Resources

View closed (7)

License question, is it based on Llama license?

#48 opened about 2 months ago by

JLouisBiz

chat_template not set in tokenizer_config

#47 opened 3 months ago by

vizzard110

Is there a checkpoint after fine-tuning only on `ultrachat_200k`, which we would like to use it to do research on alignment algorithms?

#45 opened 6 months ago by

AIR-hl

Interview request: genAI evaluation & documentation

#44 opened 6 months ago by

evatang

TinyPi

#43 opened 6 months ago by

nmulvaine

Adding Evaluation Results

#42 opened 7 months ago by

leaderboard-pr-bot

How to remove input token to get only output token ?

#41 opened 7 months ago by

ducknificient

Multilingual model

#40 opened 7 months ago by

ducknificient

Instruction Tuning Model

#39 opened 7 months ago by

ducknificient

Request: DOI

#38 opened 8 months ago by

climbingm

Adding Evaluation Results

#37 opened 9 months ago by

leaderboard-pr-bot

CUDA assertion error when trying to train

#36 opened 9 months ago by

brianwilcken

Can you upload the SFT version as well?

#34 opened 10 months ago by

jiwan-chung

Adding Evaluation Results

#33 opened 10 months ago by

leaderboard-pr-bot

Adding Evaluation Results

#32 opened 11 months ago by

asck

Adding Evaluation Results

#31 opened 11 months ago by

leaderboard-pr-bot

It wrote an credible new recipe for spiced frog salad

#30 opened 11 months ago by

MartialTerran

Write a story....

#29 opened 11 months ago by

MartialTerran

Too much Junk vocab words in the vocab.json.

#28 opened 11 months ago by

MartialTerran

Bing (ChatGPT4) analyzes the "def fibonacci_sequence_to_digits(n)" example code.

#27 opened 11 months ago by

MartialTerran

Update widget example

#26 opened 12 months ago by

Xenova

Adding Evaluation Results

#25 opened 12 months ago by

leaderboard-pr-bot

Deployment?

#24 opened 12 months ago by

huggingface9837

[AUTOMATED] Model Memory Requirements

#22 opened about 1 year ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#21 opened about 1 year ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#20 opened about 1 year ago by

model-sizer-bot

Dataset for DPO, with a Template?

#17 opened about 1 year ago by

ewqr2130

Prompt format?

#16 opened about 1 year ago by

anuragrawal

Minimum supported device?

#15 opened about 1 year ago by

sachinmyneni

Transformers unable to load the model

#14 opened about 1 year ago by

iammayur

BFloat16 is not supported on MPS

#13 opened about 1 year ago by

nhannn

ImportError: cannot import name 'LlamaTokenizer' from 'transformers' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/init.py)

#12 opened about 1 year ago by

gmdl007

Training on corpus of text (astronomy) - without templates

#11 opened about 1 year ago by

demetera

what are use cases , it is deranged like Joe Biden

#10 opened about 1 year ago by

froilo

What is the context size?

#9 opened about 1 year ago by

streamerbtw1002

Is it on the leaderboard?

#8 opened about 1 year ago by

AIWintermuteAI

<0x0A>

#7 opened about 1 year ago by

Omidh

You know what we are going to ask

#6 opened about 1 year ago by

LaferriereJC

Fine Tuning

#5 opened about 1 year ago by

ybsid

You should try training a model with 2B parameters and context length 32000.

#3 opened about 1 year ago by

win10

Fantastic work guys!

#1 opened about 1 year ago by

dillfrescott

License question, is it based on Llama license?

chat_template not set in tokenizer_config

Is there a checkpoint after fine-tuning only on `ultrachat_200k`, which we would like to use it to do research on alignment algorithms?

Interview request: genAI evaluation & documentation

TinyPi

Adding Evaluation Results

How to remove input token to get only output token ?

Multilingual model

Instruction Tuning Model

Request: DOI

Adding Evaluation Results

CUDA assertion error when trying to train

Can you upload the SFT version as well?

Adding Evaluation Results

Adding Evaluation Results

Adding Evaluation Results

It wrote an credible new recipe for spiced frog salad

Write a story....

Too much Junk vocab words in the vocab.json.

Bing (ChatGPT4) analyzes the "def fibonacci_sequence_to_digits(n)" example code.

Update widget example

Adding Evaluation Results

Deployment?

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

Dataset for DPO, with a Template?

Prompt format?

Minimum supported device?

Transformers unable to load the model

BFloat16 is not supported on MPS

ImportError: cannot import name 'LlamaTokenizer' from 'transformers' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/__init__.py)

Training on corpus of text (astronomy) - without templates

what are use cases , it is deranged like Joe Biden

What is the context size?

Is it on the leaderboard?

<0x0A>

You know what we are going to ask

Fine Tuning

You should try training a model with 2B parameters and context length 32000.

Fantastic work guys!

ImportError: cannot import name 'LlamaTokenizer' from 'transformers' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/init.py)