision or 1xA100-40GB in 8-bit precision.
This model uses the MosaicML LLM codebase, which can be found in the [llm-foundry repository](https://github.com/mosaicml/llm-foundry). It was trained by MosaicML’s NLP team on the [MosaicML platform](https://www.mosaicml.com/training) for LLM pretraining, finetuning, and inference.
### How is this model different?
MPT-30B is:
* **Licensed for the possibility of commercial use** (unlike [LLaMA](https://arxiv.org/abs/2302.13971)).
* **Trained on a large amount of data** (1T tokens like [LLaMA](https://arxiv.org/abs/2302.13971) vs. 300B for [Pythia](https://github.com/EleutherAI/pythia), 300B for [OpenLLaMA](https://github.com/openlm-research/open_llama), and 800B for [StableLM](https://github.com/Stability-AI/StableLM)).
* **Prepared to handle extremely long inputs** thanks to [ALiBi](https://arxiv.org/abs/2108.12409).
* **Capable of fast training and inference** (via [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) and [FasterTransformer](https://github.com/NVIDIA/FasterTransformer))
* **Equipped with highly efficient open-source training code** via the [llm-foundry repository](https://github.com/mosaicml/llm-foundry)
### Models finetuned off MPT-30B:
The following models are finetuned on MPT-30B:
* [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct): a model for short-form instruction following.
Built by finetuning MPT-30B on several carefully curated datasets.
* License: _CC-BY-SA-3.0_
* [MPT-30B-Chat](https://huggingface.co/mosaicml/mpt-30b-chat): a chatbot-like model for dialogue generation.
Built by finetuning MPT-30B on [ShareGPT-Vicuna](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered), [Camel-AI](https://huggingface.co/camel-ai),
[GPTeacher](https://github.com/teknium1/GPTeacher), [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco), [Baize](https://github.com/project-baize/baize-chatbot) and some generated datasets.
* License: _CC-By-NC-SA-4.0_
* [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-30b-chat)
## Model Date
June 22, 2023
## Model License
Apache-2.0
## Documentation
* [Blog post: MPT-30B: Raising the bar for open-source foundation models](https://www.mosaicml.com/blog/mpt-30b)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
## How to Use
This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-30b',
trust_remote_code=True
)
```
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method.
This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package.
`MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more.
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-30b'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
The model was trained initially with a sequence length of 2048 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-30b'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the MPT-30B tokenizer which is identical to the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
with torch.autocast('cuda', dtype=torch.bfloat16):
inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda')
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
# or using the HF pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 29.95B |
|n_layers | 48 |
| n_heads | 64 |
| d_model | 7168 |
| vocab size | 50432 |
| sequence length | 8192 |
## Training Data
### Streaming Datasets
Data was formatted using the MosaicML [StreamingDataset](https://github.com/mosaicml/streaming) library to host our data in object storage and efficiently stream it to our compute cluster during training.
StreamingDataset obviates the need to download the whole dataset before starting training, and allows instant resumption of training from any point in the dataset.
### Data Mix
The model was trained for 1T tokens on the following data mix:
| Data Source | Number of Tokens in Source | Proportion | Effective Number of Tokens | Epochs |
|-------------|----------------------------|------------|----------------------------|--------|
| mC4 3.1.0 - English (200+ words) | 2417.99 B | 33.50% | 335 B | 0.14 |
| c4 - English - SemDedup 80% | 100.42 B | 29.90% | 299 B | 2.98 |
| RedPajama - CommonCrawl | 878.45 B | 8.50% | 85 B | 0.097 |
| The Stack - Selected Languages | 463.78 B | 10.00% | 100 B | 0.22 |
| RedPajama - Wikipedia | 4.87 B | 4.00% | 40 B | 8.21 |
| The Stack - Markdown | 107.07 B | 4.50% | 45 B | 0.42 |
| Semantic Scholar ORC | 48.95 B | 3.30% | 33 B | 0.67 |
| RedPajama - Books | 26.02 B | 3.00% | 30 B | 1.15 |
| RedPajama - arXiv | 28.10 B | 1.90% | 19 B | 0.68 |
| RedPajama - StackExchange | 20.54 B | 1.40% | 14 B |0.68 |
Samples for each batch were selected from one of the datasets with the probability specified above. The examples were shuffled within each dataset, and each example was constructed from as many sequences from that dataset as were necessary to fill the sequence length. To build 8k support into MPT-30B efficiently, we first pre-trained on 1T tokens using sequences that were 2k tokens long, and then trained for an additional 50B tokens using sequences that were 8k tokens long.
The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. This BPE tokenizer has a number of desirable characteristics,
most of which are relevant for tokenizing code:
(1) It was trained on a diverse mix of data that includes code (The Pile)
(2) It applies consistent space delimitation, unlike the GPT2 tokenizer which tokenizes inconsistently depending on the presence of prefix spaces
(3) It contains tokens for repeated space characters, which allows superior compression of text with large amounts of repeated space characters.
The model vocabulary size of 50432 was set to be a multiple of 128 (as in [MEGATRON-LM](https://arxiv.org/abs/1909.08053)).
### Training Configuration
The model was trained in three stages using the [MosaicML Platform](https://www.mosaicml.com/platform):
(i) First it was trained on 440 A100-40GBs with a batch size of 1760.
(ii) Then, on 216 A100-40GBs with a batch size of 1728.
(iii) Training was completed on 256 H100-80GBs with a batch size of 512 with 8k context length and 50B tokens.
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the [LION](https://arxiv.org/abs/2302.06675) optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-30B (Base) is **not** intended for deployment without finetuning.
It should not be used for human-facing interactions without further guardrails and user consent.
MPT-30B can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-30B was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-30b).
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-30B: Raising the bar
for open-source foundation models},
year = {2023},
url = {www.mosaicml.com/blog/mpt-30b},
note = {Accessed: 2023-06-22},
urldate = {2023-06-22}
}
```
|
maidh/ppo-LunarLander-v2-unit8-v1
|
maidh
| 2023-06-27T16:41:53Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-27T16:40:37Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 21.08 +/- 78.81
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 2000000
'learning_rate': 0.0001
'num_envs': 4
'num_steps': 512
'anneal_lr': True
'gae': True
'gamma': 0.999
'gae_lambda': 0.98
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'WilliamADSP/ppo-LunarLander-v2-unit8-v1'
'batch_size': 2048
'minibatch_size': 512}
```
|
kesslya1/F1_cars
|
kesslya1
| 2023-06-27T16:18:10Z | 7 | 0 |
keras
|
[
"keras",
"tf-keras",
"image-classification",
"region:us"
] |
image-classification
| 2023-06-16T07:08:00Z |
---
metrics:
- accuracy
library_name: keras
pipeline_tag: image-classification
---
|
gongliyu/fine-tuned-t5-small
|
gongliyu
| 2023-06-27T15:44:16Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-23T19:00:44Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: fine-tuned-t5-small
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fine-tuned-t5-small
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.5422
- Precision: nan
- Recall: 0.7117
- F1: 0.5635
- Hashcode: roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2)
- Gen Len: 19.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Hashcode | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:------------------------------------------------------:|:-------:|
| No log | 1.0 | 1 | 12.9679 | 0.7745 | 0.7227 | 0.7474 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 2.0 | 2 | 12.1426 | 0.7811 | 0.7221 | 0.7503 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 3.0 | 3 | 11.2809 | 0.7811 | 0.7221 | 0.7503 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 4.0 | 4 | 10.4669 | 0.7821 | 0.7273 | 0.7536 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 5.0 | 5 | 9.7061 | 0.7821 | 0.7273 | 0.7536 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 6.0 | 6 | 9.0054 | 0.7821 | 0.7273 | 0.7536 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 7.0 | 7 | 8.3875 | 0.7821 | 0.7273 | 0.7536 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 8.0 | 8 | 7.8287 | 0.7772 | 0.7278 | 0.7515 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 9.0 | 9 | 7.3385 | 0.7772 | 0.7278 | 0.7515 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 10.0 | 10 | 6.9141 | 0.7772 | 0.7278 | 0.7515 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 11.0 | 11 | 6.5516 | 0.7801 | 0.7240 | 0.7509 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 12.0 | 12 | 6.2399 | 0.7801 | 0.7240 | 0.7509 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 13.0 | 13 | 5.9851 | 0.7801 | 0.7240 | 0.7509 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 14.0 | 14 | 5.7744 | 0.7801 | 0.7240 | 0.7509 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 15.0 | 15 | 5.5976 | 0.7801 | 0.7240 | 0.7509 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 16.0 | 16 | 5.4546 | 0.7873 | 0.7158 | 0.7497 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 17.0 | 17 | 5.3403 | 0.7873 | 0.7158 | 0.7497 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 18.0 | 18 | 5.2461 | 0.7873 | 0.7158 | 0.7497 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 19.0 | 19 | 5.1688 | 0.7873 | 0.7158 | 0.7497 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 20.0 | 20 | 5.1052 | 0.7922 | 0.7169 | 0.7525 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 21.0 | 21 | 5.0489 | 0.7922 | 0.7169 | 0.7525 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 22.0 | 22 | 5.0025 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 23.0 | 23 | 4.9621 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 24.0 | 24 | 4.9263 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 25.0 | 25 | 4.8933 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 26.0 | 26 | 4.8623 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 27.0 | 27 | 4.8327 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 28.0 | 28 | 4.8060 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 29.0 | 29 | 4.7811 | 0.7941 | 0.7122 | 0.7508 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 30.0 | 30 | 4.7583 | 0.7712 | 0.7105 | 0.7392 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 31.0 | 31 | 4.7361 | 0.7712 | 0.7105 | 0.7392 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 32.0 | 32 | 4.7152 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 33.0 | 33 | 4.6964 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 34.0 | 34 | 4.6789 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 35.0 | 35 | 4.6627 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 36.0 | 36 | 4.6475 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 37.0 | 37 | 4.6330 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 38.0 | 38 | 4.6192 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 39.0 | 39 | 4.6066 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 40.0 | 40 | 4.5957 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 41.0 | 41 | 4.5859 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 42.0 | 42 | 4.5771 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 43.0 | 43 | 4.5693 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 44.0 | 44 | 4.5625 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 45.0 | 45 | 4.5567 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 46.0 | 46 | 4.5518 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 47.0 | 47 | 4.5480 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 48.0 | 48 | 4.5451 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 49.0 | 49 | 4.5432 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
| No log | 50.0 | 50 | 4.5422 | nan | 0.7117 | 0.5635 | roberta-large_L17_idf_version=0.3.12(hug_trans=4.30.2) | 19.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
sdocio/es_trf_ner_cds_xlm-large
|
sdocio
| 2023-06-27T14:00:26Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"PyTorch",
"Transformers",
"Token Classification",
"xlm-roberta-large",
"es",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-06-27T13:45:59Z |
---
language: es
license: gpl-3.0
tags:
- PyTorch
- Transformers
- Token Classification
- xlm-roberta
- xlm-roberta-large
widget:
- text: "Fue antes de llegar a Sigüeiro, en el Camino de Santiago."
- text: "Si te metes en el Franco desde la Alameda, vas hacia la Catedral."
- text: "Y allí precisamente es Santiago el patrón del pueblo."
model-index:
- name: es_trf_ner_cds_xlm-large
results: []
---
# Introduction
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) for Named-Entity Recognition, in the domain of tourism related to the Way of Saint Jacques. It recognizes four types of entities: location (LOC), organizations (ORG), person (PER) and miscellaneous (MISC).
## Usage
You can use this model with Transformers *pipeline* for NER.
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("es_trf_ner_cds_xlm-large")
model = AutoModelForTokenClassification.from_pretrained("es_trf_ner_cds_xlm-large")
example = "Fue antes de llegar a Sigüeiro, en el Camino de Santiago. Si te metes en el Franco desde la Alameda, vas hacia la Catedral. Y allí precisamente es Santiago el patrón del pueblo."
ner_pipe = pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy="simple")
for ent in ner_pipe(example):
print(ent)
```
## Dataset
ToDo
## Model performance
entity|precision|recall|f1
-|-|-|-
LOC|0.973|0.983|0.978
MISC|0.760|0.788|0.773
ORG|0.885|0.701|0.783
PER|0.937|0.878|0.906
micro avg|0.953|0.958|0.955
macro avg|0.889|0.838|0.860
weighted avg|0.953|0.958|0.955
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
aidn/squadBert3Epochs
|
aidn
| 2023-06-27T11:39:42Z | 63 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"question-answering",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-27T10:47:14Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: aidn/squadBert3Epochs
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# aidn/squadBert3Epochs
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.8730
- Validation Loss: 1.1031
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 8758, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 1.5485 | 1.1485 | 0 |
| 0.9929 | 1.1031 | 1 |
| 0.8730 | 1.1031 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
maidh/poca-SoccerTwos
|
maidh
| 2023-06-27T10:53:06Z | 17 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"unity-ml-agents",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-06-27T10:52:53Z |
---
tags:
- unity-ml-agents
- ml-agents
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
library_name: ml-agents
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser:**.
1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
2. Step 1: Write your model_id: maidh/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
haddadalwi/multi-qa-mpnet-base-dot-v1-finetuned-squad2-all
|
haddadalwi
| 2023-06-27T07:29:46Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mpnet",
"question-answering",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-27T07:16:35Z |
---
tags:
- generated_from_trainer
model-index:
- name: multi-qa-mpnet-base-dot-v1-finetuned-squad2-all
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# multi-qa-mpnet-base-dot-v1-finetuned-squad2-all
This model is a fine-tuned version of [sentence-transformers/multi-qa-mpnet-base-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0718
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8521 | 1.0 | 840 | 1.3531 |
| 1.2732 | 2.0 | 1680 | 1.0718 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
limcheekin/mpt-7b-storywriter-ct2
|
limcheekin
| 2023-06-27T07:04:45Z | 4 | 0 |
transformers
|
[
"transformers",
"ctranslate2",
"mpt-7b-storywriter",
"quantization",
"int8",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2023-06-01T09:09:40Z |
---
license: apache-2.0
language:
- en
tags:
- ctranslate2
- mpt-7b-storywriter
- quantization
- int8
---
# Model Card for MPT-7B-StoryWriter-65k+ Q8
The model is quantized version of the [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) with int8 quantization.
## Model Details
### Model Description
The model being quantized using [CTranslate2](https://opennmt.net/CTranslate2/) with the following command:
```
ct2-transformers-converter --model mosaicml/mpt-7b-storywriter --output_dir mosaicml/mpt-7b-storywriter-ct2 --copy_files generation_config.json tokenizer.json tokenizer_config.json special_tokens_map.json --quantization int8 --force --low_cpu_mem_usage --trust_remote_code
```
If you want to perform the quantization yourself, you need to install the following dependencies:
```
pip install -qU ctranslate2 transformers[torch] accelerate einops
```
- **Shared by:** Lim Chee Kin
- **License:** Apache 2.0
## How to Get Started with the Model
Use the code below to get started with the model.
```python
import ctranslate2
import transformers
generator = ctranslate2.Generator("limcheekin/mpt-7b-storywriter-ct2")
tokenizer = transformers.AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
prompt = "Long long time ago, "
tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt))
results = generator.generate_batch([tokens], max_length=256, sampling_topk=10)
text = tokenizer.decode(results[0].sequences_ids[0])
```
The code is taken from https://opennmt.net/CTranslate2/guides/transformers.html#mpt.
The key method of the code above is `generate_batch`, you can find out [its supported parameters here](https://opennmt.net/CTranslate2/python/ctranslate2.Generator.html#ctranslate2.Generator.generate_batch).
|
AlgorithmicResearchGroup/flan-t5-xxl-arxiv-math-closed-qa
|
AlgorithmicResearchGroup
| 2023-06-27T04:39:54Z | 13 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"arxiv",
"summarization",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-06-24T16:45:00Z |
---
license: apache-2.0
language:
- en
pipeline_tag: summarization
widget:
- text: What is the peak phase of T-eV?
example_title: Question Answering
tags:
- arxiv
---
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Model Details](#model-details)
2. [Usage](#usage)
3. [Uses](#uses)
4. [Citation](#citation)
# TL;DR
This is a FLAN-T5-XXL model trained on [ArtifactAI/arxiv-math-instruct-50k](https://huggingface.co/datasets/ArtifactAI/arxiv-math-instruct-50k). This model is for research purposes only and ***should not be used in production settings***.
## Model Description
- **Model type:** Language model
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
# Usage
Find below some example scripts on how to use the model in `transformers`:
## Using the Pytorch model
```python
import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
# Load peft config for pre-trained checkpoint etc.
peft_model_id = "ArtifactAI/flant5-xxl-math-full-training-run-one"
config = PeftConfig.from_pretrained(peft_model_id)
# load base LLM model and tokenizer
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, load_in_8bit=True, device_map={"":0})
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load the Lora model
model = PeftModel.from_pretrained(model, peft_model_id, device_map={"":0})
model.eval()
input_ids = tokenizer("What is the peak phase of T-eV?", return_tensors="pt", truncation=True).input_ids.cuda()
# with torch.inference_mode():
outputs = model.generate(input_ids=input_ids, max_new_tokens=1000, do_sample=True, top_p=0.9)
print(f"summary: {tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]}")
```
## Training Data
The model was trained on [ArtifactAI/arxiv-math-instruct-50k](https://huggingface.co/datasets/ArtifactAI/arxiv-math-instruct-50k), a dataset of question/answer pairs. Questions are generated using the t5-base model, while the answers are generated using the GPT-3.5-turbo model.
# Citation
```
@misc{flan-t5-xxl-arxiv-math-zeroshot-qa,
title={flan-t5-xxl-arxiv-math-zeroshot-qa},
author={Matthew Kenney},
year={2023}
}
```
|
microsoft/resnet-152
|
microsoft
| 2023-06-26T19:49:50Z | 19,045 | 12 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"safetensors",
"resnet",
"image-classification",
"vision",
"dataset:imagenet-1k",
"arxiv:1512.03385",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2022-03-16T14:54:22Z |
---
license: apache-2.0
tags:
- vision
- image-classification
datasets:
- imagenet-1k
---
# ResNet-152 v1.5
ResNet model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) by He et al.
Disclaimer: The team releasing ResNet did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
ResNet (Residual Network) is a convolutional neural network that democratized the concepts of residual learning and skip connections. This enables to train much deeper models.
This is ResNet v1.5, which differs from the original model: in the bottleneck blocks which require downsampling, v1 has stride = 2 in the first 1x1 convolution, whereas v1.5 has stride = 2 in the 3x3 convolution. This difference makes ResNet50 v1.5 slightly more accurate (\~0.5% top1) than v1, but comes with a small performance drawback (~5% imgs/sec) according to [Nvidia](https://catalog.ngc.nvidia.com/orgs/nvidia/resources/resnet_50_v1_5_for_pytorch).
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=resnet) to look for
fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
```python
from transformers import AutoFeatureExtractor, ResNetForImageClassification
import torch
from datasets import load_dataset
dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]
feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-152")
model = ResNetForImageClassification.from_pretrained("microsoft/resnet-152")
inputs = feature_extractor(image, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
# model predicts one of the 1000 ImageNet classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label])
```
For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/resnet).
### BibTeX entry and citation info
```bibtex
@inproceedings{he2016deep,
title={Deep residual learning for image recognition},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={770--778},
year={2016}
}
```
|
kalyaniAI/autotrain-autotrain-69874137966
|
kalyaniAI
| 2023-06-26T12:08:29Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"autotrain",
"summarization",
"en",
"dataset:kalyaniAI/autotrain-data-autotrain",
"co2_eq_emissions",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-06-26T12:07:46Z |
---
tags:
- autotrain
- summarization
language:
- en
widget:
- text: "I love AutoTrain"
datasets:
- kalyaniAI/autotrain-data-autotrain
co2_eq_emissions:
emissions: 0.025148621653341533
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 69874137966
- CO2 Emissions (in grams): 0.0251
## Validation Metrics
- Loss: 8.770
- Rouge1: 0.000
- Rouge2: 0.000
- RougeL: 0.000
- RougeLsum: 0.000
- Gen Len: 16.333
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/kalyaniAI/autotrain-autotrain-69874137966
```
|
abelko/abel-alpaca
|
abelko
| 2023-06-26T08:39:42Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-26T08:39:41Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
RashidNLP/NER-Deberta
|
RashidNLP
| 2023-06-26T07:36:07Z | 199 | 6 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"deberta-v2",
"token-classification",
"deberta-v3",
"en",
"dataset:DFKI-SLT/few-nerd",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-05-19T18:28:34Z |
---
language:
- en
metrics:
- accuracy
- f1
library_name: transformers
pipeline_tag: token-classification
tags:
- deberta-v3
datasets:
- DFKI-SLT/few-nerd
license: mit
---
## Deberta for Named Entity Recognition
I used a Pretrained Deberta-v3-base and finetuned it on Few-NERD, A NER dataset that contains over 180k examples and over 4.6 million tokens.
The Token labels are Person, Organisation, Location, Building, Event, Product, Art & Misc.
## How to use the model
```python
from transformers import pipeline
def print_ner(sentences):
"""Cleaning and printing NER results
"""
for sentence in sentences:
last_entity_type = sentence[0]['entity']
last_index = sentence[0]['index']
word = sentence[0]['word']
for i, token in enumerate(sentence):
if (i > 0):
if (token['entity'] == last_entity_type) and (token['index'] == last_index + 1):
word = word + '' + token['word']
else:
word = word.replace('▁', ' ')
print(f"{word[1:]} {last_entity_type}")
word = token['word']
last_entity_type = token['entity']
last_index = token['index']
if i == len(sentence) - 1:
word = word.replace('▁', ' ')
print(f"{word[1:]} {last_entity_type}")
pipe = pipeline(model='RashidNLP/NER-Deberta')
sentence = pipe(["Elon Musk will be at SpaceX's Starbase facility in Boca Chica for the orbital launch of starship next month"])
print_ner(sentence)
```
|
Retrial9842/ppo-cleanrl-LunarLander-v2
|
Retrial9842
| 2023-06-26T05:18:56Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-26T04:26:01Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -139.40 +/- 97.19
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 200000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.9999
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'Retrial9842/ppo-cleanrl-LunarLander-v2'
'batch_size': 512
'minibatch_size': 128}
```
|
cagmfr/q-Taxi-v3
|
cagmfr
| 2023-06-25T15:35:26Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-25T15:25:40Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="cagmfr/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
MonkDalma/xlm-roberta-base-finetuned-panx-en
|
MonkDalma
| 2023-06-24T23:39:45Z | 101 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-06-24T23:37:22Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-en
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.en
split: validation
args: PAN-X.en
metrics:
- name: F1
type: f1
value: 0.6972579742585339
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-panx-en
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3933
- F1: 0.6973
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.1624 | 1.0 | 50 | 0.5666 | 0.4889 |
| 0.516 | 2.0 | 100 | 0.4598 | 0.6326 |
| 0.3813 | 3.0 | 150 | 0.3933 | 0.6973 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
digiplay/ChillyMix_v1
|
digiplay
| 2023-06-24T21:19:54Z | 291 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-23T16:14:13Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/58772?modelVersionId=63220
Original Author's DEMO image :
image detailed link: https://civitai.com/images/701538
|
jobeid1/ppo-LunarLander
|
jobeid1
| 2023-06-24T06:41:32Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-24T06:41:26Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -130.74 +/- 95.24
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'test'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'jobeid1/ppo-LunarLander'
'batch_size': 512
'minibatch_size': 128}
```
|
DionnisB/MOVA
|
DionnisB
| 2023-06-23T11:48:34Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-23T11:27:53Z |
---
license: creativeml-openrail-m
---
|
leons-esposa02/BeedTesting.AI
|
leons-esposa02
| 2023-06-23T05:08:15Z | 0 | 0 |
asteroid
|
[
"asteroid",
"code",
"text-classification",
"en",
"dataset:tiiuae/falcon-refinedweb",
"region:us"
] |
text-classification
| 2023-06-23T05:06:26Z |
---
datasets:
- tiiuae/falcon-refinedweb
language:
- en
metrics:
- character
library_name: asteroid
pipeline_tag: text-classification
tags:
- code
---
|
deandrasetya/indobert-abusive-language-classifier
|
deandrasetya
| 2023-06-23T00:17:37Z | 62 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-03-14T10:14:29Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: indobert-abusive-language-classifier
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# indobert-abusive-language-classifier
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1613
- Train Sparse Categorical Accuracy: 0.9417
- Validation Loss: 0.2973
- Validation Sparse Categorical Accuracy: 0.8857
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
| 0.4496 | 0.7811 | 0.3146 | 0.8671 | 0 |
| 0.2437 | 0.9026 | 0.2959 | 0.8888 | 1 |
| 0.1613 | 0.9417 | 0.2973 | 0.8857 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Dans-Archive/Dans-PersonalityEngine-30b
|
Dans-Archive
| 2023-06-23T00:14:59Z | 52 | 5 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-16T04:25:05Z |
---
language:
- en
---
### Description:
This is a multipurpose chat / chat instruct hybrid model in the same vein as the Pygmalion team's Metharme. It uses a curated pile of training data that has been normalized into a consistent training format. It has been trained on a wide array of one shot instructions, multi round instructions, and role playing scenarios.
The training parameters were suboptimal for the most recent run and I decided to stop after 2 epochs as 3 likely would have overtrained it. I plan on iterating the model and improving it further when I have access to more funds to do so.
### Prompt format:
Metharme
The prompt should start with the cursor on the same line directly after "<|model|>" with no space. The following are all valid formats and can be extended to as many rounds as desired.
```
<|system|>system message here<|user|>user message here<|model|>
```
```
<|system|>system message here<|user|>user message here<|model|>model message<|user|>user message here<|model|>
```
```
<|system|>system message here<|model|>
```
```
<|system|>system message here<|model|>model message<|user|>user message here<|model|>
```
Some example prompts:
```
<|system|>The following is a transcript between a helpful assistant and a user.<|user|>Why is the sky blue?<|model|>
```
```
<|system|>You are a Virtual Story Generator. You take the user's input and create an excellent and captivating story that goes in that direction. Use an abundance of sensory descriptions and eloquent prose.<|user|>Alpha Centauri has fallen, to the bears. This is a point of view tale about a soldier on the ground.<|model|>
```
```
<|system|>You are a professional editor with decades of experience, help the user with any task they have for you.<|user|>Can you rewrite this to flow better? "I knew I probably shouldnt have done that but oh well"<|model|>
```
More will be added at a later date.
### Perplexity Benchmarks:
- TBA
### Training information:
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="150" height="24"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- GPTQ 4 bit LoRA
- 2 Epochs
- 64 / 32 R / A
- 2048 Cutoff
- 42 hours on 1x RTX 4090
### Data used in training:
- TBA
### Models used:
For training:
https://huggingface.co/PocketDoc/llama-30b-gptq-4bit-128g
For merging:
https://huggingface.co/PocketDoc/Dans-PersonalityEngine-30b-LoRA
and
https://huggingface.co/huggyllama/llama-30b
### Disclaimer:
It has not been aligned and no warranty is given for the quality or safety of its outputs.
|
Inzamam567/Useless_Cyan-World
|
Inzamam567
| 2023-06-22T20:57:16Z | 0 | 2 | null |
[
"license:other",
"region:us"
] | null | 2023-04-03T14:39:20Z |
---
license: other
duplicated_from: Bobybb/zziJnIyMstnaP
---
|
Tese/Tese
|
Tese
| 2023-06-22T19:05:07Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-19T17:41:43Z |
---
license: bigscience-openrail-m
---
|
swl-models/CuteYukiMix-v2.0
|
swl-models
| 2023-06-22T14:47:21Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-22T14:34:08Z |
---
license: creativeml-openrail-m
---
|
bluemoonwj/my_awesome_eli5_clm-model
|
bluemoonwj
| 2023-06-22T01:34:22Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-22T00:53:06Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_clm-model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7297
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.8699 | 1.0 | 1109 | 3.7485 |
| 3.7734 | 2.0 | 2218 | 3.7342 |
| 3.7371 | 3.0 | 3327 | 3.7297 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
|
usakha/Pegasus_bigPatent_model
|
usakha
| 2023-06-21T19:34:18Z | 8 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"pegasus",
"text2text-generation",
"summarization",
"dataset:big_patent",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-06-21T13:49:45Z |
---
datasets:
- big_patent
metrics:
- rouge
- bleu
pipeline_tag: summarization
---
|
EleutherAI/gpt-j-6b
|
EleutherAI
| 2023-06-21T14:33:36Z | 256,005 | 1,477 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"gptj",
"text-generation",
"causal-lm",
"en",
"dataset:EleutherAI/pile",
"arxiv:2104.09864",
"arxiv:2101.00027",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:04Z |
---
language:
- en
tags:
- pytorch
- causal-lm
license: apache-2.0
datasets:
- EleutherAI/pile
---
# GPT-J 6B
## Model Description
GPT-J 6B is a transformer model trained using Ben Wang's [Mesh Transformer JAX](https://github.com/kingoflolz/mesh-transformer-jax/). "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters.
<figure>
| Hyperparameter | Value |
|----------------------|------------|
| \\(n_{parameters}\\) | 6053381344 |
| \\(n_{layers}\\) | 28* |
| \\(d_{model}\\) | 4096 |
| \\(d_{ff}\\) | 16384 |
| \\(n_{heads}\\) | 16 |
| \\(d_{head}\\) | 256 |
| \\(n_{ctx}\\) | 2048 |
| \\(n_{vocab}\\) | 50257/50400† (same tokenizer as GPT-2/3) |
| Positional Encoding | [Rotary Position Embedding (RoPE)](https://arxiv.org/abs/2104.09864) |
| RoPE Dimensions | [64](https://github.com/kingoflolz/mesh-transformer-jax/blob/f2aa66e0925de6593dcbb70e72399b97b4130482/mesh_transformer/layers.py#L223) |
<figcaption><p><strong>*</strong> Each layer consists of one feedforward block and one self attention block.</p>
<p><strong>†</strong> Although the embedding matrix has a size of 50400, only 50257 entries are used by the GPT-2 tokenizer.</p></figcaption></figure>
The model consists of 28 layers with a model dimension of 4096, and a feedforward dimension of 16384. The model
dimension is split into 16 heads, each with a dimension of 256. Rotary Position Embedding (RoPE) is applied to 64
dimensions of each head. The model is trained with a tokenization vocabulary of 50257, using the same set of BPEs as
GPT-2/GPT-3.
## Intended Use and Limitations
GPT-J learns an inner representation of the English language that can be used to
extract features useful for downstream tasks. The model is best at what it was
pretrained for however, which is generating text from a prompt.
### Out-of-scope use
GPT-J-6B is **not** intended for deployment without fine-tuning, supervision,
and/or moderation. It is not a in itself a product and cannot be used for
human-facing interactions. For example, the model may generate harmful or
offensive text. Please evaluate the risks associated with your particular use case.
GPT-J-6B was trained on an English-language only dataset, and is thus **not**
suitable for translation or generating text in other languages.
GPT-J-6B has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means GPT-J-6B will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “follow” human instructions.
### Limitations and Biases
The core functionality of GPT-J is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work. When prompting GPT-J it is important to remember that the statistically most likely next token is often not the token that produces the most "accurate" text. Never depend upon GPT-J to produce factually accurate output.
GPT-J was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending upon use case GPT-J may produce socially unacceptable text. See [Sections 5 and 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a more detailed analysis of the biases in the Pile.
As with all language models, it is hard to predict in advance how GPT-J will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.
### How to use
This model can be easily loaded using the `AutoModelForCausalLM` functionality:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-j-6B")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-j-6B")
```
## Training data
GPT-J 6B was trained on [the Pile](https://pile.eleuther.ai), a large-scale curated dataset created by [EleutherAI](https://www.eleuther.ai).
## Training procedure
This model was trained for 402 billion tokens over 383,500 steps on TPU v3-256 pod. It was trained as an autoregressive language model, using cross-entropy loss to maximize the likelihood of predicting the next token correctly.
## Evaluation results
<figure>
| Model | Public | Training FLOPs | LAMBADA PPL ↓ | LAMBADA Acc ↑ | Winogrande ↑ | Hellaswag ↑ | PIQA ↑ | Dataset Size (GB) |
|--------------------------|-------------|----------------|--- |--- |--- |--- |--- |-------------------|
| Random Chance | ✓ | 0 | ~a lot | ~0% | 50% | 25% | 25% | 0 |
| GPT-3 Ada‡ | ✗ | ----- | 9.95 | 51.6% | 52.9% | 43.4% | 70.5% | ----- |
| GPT-2 1.5B | ✓ | ----- | 10.63 | 51.21% | 59.4% | 50.9% | 70.8% | 40 |
| GPT-Neo 1.3B‡ | ✓ | 3.0e21 | 7.50 | 57.2% | 55.0% | 48.9% | 71.1% | 825 |
| Megatron-2.5B* | ✗ | 2.4e21 | ----- | 61.7% | ----- | ----- | ----- | 174 |
| GPT-Neo 2.7B‡ | ✓ | 6.8e21 | 5.63 | 62.2% | 56.5% | 55.8% | 73.0% | 825 |
| GPT-3 1.3B*‡ | ✗ | 2.4e21 | 5.44 | 63.6% | 58.7% | 54.7% | 75.1% | ~800 |
| GPT-3 Babbage‡ | ✗ | ----- | 5.58 | 62.4% | 59.0% | 54.5% | 75.5% | ----- |
| Megatron-8.3B* | ✗ | 7.8e21 | ----- | 66.5% | ----- | ----- | ----- | 174 |
| GPT-3 2.7B*‡ | ✗ | 4.8e21 | 4.60 | 67.1% | 62.3% | 62.8% | 75.6% | ~800 |
| Megatron-11B† | ✓ | 1.0e22 | ----- | ----- | ----- | ----- | ----- | 161 |
| **GPT-J 6B‡** | **✓** | **1.5e22** | **3.99** | **69.7%** | **65.3%** | **66.1%** | **76.5%** | **825** |
| GPT-3 6.7B*‡ | ✗ | 1.2e22 | 4.00 | 70.3% | 64.5% | 67.4% | 78.0% | ~800 |
| GPT-3 Curie‡ | ✗ | ----- | 4.00 | 69.3% | 65.6% | 68.5% | 77.9% | ----- |
| GPT-3 13B*‡ | ✗ | 2.3e22 | 3.56 | 72.5% | 67.9% | 70.9% | 78.5% | ~800 |
| GPT-3 175B*‡ | ✗ | 3.1e23 | 3.00 | 76.2% | 70.2% | 78.9% | 81.0% | ~800 |
| GPT-3 Davinci‡ | ✗ | ----- | 3.0 | 75% | 72% | 78% | 80% | ----- |
<figcaption><p>Models roughly sorted by performance, or by FLOPs if not available.</p>
<p><strong>*</strong> Evaluation numbers reported by their respective authors. All other numbers are provided by
running <a href="https://github.com/EleutherAI/lm-evaluation-harness/"><code>lm-evaluation-harness</code></a> either with released
weights or with API access. Due to subtle implementation differences as well as different zero shot task framing, these
might not be directly comparable. See <a href="https://blog.eleuther.ai/gpt3-model-sizes/">this blog post</a> for more
details.</p>
<p><strong>†</strong> Megatron-11B provides no comparable metrics, and several implementations using the released weights do not
reproduce the generation quality and evaluations. (see <a href="https://github.com/huggingface/transformers/pull/10301">1</a>
<a href="https://github.com/pytorch/fairseq/issues/2358">2</a> <a href="https://github.com/pytorch/fairseq/issues/2719">3</a>)
Thus, evaluation was not attempted.</p>
<p><strong>‡</strong> These models have been trained with data which contains possible test set contamination. The OpenAI GPT-3 models
failed to deduplicate training data for certain test sets, while the GPT-Neo models as well as this one is
trained on the Pile, which has not been deduplicated against any test sets.</p></figcaption></figure>
## Citation and Related Information
### BibTeX entry
To cite this model:
```bibtex
@misc{gpt-j,
author = {Wang, Ben and Komatsuzaki, Aran},
title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
year = 2021,
month = May
}
```
To cite the codebase that trained this model:
```bibtex
@misc{mesh-transformer-jax,
author = {Wang, Ben},
title = {{Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX}},
howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
year = 2021,
month = May
}
```
If you use this model, we would love to hear about it! Reach out on [GitHub](https://github.com/kingoflolz/mesh-transformer-jax), Discord, or shoot Ben an email.
## Acknowledgements
This project would not have been possible without compute generously provided by Google through the
[TPU Research Cloud](https://sites.research.google/trc/), as well as the Cloud TPU team for providing early access to the [Cloud TPU VM](https://cloud.google.com/blog/products/compute/introducing-cloud-tpu-vms) Alpha.
Thanks to everyone who have helped out one way or another (listed alphabetically):
- [James Bradbury](https://twitter.com/jekbradbury) for valuable assistance with debugging JAX issues.
- [Stella Biderman](https://www.stellabiderman.com), [Eric Hallahan](https://twitter.com/erichallahan), [Kurumuz](https://github.com/kurumuz/), and [Finetune](https://github.com/finetuneanon/) for converting the model to be compatible with the `transformers` package.
- [Leo Gao](https://twitter.com/nabla_theta) for running zero shot evaluations for the baseline models for the table.
- [Laurence Golding](https://github.com/researcher2/) for adding some features to the web demo.
- [Aran Komatsuzaki](https://twitter.com/arankomatsuzaki) for advice with experiment design and writing the blog posts.
- [Janko Prester](https://github.com/jprester/) for creating the web demo frontend.
|
hassansoliman/falcon-40b-qlora-utterance-adaptations_v5
|
hassansoliman
| 2023-06-21T13:03:56Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-21T13:03:09Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
moka-ai/m3e-large
|
moka-ai
| 2023-06-21T11:25:23Z | 2,209 | 205 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"embedding",
"text-embedding",
"zh",
"en",
"region:us"
] | null | 2023-06-21T09:07:12Z |
---
language:
- zh
- en
tags:
- embedding
- text-embedding
library_name: sentence-transformers
---
# M3E Models
[m3e-small](https://huggingface.co/moka-ai/m3e-small) | [m3e-base](https://huggingface.co/moka-ai/m3e-base) | [m3e-large](https://huggingface.co/moka-ai/m3e-large)
M3E 是 Moka Massive Mixed Embedding 的缩写
- Moka，此模型由 MokaAI 训练，开源和评测，训练脚本使用 [uniem](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/train_m3e.py) ，评测 BenchMark 使用 [MTEB-zh](https://github.com/wangyuxinwhy/uniem/tree/main/mteb-zh)
- Massive，此模型通过**千万级** (2200w+) 的中文句对数据集进行训练
- Mixed，此模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索
- Embedding，此模型是文本嵌入模型，可以将自然语言转换成稠密的向量
## 更新说明
- 2023.06.14，添加了三个中文开源文本嵌入模型到评测中，包括 UER, ErLangShen, DMetaSoul
- 2023.06.08，添加检索任务的评测结果，在 T2Ranking 1W 中文数据集上，m3e-base 在 ndcg@10 上达到了 0.8004，超过了 openai-ada-002 的 0.7786
- 2023.06.07，添加文本分类任务的评测结果，在 6 种文本分类数据集上，m3e-base 在 accuracy 上达到了 0.6157，超过了 openai-ada-002 的 0.5956
## 模型对比
| | 参数数量 | 维度 | 中文 | 英文 | s2s | s2p | s2c | 开源 | 兼容性 | s2s Acc | s2p ndcg@10 |
| --------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- | ---- | ---------- | ------------ | -------- |
| m3e-small | 24M | 512 | 是 | 否 | 是 | 否 | 否 | 是 | 优 | 0.5834 | 0.7262 |
| m3e-base | 110M | 768 | 是 | 是 | 是 | 是 | 否 | 是 | 优 | 0.6157 | **0.8004** |
| m3e-large | 340M | 768 | 是 | 否 | 是 | 是 | 否 | 是 | 优 | **0.6231** | 0.7974 |
| text2vec | 110M | 768 | 是 | 否 | 是 | 否 | 否 | 是 | 优 | 0.5755 | 0.6346 |
| openai-ada-002 | 未知 | 1536 | 是 | 是 | 是 | 是 | 是 | 否 | 优 | 0.5956 | 0.7786 |
说明：
- s2s, 即 sentence to sentence ，代表了同质文本之间的嵌入能力，适用任务：文本相似度，重复问题检测，文本分类等
- s2p, 即 sentence to passage ，代表了异质文本之间的嵌入能力，适用任务：文本检索，GPT 记忆模块等
- s2c, 即 sentence to code ，代表了自然语言和程序语言之间的嵌入能力，适用任务：代码检索
- 兼容性，代表了模型在开源社区中各种项目被支持的程度，由于 m3e 和 text2vec 都可以直接通过 sentence-transformers 直接使用，所以和 openai 在社区的支持度上相当
- ACC & ndcg@10，详情见下方的评测
Tips:
- 使用场景主要是中文，少量英文的情况，建议使用 m3e 系列的模型
- 多语言使用场景，并且不介意数据隐私的话，我建议使用 openai text-embedding-ada-002
- 代码检索场景，推荐使用 openai text-embedding-ada-002
- 文本检索场景，请使用具备文本检索能力的模型，只在 S2S 上训练的文本嵌入模型，没有办法完成文本检索任务
## 使用方式
您需要先安装 sentence-transformers
```bash
pip install -U sentence-transformers
```
安装完成后，您可以使用以下代码来使用 M3E Models
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('moka-ai/m3e-base')
#Our sentences we like to encode
sentences = [
'* Moka 此文本嵌入模型由 MokaAI 训练并开源，训练脚本使用 uniem',
'* Massive 此文本嵌入模型通过**千万级**的中文句对数据集进行训练',
'* Mixed 此文本嵌入模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索，ALL in one'
]
#Sentences are encoded by calling model.encode()
embeddings = model.encode(sentences)
#Print the embeddings
for sentence, embedding in zip(sentences, embeddings):
print("Sentence:", sentence)
print("Embedding:", embedding)
print("")
```
M3E 系列的所有模型在设计的时候就考虑到完全兼容 [sentence-transformers](https://www.sbert.net/) ，所以你可以通过**替换名称字符串**的方式在所有支持 sentence-transformers 的项目中**无缝**使用 M3E Models，比如 [chroma](https://docs.trychroma.com/getting-started), [guidance](https://github.com/microsoft/guidance), [semantic-kernel](https://github.com/microsoft/semantic-kernel) 。
## 训练方案
M3E 使用 in-batch 负采样的对比学习的方式在句对数据集进行训练，为了保证 in-batch 负采样的效果，我们使用 A100 80G 来最大化 batch-size，并在共计 2200W+ 的句对数据集上训练了 1 epoch。训练脚本使用 [uniem](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/train_m3e.py)，您可以在这里查看具体细节。
## 特性
- 中文训练集，M3E 在大规模句对数据集上的训练，包含中文百科，金融，医疗，法律，新闻，学术等多个领域共计 2200W 句对样本，数据集详见 [M3E 数据集](#M3E数据集)
- 英文训练集，M3E 使用 MEDI 145W 英文三元组数据集进行训练，数据集详见 [MEDI 数据集](https://drive.google.com/file/d/1vZ5c2oJNonGOvXzppNg5mHz24O6jcc52/view)，此数据集由 [instructor team](https://github.com/HKUNLP/instructor-embedding) 提供
- 指令数据集，M3E 使用了 300W + 的指令微调数据集，这使得 M3E 对文本编码的时候可以遵从指令，这部分的工作主要被启发于 [instructor-embedding](https://github.com/HKUNLP/instructor-embedding)
- 基础模型，M3E 使用 hfl 实验室的 [Roberta](https://huggingface.co/hfl/chinese-roberta-wwm-ext) 系列模型进行训练，目前提供 small、base和large三个版本，大家则需选用
- ALL IN ONE，M3E 旨在提供一个 ALL IN ONE 的文本嵌入模型，不仅支持同质句子相似度判断，还支持异质文本检索，你只需要一个模型就可以覆盖全部的应用场景，未来还会支持代码检索
## 评测
- 评测模型，[text2vec](https://github.com/shibing624/text2vec), m3e-base, m3e-small, openai text-embedding-ada-002, [DMetaSoul](https://huggingface.co/DMetaSoul/sbert-chinese-general-v2), [UER](https://huggingface.co/uer/sbert-base-chinese-nli), [ErLangShen](https://huggingface.co/IDEA-CCNL/Erlangshen-SimCSE-110M-Chinese)
- 评测脚本，具体参考 [MTEB-zh] (https://github.com/wangyuxinwhy/uniem/blob/main/mteb-zh)
### 文本分类
- 数据集选择，选择开源在 HuggingFace 上的 6 种文本分类数据集，包括新闻、电商评论、股票评论、长文本等
- 评测方式，使用 MTEB 的方式进行评测，报告 Accuracy。
| | text2vec | m3e-small | m3e-base | m3e-large | openai | DMetaSoul | uer | erlangshen |
| ----------------- | -------- | --------- | -------- | ------ | ----------- | ------- | ----------- | ----------- |
| TNews | 0.43 | 0.4443 | 0.4827 | **0.4866** | 0.4594 | 0.3084 | 0.3539 | 0.4361 |
| JDIphone | 0.8214 | 0.8293 | 0.8533 | **0.8692** | 0.746 | 0.7972 | 0.8283 | 0.8356 |
| GubaEastmony | 0.7472 | 0.712 | 0.7621 | 0.7663 | 0.7574 | 0.735 | 0.7534 | **0.7787** |
| TYQSentiment | 0.6099 | 0.6596 | 0.7188 | **0.7247** | 0.68 | 0.6437 | 0.6662 | 0.6444 |
| StockComSentiment | 0.4307 | 0.4291 | 0.4363 | 0.4475 | **0.4819** | 0.4309 | 0.4555 | 0.4482 |
| IFlyTek | 0.414 | 0.4263 | 0.4409 | 0.4445 | **0.4486** | 0.3969 | 0.3762 | 0.4241 |
| Average | 0.5755 | 0.5834 | 0.6157 | **0.6231** | 0.5956 | 0.552016667 | 0.57225 | 0.594516667 |
### 检索排序
#### T2Ranking 1W
- 数据集选择，使用 [T2Ranking](https://github.com/THUIR/T2Ranking/tree/main) 数据集，由于 T2Ranking 的数据集太大，openai 评测起来的时间成本和 api 费用有些高，所以我们只选择了 T2Ranking 中的前 10000 篇文章
- 评测方式，使用 MTEB 的方式进行评测，报告 map@1, map@10, mrr@1, mrr@10, ndcg@1, ndcg@10
- 注意！从实验结果和训练方式来看，除了 M3E 模型和 openai 模型外，其余模型都没有做检索任务的训练，所以结果仅供参考。
| | text2vec | openai-ada-002 | m3e-small | m3e-base | m3e-large | DMetaSoul | uer | erlangshen |
| ------- | -------- | -------------- | --------- | -------- | --------- | ------- | ---------- | ---------- |
| map@1 | 0.4684 | 0.6133 | 0.5574 | **0.626** | 0.6256 | 0.25203 | 0.08647 | 0.25394 |
| map@10 | 0.5877 | 0.7423 | 0.6878 | **0.7656** | 0.7627 | 0.33312 | 0.13008 | 0.34714 |
| mrr@1 | 0.5345 | 0.6931 | 0.6324 | 0.7047 | **0.7063** | 0.29258 | 0.10067 | 0.29447 |
| mrr@10 | 0.6217 | 0.7668 | 0.712 | **0.7841** | 0.7827 | 0.36287 | 0.14516 | 0.3751 |
| ndcg@1 | 0.5207 | 0.6764 | 0.6159 | 0.6881 | **0.6884** | 0.28358 | 0.09748 | 0.28578 |
| ndcg@10 | 0.6346 | 0.7786 | 0.7262 | **0.8004** | 0.7974 | 0.37468 | 0.15783 | 0.39329 |
#### T2Ranking
- 数据集选择，使用 T2Ranking，刨除 openai-ada-002 模型后，我们对剩余的三个模型，进行 T2Ranking 10W 和 T2Ranking 50W 的评测。（T2Ranking 评测太耗内存了... 128G 都不行）
- 评测方式，使用 MTEB 的方式进行评测，报告 ndcg@10
| | text2vec | m3e-small | m3e-base |
| ------- | -------- | --------- | -------- |
| t2r-1w | 0.6346 | 0.72621 | **0.8004** |
| t2r-10w | 0.44644 | 0.5251 | **0.6263** |
| t2r-50w | 0.33482 | 0.38626 | **0.47364** |
说明：
- 检索排序对于 text2vec 并不公平，因为 text2vec 在训练的时候没有使用过检索相关的数据集，所以没有办法很好的完成检索任务也是正常的。
## M3E数据集
如果您想要使用这些数据集，你可以在 [uniem process_zh_datasets](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/process_zh_datasets.py) 中找到加载 huggingface 数据集的脚本，非 huggingface 数据集需要您根据下方提供的链接自行下载和处理。
| 数据集名称 | 领域 | 数量 | 任务类型 | Prompt | 质量 | 数据提供者 | 说明 | 是否开源/研究使用 | 是否商用 | 脚本 | Done | URL | 是否同质 |
| -------------------- | ---- | --------- | ----------------- | ------ | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | ----------------- | -------- | ---- | ---- | ------------------------------------------------------------ | -------- |
| cmrc2018 | 百科 | 14,363 | 问答 | 问答 | 优 | Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu | https://github.com/ymcui/cmrc2018/blob/master/README_CN.md 专家标注的基于维基百科的中文阅读理解数据集，将问题和上下文视为正例 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/cmrc2018 | 否 |
| belle_2m | 百科 | 2,000,000 | 指令微调 | 无 | 优 | LianjiaTech/BELLE | belle 的指令微调数据集，使用 self instruct 方法基于 gpt3.5 生成 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/BelleGroup/train_2M_CN | 否 |
| firefily | 百科 | 1,649,399 | 指令微调 | 无 | 优 | YeungNLP | Firefly（流萤） 是一个开源的中文对话式大语言模型，使用指令微调（Instruction Tuning）在中文数据集上进行调优。使用了词表裁剪、ZeRO等技术，有效降低显存消耗和提高训练效率。 在训练中，我们使用了更小的模型参数量，以及更少的计算资源。 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M | 否 |
| alpaca_gpt4 | 百科 | 48,818 | 指令微调 | 无 | 优 | Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao | 本数据集是参考Alpaca方法基于GPT4得到的self-instruct数据，约5万条。 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/alpaca-zh | 否 |
| zhihu_kol | 百科 | 1,006,218 | 问答 | 问答 | 优 | wangrui6 | 知乎问答 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/wangrui6/Zhihu-KOL | 否 |
| hc3_chinese | 百科 | 39,781 | 问答 | 问答 | 良 | Hello-SimpleAI | 问答数据，包括人工回答和 GPT 回答 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese | 否 |
| amazon_reviews_multi | 电商 | 210,000 | 问答 文本分类 | 摘要 | 优 | 亚马逊 | 亚马逊产品评论数据集 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/amazon_reviews_multi/viewer/zh/train?row=8 | 否 |
| mlqa | 百科 | 85,853 | 问答 | 问答 | 良 | patrickvonplaten | 一个用于评估跨语言问答性能的基准数据集 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/mlqa/viewer/mlqa-translate-train.zh/train?p=2 | 否 |
| xlsum | 新闻 | 93,404 | 摘要 | 摘要 | 良 | BUET CSE NLP Group | BBC的专业注释文章摘要对 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/csebuetnlp/xlsum/viewer/chinese_simplified/train?row=259 | 否 |
| ocnli | 口语 | 17,726 | 自然语言推理 | 推理 | 良 | Thomas Wolf | 自然语言推理数据集 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/clue/viewer/ocnli | 是 |
| BQ | 金融 | 60,000 | 文本分类 | 相似 | 良 | Intelligent Computing Research Center, Harbin Institute of Technology(Shenzhen) | http://icrc.hitsz.edu.cn/info/1037/1162.htm BQ 语料库包含来自网上银行自定义服务日志的 120，000 个问题对。它分为三部分：100，000 对用于训练，10，000 对用于验证，10，000 对用于测试。 数据提供者： 哈尔滨工业大学（深圳）智能计算研究中心 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/nli_zh/viewer/BQ | 是 |
| lcqmc | 口语 | 149,226 | 文本分类 | 相似 | 良 | Ming Xu | 哈工大文本匹配数据集，LCQMC 是哈尔滨工业大学在自然语言处理国际顶会 COLING2018 构建的问题语义匹配数据集，其目标是判断两个问题的语义是否相同 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/nli_zh/viewer/LCQMC/train | 是 |
| paws-x | 百科 | 23,576 | 文本分类 | 相似 | 优 | Bhavitvya Malik | PAWS Wiki中的示例 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/paws-x/viewer/zh/train | 是 |
| wiki_atomic_edit | 百科 | 1,213,780 | 平行语义 | 相似 | 优 | abhishek thakur | 基于中文维基百科的编辑记录收集的数据集 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/wiki_atomic_edits | 是 |
| chatmed_consult | 医药 | 549,326 | 问答 | 问答 | 优 | Wei Zhu | 真实世界的医学相关的问题，使用 gpt3.5 进行回答 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset | 否 |
| webqa | 百科 | 42,216 | 问答 | 问答 | 优 | suolyer | 百度于2016年开源的数据集，数据来自于百度知道；格式为一个问题多篇意思基本一致的文章，分为人为标注以及浏览器检索；数据整体质量中，因为混合了很多检索而来的文章 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/suolyer/webqa/viewer/suolyer--webqa/train?p=3 | 否 |
| dureader_robust | 百科 | 65,937 | 机器阅读理解 问答 | 问答 | 优 | 百度 | DuReader robust旨在利用真实应用中的数据样本来衡量阅读理解模型的鲁棒性，评测模型的过敏感性、过稳定性以及泛化能力，是首个中文阅读理解鲁棒性数据集。 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/PaddlePaddle/dureader_robust/viewer/plain_text/train?row=96 | 否 |
| csl | 学术 | 395,927 | 语料 | 摘要 | 优 | Yudong Li, Yuqing Zhang, Zhe Zhao, Linlin Shen, Weijie Liu, Weiquan Mao and Hui Zhang | 提供首个中文科学文献数据集（CSL），包含 396,209 篇中文核心期刊论文元信息 （标题、摘要、关键词、学科、门类）。CSL 数据集可以作为预训练语料，也可以构建许多NLP任务，例如文本摘要（标题预测）、 关键词生成和文本分类等。 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/neuclir/csl | 否 |
| miracl-corpus | 百科 | 4,934,368 | 语料 | 摘要 | 优 | MIRACL | The corpus for each language is prepared from a Wikipedia dump, where we keep only the plain text and discard images, tables, etc. Each article is segmented into multiple passages using WikiExtractor based on natural discourse units (e.g., \n\n in the wiki markup). Each of these passages comprises a "document" or unit of retrieval. We preserve the Wikipedia article title of each passage. | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/miracl/miracl-corpus | 否 |
| lawzhidao | 法律 | 36,368 | 问答 | 问答 | 优 | 和鲸社区-Ustinian | 百度知道清洗后的法律问答 | 是 | 是 | 否 | 是 | https://www.heywhale.com/mw/dataset/5e953ca8e7ec38002d02fca7/content | 否 |
| CINLID | 成语 | 34,746 | 平行语义 | 相似 | 优 | 高长宽 | 中文成语语义推理数据集（Chinese Idioms Natural Language Inference Dataset）收集了106832条由人工撰写的成语对（含少量歇后语、俗语等短文本），通过人工标注的方式进行平衡分类，标签为entailment、contradiction和neutral，支持自然语言推理（NLI）的任务。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=39 | 是 |
| DuSQL | SQL | 25,003 | NL2SQL | SQL | 优 | 百度 | DuSQL是一个面向实际应用的数据集，包含200个数据库，覆盖了164个领域，问题覆盖了匹配、计算、推理等实际应用中常见形式。该数据集更贴近真实应用场景，要求模型领域无关、问题无关，且具备计算推理等能力。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=13 | 否 |
| Zhuiyi-NL2SQL | SQL | 45,918 | NL2SQL | SQL | 优 | 追一科技 刘云峰 | NL2SQL是一个多领域的简单数据集，其主要包含匹配类型问题。该数据集主要验证模型的泛化能力，其要求模型具有较强的领域泛化能力、问题泛化能力。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=12 | 否 |
| Cspider | SQL | 7,785 | NL2SQL | SQL | 优 | 西湖大学 张岳 | CSpider是一个多语言数据集，其问题以中文表达，数据库以英文存储，这种双语模式在实际应用中也非常常见，尤其是数据库引擎对中文支持不好的情况下。该数据集要求模型领域无关、问题无关，且能够实现多语言匹配。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=11 | 否 |
| news2016zh | 新闻 | 2,507,549 | 语料 | 摘要 | 良 | Bright Xu | 包含了250万篇新闻。新闻来源涵盖了6.3万个媒体，含标题、关键词、描述、正文。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| baike2018qa | 百科 | 1,470,142 | 问答 | 问答 | 良 | Bright Xu | 含有150万个预先过滤过的、高质量问题和答案，每个问题属于一个类别。总共有492个类别，其中频率达到或超过10次的类别有434个。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| webtext2019zh | 百科 | 4,258,310 | 问答 | 问答 | 优 | Bright Xu | 含有410万个预先过滤过的、高质量问题和回复。每个问题属于一个【话题】，总共有2.8万个各式话题，话题包罗万象。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| SimCLUE | 百科 | 775,593 | 平行语义 | 相似 | 良 | 数据集合，请在 simCLUE 中查看 | 整合了中文领域绝大多数可用的开源的语义相似度和自然语言推理的数据集，并重新做了数据拆分和整理。 | 是 | 否 | 否 | 是 | https://github.com/CLUEbenchmark/SimCLUE | 是 |
| Chinese-SQuAD | 新闻 | 76,449 | 机器阅读理解 | 问答 | 优 | junzeng-pluto | 中文机器阅读理解数据集，通过机器翻译加人工校正的方式从原始Squad转换而来 | 是 | 否 | 否 | 是 | https://github.com/pluto-junzeng/ChineseSquad | 否 |
## 计划表
- [x] 完成 MTEB 中文评测 BenchMark, [MTEB-zh](https://github.com/wangyuxinwhy/uniem/tree/main/mteb-zh)
- [ ] 完成 Large 模型的训练和开源
- [ ] 完成支持代码检索的模型
- [ ] 对 M3E 数据集进行清洗，保留高质量的部分，组成 m3e-hq，并在 huggingface 上开源
- [ ] 在 m3e-hq 的数据集上补充 hard negative 的样本及相似度分数，组成 m3e-hq-with-score，并在 huggingface 上开源
- [ ] 在 m3e-hq-with-score 上通过 [cosent loss](https://github.com/wangyuxinwhy/uniem/blob/main/uniem/criteria.py#LL24C39-L24C39) loss 进行训练并开源模型，CoSent 原理参考这篇[博客](https://kexue.fm/archives/8847)
- [ ] 开源商用版本的 M3E models
## 致谢
感谢开源社区提供的中文语料，感谢所有在此工作中提供帮助的人们，希望中文社区越来越好，共勉！
## License
M3E models 使用的数据集中包括大量非商用的数据集，所以 M3E models 也是非商用的，仅供研究使用。不过我们已经在 M3E 数据集上标识了商用和非商用的数据集，您可以根据自己的需求自行训练。
## Citation
Please cite this model using the following format:
```
@software {Moka Massive Mixed Embedding,
author = {Wang Yuxin,Sun Qingxuan,He sicheng},
title = {M3E: Moka Massive Mixed Embedding Model},
year = {2023}
}
```
|
wordcab/whisper-large-int8-he
|
wordcab
| 2023-06-21T08:47:20Z | 1 | 0 |
transformers
|
[
"transformers",
"he",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2023-06-20T15:35:55Z |
---
license: apache-2.0
language:
- he
---
This is a ctranslate2 `int8` version of the [Shiry/whisper-large-v2-he](https://huggingface.co/Shiry/whisper-large-v2-he) model.
|
ThuTrang/distilbert-base-uncased-finetuned-imdb
|
ThuTrang
| 2023-06-20T20:38:14Z | 124 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"fill-mask",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-19T23:36:07Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
model-index:
- name: distilbert-base-uncased-finetuned-imdb
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-imdb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
allenai/open-instruct-baize-13b
|
allenai
| 2023-06-20T17:44:30Z | 18 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"arxiv:2306.04751",
"arxiv:2302.13971",
"arxiv:2304.01196",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-07T17:24:03Z |
---
language:
- en
---
# Open-Instruct Baize 13B
This model is a 13B LLaMa model finetuned on the Baize dataset. *Please note this is a model diff - see below for usage instructions*.
This was trained as part of the paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://arxiv.org/abs/2306.04751).
The codebase used to train and evaluate this model can be found at [https://github.com/allenai/open-instruct](https://github.com/allenai/open-instruct).
This model is licensed under the AI model license given in LICENSE.txt along with the original Llama license (llama_license.txt).
## Usage
We assume you have access to a LLaMa model in HF format already. You can find details on getting access and converting the model here:
[https://huggingface.co/docs/transformers/main/model_doc/llama](https://huggingface.co/docs/transformers/main/model_doc/llama)
Clone [https://github.com/allenai/open-instruct](https://github.com/allenai/open-instruct) and install the required dependencies, or just copy `scripts/weight_diff.py`
and install the minimal requirements listed in `weight-diff-requirements.txt`. Then download or clone this model diff to the same machine.
Then, run:
```bash
python scripts/weight_diff.py recover --path_raw ${hf_llama_path} --path_tuned ${output_path} --path_diff ${diff_location}
```
And you will have a recovered model! Note this takes up a decent amount of RAM, especially for the larger models.
## Input Format
The model is trained to use the following format (note the newlines):
```
<|user|>
Your message here!
<|assistant|>
```
For best results, format all inputs in this manner. **Make sure to include a newline after `<|assistant|>`, this can affect generation quality quite a bit.**
## Performance
Here is the performance of this model across benchmarks explored in our paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://arxiv.org/abs/2306.04751):
| MMLU 0-shot | MMLU 5-shot | GSM Direct | GSM CoT | BBH Direct | BBH CoT | TydiQA Gold-Passage | TydiQA Closed-book | Codex-Eval Pass@1 | Codex-Eval Pass@10 | AlpacaFarm vs Davinci-003 | Average |
|:-----------:|:-----------:|:----------:|:-------:|:----------:|:-------:|:-------------------:|:------------------:|:-----------------:|:------------------:|:-------------------------:|---------|
| 43.5 | 41.5 | 4.5 | 8.5 | 35.3 | 36.7 | 33.9 | 9.0 | 14.5 | 27.3 | 28.7 | 26.0 |
If you use this model, please cite our work, the llama paper, and the original dataset:
```
@misc{wang2023far,
title={How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources},
author={Yizhong Wang and Hamish Ivison and Pradeep Dasigi and Jack Hessel and Tushar Khot and Khyathi Raghavi Chandu and David Wadden and Kelsey MacMillan and Noah A. Smith and Iz Beltagy and Hannaneh Hajishirzi},
year={2023},
eprint={2306.04751},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{touvron2023llama,
title={LLaMA: Open and Efficient Foundation Language Models},
author={Hugo Touvron and Thibaut Lavril and Gautier Izacard and Xavier Martinet and Marie-Anne Lachaux and Timothée Lacroix and Baptiste Rozière and Naman Goyal and Eric Hambro and Faisal Azhar and Aurelien Rodriguez and Armand Joulin and Edouard Grave and Guillaume Lample},
year={2023},
eprint={2302.13971},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@article{xu2023baize,
title={Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data},
author={Xu, Canwen and Guo, Daya and Duan, Nan and McAuley, Julian},
journal={arXiv preprint arXiv:2304.01196},
year={2023}
}
```
|
joncam14/dqn-SpaceInvadersNoFrameskip-v4
|
joncam14
| 2023-06-20T13:11:20Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-20T13:10:46Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 357.00 +/- 110.25
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga joncam14 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga joncam14 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga joncam14
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 10000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
MarketingHHM/autotrain-hhmleoom-68141137245
|
MarketingHHM
| 2023-06-20T09:37:32Z | 98 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"led",
"text2text-generation",
"autotrain",
"summarization",
"unk",
"dataset:MarketingHHM/autotrain-data-hhmleoom",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-06-20T02:35:25Z |
---
tags:
- autotrain
- summarization
language:
- unk
widget:
- text: "I love AutoTrain"
datasets:
- MarketingHHM/autotrain-data-hhmleoom
co2_eq_emissions:
emissions: 292.1583830151034
---
# Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 68141137245
- CO2 Emissions (in grams): 292.1584
## Validation Metrics
- Loss: 0.771
- Rouge1: 37.289
- Rouge2: 25.451
- RougeL: 31.188
- RougeLsum: 35.055
- Gen Len: 108.526
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/MarketingHHM/autotrain-hhmleoom-68141137245
```
|
gokuls/hbertv2-Massive-intent
|
gokuls
| 2023-06-20T09:05:06Z | 47 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"hybridbert",
"text-classification",
"generated_from_trainer",
"dataset:massive",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-20T08:56:06Z |
---
tags:
- generated_from_trainer
datasets:
- massive
metrics:
- accuracy
model-index:
- name: hbertv2-Massive-intent
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: massive
type: massive
config: en-US
split: validation
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.8514510575504181
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# hbertv2-Massive-intent
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new) on the massive dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9457
- Accuracy: 0.8515
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1277 | 1.0 | 180 | 1.0263 | 0.7364 |
| 0.9042 | 2.0 | 360 | 0.8013 | 0.7875 |
| 0.6379 | 3.0 | 540 | 0.8182 | 0.7914 |
| 0.4865 | 4.0 | 720 | 0.8074 | 0.7973 |
| 0.3637 | 5.0 | 900 | 0.7780 | 0.8190 |
| 0.3019 | 6.0 | 1080 | 0.7656 | 0.8288 |
| 0.2218 | 7.0 | 1260 | 0.8253 | 0.8254 |
| 0.1741 | 8.0 | 1440 | 0.8295 | 0.8239 |
| 0.1316 | 9.0 | 1620 | 0.8590 | 0.8308 |
| 0.1011 | 10.0 | 1800 | 0.8465 | 0.8431 |
| 0.078 | 11.0 | 1980 | 0.9007 | 0.8401 |
| 0.0573 | 12.0 | 2160 | 0.9133 | 0.8470 |
| 0.0382 | 13.0 | 2340 | 0.9233 | 0.8470 |
| 0.0247 | 14.0 | 2520 | 0.9365 | 0.8490 |
| 0.0148 | 15.0 | 2700 | 0.9457 | 0.8515 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
|
gurugaurav/lilt-en-funsd
|
gurugaurav
| 2023-06-19T06:08:05Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"lilt",
"token-classification",
"generated_from_trainer",
"dataset:funsd-layoutlmv3",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-06-19T05:26:52Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- funsd-layoutlmv3
model-index:
- name: lilt-en-funsd
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# lilt-en-funsd
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the funsd-layoutlmv3 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5496
- Answer: {'precision': 0.875, 'recall': 0.9253365973072215, 'f1': 0.8994646044021416, 'number': 817}
- Header: {'precision': 0.6276595744680851, 'recall': 0.4957983193277311, 'f1': 0.5539906103286385, 'number': 119}
- Question: {'precision': 0.9049360146252285, 'recall': 0.9192200557103064, 'f1': 0.9120221096269001, 'number': 1077}
- Overall Precision: 0.8796
- Overall Recall: 0.8967
- Overall F1: 0.8881
- Overall Accuracy: 0.8134
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 0.434 | 10.53 | 200 | 1.0227 | {'precision': 0.8357705286839145, 'recall': 0.9094247246022031, 'f1': 0.8710433763188746, 'number': 817} | {'precision': 0.7058823529411765, 'recall': 0.40336134453781514, 'f1': 0.5133689839572192, 'number': 119} | {'precision': 0.8683522231909329, 'recall': 0.924791086350975, 'f1': 0.89568345323741, 'number': 1077} | 0.8493 | 0.8877 | 0.8681 | 0.7935 |
| 0.0484 | 21.05 | 400 | 1.3626 | {'precision': 0.8098360655737705, 'recall': 0.9069767441860465, 'f1': 0.8556581986143187, 'number': 817} | {'precision': 0.6086956521739131, 'recall': 0.47058823529411764, 'f1': 0.5308056872037914, 'number': 119} | {'precision': 0.8613333333333333, 'recall': 0.8997214484679665, 'f1': 0.8801089918256131, 'number': 1077} | 0.8283 | 0.8773 | 0.8521 | 0.7995 |
| 0.0168 | 31.58 | 600 | 1.3003 | {'precision': 0.8440046565774156, 'recall': 0.8873929008567931, 'f1': 0.8651551312649164, 'number': 817} | {'precision': 0.6421052631578947, 'recall': 0.5126050420168067, 'f1': 0.5700934579439252, 'number': 119} | {'precision': 0.8776595744680851, 'recall': 0.9192200557103064, 'f1': 0.8979591836734694, 'number': 1077} | 0.8530 | 0.8823 | 0.8674 | 0.8189 |
| 0.008 | 42.11 | 800 | 1.3225 | {'precision': 0.8584795321637427, 'recall': 0.8984088127294981, 'f1': 0.8779904306220095, 'number': 817} | {'precision': 0.5736434108527132, 'recall': 0.6218487394957983, 'f1': 0.596774193548387, 'number': 119} | {'precision': 0.888468809073724, 'recall': 0.872794800371402, 'f1': 0.8805620608899298, 'number': 1077} | 0.8560 | 0.8684 | 0.8621 | 0.8210 |
| 0.0059 | 52.63 | 1000 | 1.6362 | {'precision': 0.8307522123893806, 'recall': 0.9192166462668299, 'f1': 0.8727484020918072, 'number': 817} | {'precision': 0.6419753086419753, 'recall': 0.4369747899159664, 'f1': 0.52, 'number': 119} | {'precision': 0.8944444444444445, 'recall': 0.8969359331476323, 'f1': 0.8956884561891516, 'number': 1077} | 0.8567 | 0.8788 | 0.8676 | 0.8061 |
| 0.0027 | 63.16 | 1200 | 1.6927 | {'precision': 0.8269858541893362, 'recall': 0.9302325581395349, 'f1': 0.8755760368663594, 'number': 817} | {'precision': 0.6046511627906976, 'recall': 0.4369747899159664, 'f1': 0.5073170731707317, 'number': 119} | {'precision': 0.9000925069380203, 'recall': 0.903435468895079, 'f1': 0.901760889712697, 'number': 1077} | 0.8557 | 0.8867 | 0.8709 | 0.7939 |
| 0.002 | 73.68 | 1400 | 1.4609 | {'precision': 0.8479467258601554, 'recall': 0.9351285189718482, 'f1': 0.889406286379511, 'number': 817} | {'precision': 0.5726495726495726, 'recall': 0.5630252100840336, 'f1': 0.5677966101694915, 'number': 119} | {'precision': 0.8917431192660551, 'recall': 0.9025069637883009, 'f1': 0.8970927549607752, 'number': 1077} | 0.8553 | 0.8957 | 0.8750 | 0.7965 |
| 0.0012 | 84.21 | 1600 | 1.4851 | {'precision': 0.865909090909091, 'recall': 0.9326805385556916, 'f1': 0.8980553918680023, 'number': 817} | {'precision': 0.6074766355140186, 'recall': 0.5462184873949579, 'f1': 0.575221238938053, 'number': 119} | {'precision': 0.9008341056533827, 'recall': 0.9025069637883009, 'f1': 0.901669758812616, 'number': 1077} | 0.8708 | 0.8937 | 0.8821 | 0.8131 |
| 0.0006 | 94.74 | 1800 | 1.5228 | {'precision': 0.850613154960981, 'recall': 0.9339045287637698, 'f1': 0.8903150525087514, 'number': 817} | {'precision': 0.594059405940594, 'recall': 0.5042016806722689, 'f1': 0.5454545454545453, 'number': 119} | {'precision': 0.896709323583181, 'recall': 0.9108635097493036, 'f1': 0.9037309995393827, 'number': 1077} | 0.8623 | 0.8962 | 0.8789 | 0.8082 |
| 0.0004 | 105.26 | 2000 | 1.5287 | {'precision': 0.867579908675799, 'recall': 0.9302325581395349, 'f1': 0.8978145304193739, 'number': 817} | {'precision': 0.6222222222222222, 'recall': 0.47058823529411764, 'f1': 0.5358851674641149, 'number': 119} | {'precision': 0.8917710196779964, 'recall': 0.9257195914577531, 'f1': 0.9084282460136676, 'number': 1077} | 0.8700 | 0.9006 | 0.8850 | 0.8128 |
| 0.0003 | 115.79 | 2200 | 1.5306 | {'precision': 0.8766006984866124, 'recall': 0.9216646266829865, 'f1': 0.8985680190930787, 'number': 817} | {'precision': 0.6263736263736264, 'recall': 0.4789915966386555, 'f1': 0.5428571428571428, 'number': 119} | {'precision': 0.8902765388046388, 'recall': 0.9266480965645311, 'f1': 0.908098271155596, 'number': 1077} | 0.8730 | 0.8982 | 0.8854 | 0.8127 |
| 0.0001 | 126.32 | 2400 | 1.5496 | {'precision': 0.875, 'recall': 0.9253365973072215, 'f1': 0.8994646044021416, 'number': 817} | {'precision': 0.6276595744680851, 'recall': 0.4957983193277311, 'f1': 0.5539906103286385, 'number': 119} | {'precision': 0.9049360146252285, 'recall': 0.9192200557103064, 'f1': 0.9120221096269001, 'number': 1077} | 0.8796 | 0.8967 | 0.8881 | 0.8134 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
|
arunptp/taxi-v3-00
|
arunptp
| 2023-06-19T05:37:04Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-19T05:36:56Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi-v3-00
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.52 +/- 2.73
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="arunptp/taxi-v3-00", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
crlandsc/bsrnn-vocals
|
crlandsc
| 2023-06-16T20:25:39Z | 0 | 2 | null |
[
"audio source separation",
"music demixing",
"band-split recurrent neural network",
"bsrnn",
"spectrogram",
"vocals",
"region:us"
] | null | 2023-06-16T20:18:04Z |
---
tags:
- audio source separation
- music demixing
- band-split recurrent neural network
- bsrnn
- spectrogram
- vocals
---
# Model Card for bsrnn-vocals
Vocals model for [Music-Demixing-with-Band-Split-RNN](https://github.com/crlandsc/Music-Demixing-with-Band-Split-RNN).
|
haytin69/archanafriend
|
haytin69
| 2023-06-16T13:17:30Z | 34 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-16T13:11:34Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### ArchanaFriend Dreambooth model trained by haytin69 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
ugiugi/inisw08-RoBERT-mlm-adamw_torch_bs16
|
ugiugi
| 2023-06-15T19:06:57Z | 115 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-15T15:32:28Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: inisw08-RoBERT-mlm-adamw_torch_bs16
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# inisw08-RoBERT-mlm-adamw_torch_bs16
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.2486
- Accuracy: 0.3717
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
peteozegov/a2c-PandaReachDense-v2
|
peteozegov
| 2023-06-15T04:26:46Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaReachDense-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-05T03:30:25Z |
---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -0.90 +/- 0.34
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
irfanamal/bert-base-uncased-classification-chain-3
|
irfanamal
| 2023-06-14T10:13:44Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2023-06-13T15:47:52Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-uncased-classification-chain-3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-classification-chain-3
This model is a fine-tuned version of [irfanamal/bert-base-uncased-finetuned-amazonreviews](https://huggingface.co/irfanamal/bert-base-uncased-finetuned-amazonreviews) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2311
- Accuracy: 0.5304
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 3.3468 | 1.0 | 1250 | 2.9103 | 0.434 |
| 2.28 | 2.0 | 2500 | 2.4665 | 0.4919 |
| 1.9336 | 3.0 | 3750 | 2.3106 | 0.5161 |
| 1.6268 | 4.0 | 5000 | 2.2438 | 0.5259 |
| 1.5101 | 5.0 | 6250 | 2.2311 | 0.5304 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
roy23roy/my_poem_model
|
roy23roy
| 2023-06-14T01:30:00Z | 116 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt_neo",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-13T23:31:15Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: my_poem_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_poem_model
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3339
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6126 | 1.0 | 799 | 1.4344 |
| 1.3488 | 2.0 | 1598 | 1.3601 |
| 1.2822 | 3.0 | 2397 | 1.3339 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Dylan1999/bert-squad-mrc
|
Dylan1999
| 2023-06-13T14:11:47Z | 105 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"bert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-13T14:01:36Z |
---
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: bert-squad-mrc
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
This checkpoint is a BRET cased model finetuned on SQuAD dataset. It can be used to general MRC(Machine Learning Comprehension) purposes.
### Framework versions
- Transformers 4.11.0.dev0
- Pytorch 1.8.1+cu111
- Datasets 1.12.2.dev0
- Tokenizers 0.10.3
|
BlueAvenir/sti_digital_affinity_V_0_1
|
BlueAvenir
| 2023-06-13T11:19:53Z | 1 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-13T11:19:29Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 245 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 245,
"warmup_steps": 25,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
keysonya/Reinforce-1
|
keysonya
| 2023-06-13T10:44:27Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-13T10:43:57Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
Zhejian/llama-7b
|
Zhejian
| 2023-06-12T00:43:20Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-12T00:13:33Z |
---
license: other
---
LLaMA-7B converted to work with Transformers/HuggingFace. This is under a special license, please see the LICENSE file for details.
--
license: other
---
# LLaMA Model Card
## Model details
**Organization developing the model**
The FAIR team of Meta AI.
**Model date**
LLaMA was trained between December. 2022 and Feb. 2023.
**Model version**
This is version 1 of the model.
**Model type**
LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters.
**Paper or resources for more information**
More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/.
**Citations details**
https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/
**License**
Non-commercial bespoke license
**Where to send questions or comments about the model**
Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue.
## Intended use
**Primary intended uses**
The primary use of LLaMA is research on large language models, including:
exploring potential applications such as question answering, natural language understanding or reading comprehension,
understanding capabilities and limitations of current language models, and developing techniques to improve those,
evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations.
**Primary intended users**
The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.
**Out-of-scope use cases**
LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.
## Factors
**Relevant factors**
One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model.
**Evaluation factors**
As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model.
## Metrics
**Model performance measures**
We use the following measure to evaluate the model:
- Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs,
- Exact match for question answering,
- The toxicity score from Perspective API on RealToxicityPrompts.
**Decision thresholds**
Not applicable.
**Approaches to uncertainty and variability**
Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training.
## Evaluation datasets
The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs.
## Training dataset
The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing.
## Quantitative analysis
Hyperparameters for the model architecture
<table>
<thead>
<tr>
<th >LLaMA</th> <th colspan=6>Model hyper parameters </th>
</tr>
<tr>
<th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
<tr>
<th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
</tbody>
</table>
*Table 1 - Summary of LLama Model Hyperparameters*
We present our results on eight standard common sense reasoning benchmarks in the table below.
<table>
<thead>
<tr>
<th>LLaMA</th> <th colspan=9>Reasoning tasks </th>
</tr>
<tr>
<th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93
</th>
<tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94
</th>
<tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92
</th>
<tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr>
</tbody>
</table>
*Table 2 - Summary of LLama Model Performance on Reasoning tasks*
We present our results on bias in the table below. Note that lower value is better indicating lower bias.
| No | Category | FAIR LLM |
| --- | -------------------- | -------- |
| 1 | Gender | 70.6 |
| 2 | Religion | 79 |
| 3 | Race/Color | 57 |
| 4 | Sexual orientation | 81 |
| 5 | Age | 70.1 |
| 6 | Nationality | 64.2 |
| 7 | Disability | 66.7 |
| 8 | Physical appearance | 77.8 |
| 9 | Socioeconomic status | 71.5 |
| | LLaMA Average | 66.6 |
*Table 3 - Summary bias of our model output*
## Ethical considerations
**Data**
The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data.
**Human life**
The model is not intended to inform decisions about matters central to human life, and should not be used in such a way.
**Mitigations**
We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier.
**Risks and harms**
Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard.
**Use cases**
LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
|
Seltion/embeddings
|
Seltion
| 2023-06-10T19:08:51Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-03-06T01:23:17Z |
---
license: creativeml-openrail-m
---
|
YakovElm/MariaDB15Classic_MSE
|
YakovElm
| 2023-06-10T01:26:22Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-10T01:25:47Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB15Classic_MSE
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# MariaDB15Classic_MSE
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0542
- Train Accuracy: 0.5222
- Validation Loss: 0.0390
- Validation Accuracy: 0.2739
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.0768 | 0.5088 | 0.0398 | 0.1834 | 0 |
| 0.0622 | 0.5079 | 0.0393 | 0.1633 | 1 |
| 0.0542 | 0.5222 | 0.0390 | 0.2739 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Hyperledger5SetFitModel_Train_balance_ratio_1
|
YakovElm
| 2023-06-09T12:50:25Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-09T12:49:52Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# YakovElm/Hyperledger5SetFitModel_Train_balance_ratio_1
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("YakovElm/Hyperledger5SetFitModel_Train_balance_ratio_1")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
TheBloke/GPT4All-13B-snoozy-GGML
|
TheBloke
| 2023-06-07T22:48:34Z | 0 | 48 | null |
[
"license:other",
"region:us"
] | null | 2023-05-05T15:24:23Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Nomic.AI's GPT4All-13B-snoozy GGML
These files are GGML format model files for [Nomic.AI's GPT4All-13B-snoozy](https://huggingface.co/nomic-ai/gpt4all-13b-snoozy).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/GPT4All-13B-snoozy-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/GPT4All-13B-snoozy-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/nomic-ai/gpt4all-13b-snoozy)
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are only compatible with llama.cpp as of June 6th, commit `2d43387`.
They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| GPT4All-13B-snoozy.ggmlv3.q2_K.bin | q2_K | 2 | 5.43 GB | 7.93 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| GPT4All-13B-snoozy.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.87 GB | 9.37 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| GPT4All-13B-snoozy.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.25 GB | 8.75 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| GPT4All-13B-snoozy.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.59 GB | 8.09 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. |
| GPT4All-13B-snoozy.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| GPT4All-13B-snoozy.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.82 GB | 10.32 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| GPT4All-13B-snoozy.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.32 GB | 9.82 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| GPT4All-13B-snoozy.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| GPT4All-13B-snoozy.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.21 GB | 11.71 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| GPT4All-13B-snoozy.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.95 GB | 11.45 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| GPT4All-13B-snoozy.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m GPT4All-13B-snoozy.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Nomic.AI's GPT4All-13B-snoozy
# Model Card for GPT4All-13b-snoozy
A GPL licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model has been finetuned from LLama 13B
- **Developed by:** [Nomic AI](https://home.nomic.ai)
- **Model Type:** A finetuned LLama 13B model on assistant style interaction data
- **Language(s) (NLP):** English
- **License:** GPL
- **Finetuned from model [optional]:** LLama 13B
This model was trained on `nomic-ai/gpt4all-j-prompt-generations` using `revision=v1.3-groovy`
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [https://github.com/nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all)
- **Base Model Repository:** [https://github.com/facebookresearch/llama](https://github.com/facebookresearch/llama)
- **Demo [optional]:** [https://gpt4all.io/](https://gpt4all.io/)
### Results
Results on common sense reasoning benchmarks
```
| Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. |
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
| GPT4All-J v1.1-breezy | 74.0 | 75.1 | 63.2 | 63.6 | 55.4 | 34.9 | 38.4 | 57.8 |
| GPT4All-J v1.2-jazzy | 74.8 | 74.9 | 63.6 | 63.8 | 56.6 | 35.3 | 41.0 | 58.6 |
| GPT4All-J v1.3-groovy | 73.6 | 74.3 | 63.8 | 63.5 | 57.7 | 35.0 | 38.8 | 58.1 |
| GPT4All-J Lora 6B | 68.6 | 75.8 | 66.2 | 63.5 | 56.4 | 35.7 | 40.2 | 58.1 |
| GPT4All LLaMa Lora 7B | 73.1 | 77.6 | 72.1 | 67.8 | 51.1 | 40.4 | 40.2 | 60.3 |
| GPT4All 13B snoozy | **83.3** | 79.2 | 75.0 | **71.3** | 60.9 | 44.2 | 43.4 | **65.3** |
| Dolly 6B | 68.8 | 77.3 | 67.6 | 63.9 | 62.9 | 38.7 | 41.2 | 60.1 |
| Dolly 12B | 56.7 | 75.4 | 71.0 | 62.2 | 64.6 | 38.5 | 40.4 | 58.4 |
| Alpaca 7B | 73.9 | 77.2 | 73.9 | 66.1 | 59.8 | 43.3 | 43.4 | 62.4 |
| Alpaca Lora 7B | 74.3 | **79.3** | 74.0 | 68.8 | 56.6 | 43.9 | 42.6 | 62.8 |
| GPT-J 6.7B | 65.4 | 76.2 | 66.2 | 64.1 | 62.2 | 36.6 | 38.2 | 58.4 |
| LLama 7B | 73.1 | 77.4 | 73.0 | 66.9 | 52.5 | 41.4 | 42.4 | 61.0 |
| LLama 13B | 68.5 | 79.1 | 76.2 | 70.1 | 60.0 | **44.6** | 42.2 | 63.0 |
| Pythia 6.7B | 63.5 | 76.3 | 64.0 | 61.1 | 61.3 | 35.2 | 37.2 | 57.0 |
| Pythia 12B | 67.7 | 76.6 | 67.3 | 63.8 | 63.9 | 34.8 | 38 | 58.9 |
| Fastchat T5 | 81.5 | 64.6 | 46.3 | 61.8 | 49.3 | 33.3 | 39.4 | 53.7 |
| Fastchat Vicuña 7B | 76.6 | 77.2 | 70.7 | 67.3 | 53.5 | 41.2 | 40.8 | 61.0 |
| Fastchat Vicuña 13B | 81.5 | 76.8 | 73.3 | 66.7 | 57.4 | 42.7 | 43.6 | 63.1 |
| StableVicuña RLHF | 82.3 | 78.6 | 74.1 | 70.9 | 61.0 | 43.5 | **44.4** | 65.0 |
| StableLM Tuned | 62.5 | 71.2 | 53.6 | 54.8 | 52.4 | 31.1 | 33.4 | 51.3 |
| StableLM Base | 60.1 | 67.4 | 41.2 | 50.1 | 44.9 | 27.0 | 32.0 | 42.2 |
| Koala 13B | 76.5 | 77.9 | 72.6 | 68.8 | 54.3 | 41.0 | 42.8 | 62.0 |
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
| Mosaic mpt-7B | 74.8 | **79.3** | **76.3** | 68.6 | **70.0** | 42.2 | 42.6 | 64.8 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
```
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.