Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +169 -0
- chat_template.jinja +327 -0
- config.json +73 -0
- generation_config.json +10 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +843 -0
- recipe.yaml +27 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- swiss-ai/Apertus-8B-Instruct-2509
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
library_name: transformers
|
| 7 |
+
tags:
|
| 8 |
+
- multilingual
|
| 9 |
+
- compliant
|
| 10 |
+
- swiss-ai
|
| 11 |
+
- apertus
|
| 12 |
+
|
| 13 |
+
extra_gated_prompt: "### Apertus LLM Acceptable Use Policy \n(1.0 | September 1, 2025)\n\"Agreement\" The Swiss National AI Institute (SNAI) is a partnership between the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \n\nBy using the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and EPFL against any third-party claims arising from your use of Apertus LLM. \n\nThe training data and the Apertus LLM may contain or generate information that directly or indirectly refers to an identifiable individual (Personal Data). You process Personal Data as independent controller in accordance with applicable data protection law. SNAI will regularly provide a file with hash values for download which you can apply as an output filter to your use of our Apertus LLM. The file reflects data protection deletion requests which have been addressed to SNAI as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from SNAI every six months following the release of the model. "
|
| 14 |
+
extra_gated_fields:
|
| 15 |
+
Your Name: text
|
| 16 |
+
Country: country
|
| 17 |
+
Affiliation: text
|
| 18 |
+
geo: ip_location
|
| 19 |
+
By clicking Submit below I accept the terms of use: checkbox
|
| 20 |
+
extra_gated_button_content: Submit
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# Apertus
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
## Table of Contents
|
| 28 |
+
|
| 29 |
+
1. [Model Summary](#model-summary)
|
| 30 |
+
2. [How to use](#how-to-use)
|
| 31 |
+
3. [Evaluation](#evaluation)
|
| 32 |
+
4. [Training](#training)
|
| 33 |
+
5. [Limitations](#limitations)
|
| 34 |
+
6. [Legal Aspects](#legal-aspects)
|
| 35 |
+
|
| 36 |
+
## Model Summary
|
| 37 |
+
|
| 38 |
+
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.
|
| 39 |
+
The model supports over 1000 languages and long context, it uses only fully compliant and open training data, and achieves comparable performance to models trained behind closed doors.
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
The model is a decoder-only transformer, pretrained on 15T tokens with a staged curriculum of web, code and math data. The model uses a new xIELU activation function and is trained from scratch with the AdEMAMix optimizer. Post-training included supervised fine-tuning and alignment via QRPO.
|
| 44 |
+
|
| 45 |
+
### Key features
|
| 46 |
+
- **Fully open model**: open weights + open data + full training details including all data and training recipes
|
| 47 |
+
- **Massively Multilingual**: 1811 natively supported languages
|
| 48 |
+
- **Compliant** Apertus is trained while respecting opt-out consent of data owners (even retrospectivey), and avoiding memorization of training data
|
| 49 |
+
|
| 50 |
+
For more details refer to our [technical report](https://github.com/swiss-ai/apertus-tech-report/blob/main/Apertus_Tech_Report.pdf)
|
| 51 |
+
|
| 52 |
+
## How to use
|
| 53 |
+
|
| 54 |
+
The modeling code for Apertus is available in transformers `v4.56.0`, so make sure to upgrade your transformers version. You can also load the model with the latest `vLLM` which uses transformers as a backend.
|
| 55 |
+
```bash
|
| 56 |
+
pip install -U transformers
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
```python
|
| 60 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 61 |
+
|
| 62 |
+
model_name = "swiss-ai/Apertus-8B-Instruct-2509"
|
| 63 |
+
device = "cuda" # for GPU usage or "cpu" for CPU usage
|
| 64 |
+
|
| 65 |
+
# load the tokenizer and the model
|
| 66 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 67 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 68 |
+
model_name,
|
| 69 |
+
).to(device)
|
| 70 |
+
|
| 71 |
+
# prepare the model input
|
| 72 |
+
prompt = "Give me a brief explanation of gravity in simple terms."
|
| 73 |
+
messages_think = [
|
| 74 |
+
{"role": "user", "content": prompt}
|
| 75 |
+
]
|
| 76 |
+
|
| 77 |
+
text = tokenizer.apply_chat_template(
|
| 78 |
+
messages_think,
|
| 79 |
+
tokenize=False,
|
| 80 |
+
add_generation_prompt=True,
|
| 81 |
+
)
|
| 82 |
+
model_inputs = tokenizer([text], return_tensors="pt", add_special_tokens=False).to(model.device)
|
| 83 |
+
|
| 84 |
+
# Generate the output
|
| 85 |
+
generated_ids = model.generate(**model_inputs, max_new_tokens=32768)
|
| 86 |
+
|
| 87 |
+
# Get and decode the output
|
| 88 |
+
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
|
| 89 |
+
print(tokenizer.decode(output_ids, skip_special_tokens=True))
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
>[!TIP]
|
| 93 |
+
> We recommend setting `temperature=0.8` and `top_p=0.9` in the sampling parameters.
|
| 94 |
+
|
| 95 |
+
### Long context processing
|
| 96 |
+
|
| 97 |
+
Apertus by default supports a context length up to 65,536 tokens.
|
| 98 |
+
|
| 99 |
+
### Agentic Usage
|
| 100 |
+
|
| 101 |
+
Apertus supports tool use
|
| 102 |
+
|
| 103 |
+
### vLLM and SGLang
|
| 104 |
+
|
| 105 |
+
You can use vLLM and SGLang to deploy the model in an API compatible with OpenAI format.
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
In this section, we report the evaluation results of Apertus model.
|
| 110 |
+
|
| 111 |
+
### Base Pre-Trained Model
|
| 112 |
+
- see [Apertus_Tech_Report.pdf](https://github.com/swiss-ai/apertus-tech-report/blob/main/Apertus_Tech_Report.pdf)
|
| 113 |
+
|
| 114 |
+
### Instruction Model
|
| 115 |
+
- see [Apertus_Tech_Report.pdf](https://github.com/swiss-ai/apertus-tech-report/blob/main/Apertus_Tech_Report.pdf)
|
| 116 |
+
|
| 117 |
+
## Training
|
| 118 |
+
|
| 119 |
+
### Model
|
| 120 |
+
|
| 121 |
+
- **Architecture:** Transformer decoder
|
| 122 |
+
- **Pretraining tokens:** 15T
|
| 123 |
+
- **Precision:** bfloat16
|
| 124 |
+
|
| 125 |
+
### Software & hardware
|
| 126 |
+
|
| 127 |
+
- **GPUs:** 4096 GH200
|
| 128 |
+
- **Training Framework:** [Megatron-LM](https://github.com/swiss-ai/Megatron-LM)
|
| 129 |
+
- ...
|
| 130 |
+
|
| 131 |
+
### Open resources
|
| 132 |
+
All elements used in the training process are made openly available
|
| 133 |
+
- **Training data reconstruction scripts:** [github.com/swiss-ai/pretrain-data](https://github.com/swiss-ai/pretrain-data)
|
| 134 |
+
- The training intermediate checkpoints are available on the different branches of this same repository
|
| 135 |
+
|
| 136 |
+
|
| 137 |
+
## Limitations
|
| 138 |
+
|
| 139 |
+
Apertus can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Legal Aspects
|
| 143 |
+
|
| 144 |
+
#### EU AI Act Transparency Documentation and Code of Practice
|
| 145 |
+
- [Apertus_EU_Public_Summary.pdf](https://huggingface.co/swiss-ai/Apertus-70B-2509/blob/main/Apertus_EU_Public_Summary.pdf)
|
| 146 |
+
- [Apertus_EU_Code_of_Practice.pdf](https://huggingface.co/swiss-ai/Apertus-70B-2509/blob/main/Apertus_EU_Code_of_Practice.pdf)
|
| 147 |
+
|
| 148 |
+
#### Data Protection and Copyright Requests
|
| 149 |
+
For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly
|
| 150 | |
| 151 | |
| 152 |
+
|
| 153 |
+
#### Output Filter for PII
|
| 154 |
+
- Currently no output filter is provided.
|
| 155 |
+
- Please check this site regularly for an output filter that can be used on top of the Apertus LLM. The filter reflects data protection deletion requests which have been addressed to us as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from this site every six months.
|
| 156 |
+
|
| 157 |
+
## Contact
|
| 158 |
+
To contact us, please send an email to
|
| 159 | |
| 160 |
+
|
| 161 |
+
## Citation
|
| 162 |
+
```bash
|
| 163 |
+
@misc{swissai2025apertus,
|
| 164 |
+
title={{Apertus: Democratizing Open and Compliant LLMs for Global Language Environments}},
|
| 165 |
+
author={Apertus Team},
|
| 166 |
+
year={2025},
|
| 167 |
+
howpublished={\url{https://huggingface.co/swiss-ai/Apertus-70B-2509}}
|
| 168 |
+
}
|
| 169 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,327 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 2 |
+
{%- if param_spec.type == "array" -%}
|
| 3 |
+
{%- if param_spec['items'] -%}
|
| 4 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 5 |
+
{{- "string[]" }}
|
| 6 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 7 |
+
{{- "number[]" }}
|
| 8 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 9 |
+
{{- "number[]" }}
|
| 10 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 11 |
+
{{- "boolean[]" }}
|
| 12 |
+
{%- else -%}
|
| 13 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 14 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 15 |
+
{{- "any[]" }}
|
| 16 |
+
{%- else -%}
|
| 17 |
+
{{- inner_type + "[]" }}
|
| 18 |
+
{%- endif -%}
|
| 19 |
+
{%- endif -%}
|
| 20 |
+
{%- if param_spec.nullable -%}
|
| 21 |
+
{{- " | null" }}
|
| 22 |
+
{%- endif -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- if param_spec.nullable -%}
|
| 26 |
+
{{- " | null" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 30 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 31 |
+
{%- if param_spec.type | length > 1 -%}
|
| 32 |
+
{{- param_spec.type | join(" | ") }}
|
| 33 |
+
{%- else -%}
|
| 34 |
+
{{- param_spec.type[0] }}
|
| 35 |
+
{%- endif -%}
|
| 36 |
+
{%- elif param_spec.oneOf -%}
|
| 37 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 38 |
+
{%- set has_object_variants = false -%}
|
| 39 |
+
{%- for variant in param_spec.oneOf -%}
|
| 40 |
+
{%- if variant.type == "object" -%}
|
| 41 |
+
{%- set has_object_variants = true -%}
|
| 42 |
+
{%- endif -%}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 45 |
+
{{- "any" }}
|
| 46 |
+
{%- else -%}
|
| 47 |
+
{%- for variant in param_spec.oneOf -%}
|
| 48 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 49 |
+
{%- if variant.description %}
|
| 50 |
+
{{- "// " + variant.description }}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- if variant.default is defined %}
|
| 53 |
+
{{ "// default: " + variant.default|tojson }}
|
| 54 |
+
{%- endif -%}
|
| 55 |
+
{%- if not loop.last %}
|
| 56 |
+
{{- " | " }}
|
| 57 |
+
{% endif -%}
|
| 58 |
+
{%- endfor -%}
|
| 59 |
+
{%- endif -%}
|
| 60 |
+
{%- elif param_spec.type == "string" -%}
|
| 61 |
+
{%- if param_spec.enum -%}
|
| 62 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 63 |
+
{%- else -%}
|
| 64 |
+
{{- "string" }}
|
| 65 |
+
{%- if param_spec.nullable %}
|
| 66 |
+
{{- " | null" }}
|
| 67 |
+
{%- endif -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "number" -%}
|
| 70 |
+
{{- "number" }}
|
| 71 |
+
{%- elif param_spec.type == "integer" -%}
|
| 72 |
+
{{- "number" }}
|
| 73 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 74 |
+
{{- "boolean" }}
|
| 75 |
+
{%- elif param_spec.type == "object" -%}
|
| 76 |
+
{%- if param_spec.properties -%}
|
| 77 |
+
{{- "{\n" }}
|
| 78 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 79 |
+
{{- prop_name -}}
|
| 80 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 81 |
+
{{- "?" }}
|
| 82 |
+
{%- endif -%}
|
| 83 |
+
{{- ": " }}
|
| 84 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 85 |
+
{%- if not loop.last -%}
|
| 86 |
+
{{-", " }}
|
| 87 |
+
{%- endif -%}
|
| 88 |
+
{%- endfor -%}
|
| 89 |
+
{{- "}" }}
|
| 90 |
+
{%- else -%}
|
| 91 |
+
{{- "object" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{%- else -%}
|
| 94 |
+
{{- "any" }}
|
| 95 |
+
{%- endif -%}
|
| 96 |
+
{%- endmacro -%}
|
| 97 |
+
|
| 98 |
+
{%- macro render_tools(tools) -%}
|
| 99 |
+
{%- for tool in tools %}
|
| 100 |
+
{{- "// " + tool.description + "\n" }}
|
| 101 |
+
{{- "type "+ tool.name + " = " }}
|
| 102 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 103 |
+
{{- "(_: {\n" }}
|
| 104 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 105 |
+
{%- if param_spec.description %}
|
| 106 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 107 |
+
{%- endif %}
|
| 108 |
+
{{- param_name }}
|
| 109 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 110 |
+
{{- "?" }}
|
| 111 |
+
{%- endif -%}
|
| 112 |
+
{{- ": " }}
|
| 113 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 114 |
+
{%- if param_spec.default is defined -%}
|
| 115 |
+
{%- if param_spec.enum %}
|
| 116 |
+
{{- ", // default: " + param_spec.default }}
|
| 117 |
+
{%- elif param_spec.oneOf %}
|
| 118 |
+
{{- "// default: " + param_spec.default }}
|
| 119 |
+
{%- else %}
|
| 120 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 121 |
+
{%- endif -%}
|
| 122 |
+
{%- endif -%}
|
| 123 |
+
{%- if not loop.last %}
|
| 124 |
+
{{- ",\n" }}
|
| 125 |
+
{%- else %}
|
| 126 |
+
{{- "\n" }}
|
| 127 |
+
{%- endif -%}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{{- "}) => any;" }}
|
| 130 |
+
{%- else -%}
|
| 131 |
+
{{- "() => any;" }}
|
| 132 |
+
{%- endif -%}
|
| 133 |
+
{%- if not loop.last -%}
|
| 134 |
+
{{- "\n" }}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- endfor %}
|
| 137 |
+
{%- endmacro -%}
|
| 138 |
+
|
| 139 |
+
{{ bos_token }}
|
| 140 |
+
|
| 141 |
+
{%- set system_token = '<|system_start|>' -%}
|
| 142 |
+
{%- set end_system_token = '<|system_end|>' -%}
|
| 143 |
+
{%- set developer_token = '<|developer_start|>' -%}
|
| 144 |
+
{%- set end_developer_token = '<|developer_end|>' -%}
|
| 145 |
+
{%- set user_token = '<|user_start|>' -%}
|
| 146 |
+
{%- set end_user_token = '<|user_end|>' -%}
|
| 147 |
+
{%- set assistant_token = '<|assistant_start|>' -%}
|
| 148 |
+
{%- set end_assistant_token = '<|assistant_end|>' -%}
|
| 149 |
+
{%- set inner_token = '<|inner_prefix|>' -%}
|
| 150 |
+
{%- set outer_token = '<|inner_suffix|>' -%}
|
| 151 |
+
{%- set tool_calls_token = '<|tools_prefix|>' -%}
|
| 152 |
+
{%- set end_tool_calls_token = '<|tools_suffix|>' -%}
|
| 153 |
+
|
| 154 |
+
{%- set ns = namespace(in_assistant=false, in_tool=false, in_inner=false, assistant_format=none) -%}
|
| 155 |
+
|
| 156 |
+
{%- if messages and messages[0].role == 'system' -%}
|
| 157 |
+
{%- if "content" in messages[0] -%}
|
| 158 |
+
{%- if messages[0].content is string -%}
|
| 159 |
+
{{ system_token + messages[0].content + end_system_token }}
|
| 160 |
+
{%- elif messages[0].content is mapping and "text" in messages[0].content -%}
|
| 161 |
+
{{ system_token + messages[0].content.text + end_system_token }}
|
| 162 |
+
{%- else -%}
|
| 163 |
+
{{- raise_exception("Invalid system message") -}}
|
| 164 |
+
{%- endif -%}
|
| 165 |
+
{%- else -%}
|
| 166 |
+
{{- raise_exception("Invalid system message") -}}
|
| 167 |
+
{%- endif -%}
|
| 168 |
+
{%- set loop_messages = messages[1:] -%}
|
| 169 |
+
{%- else -%}
|
| 170 |
+
{{ system_token + 'You are Apertus, a helpful assistant created by the SwissAI initiative.\nKnowledge cutoff: 2024-04\nCurrent date: ' + strftime_now('%Y-%m-%d') + end_system_token }}
|
| 171 |
+
{%- set loop_messages = messages -%}
|
| 172 |
+
{%- endif -%}
|
| 173 |
+
|
| 174 |
+
{{ developer_token + 'Deliberation: ' }}
|
| 175 |
+
{%- if enable_thinking is defined and enable_thinking -%}
|
| 176 |
+
{{ 'enabled\n' }}
|
| 177 |
+
{%- else -%}
|
| 178 |
+
{{ 'disabled\n' }}
|
| 179 |
+
{%- endif -%}
|
| 180 |
+
{%- if tools is defined and tools -%}
|
| 181 |
+
{{ 'Tool Capabilities:\n' + render_tools(tools) }}
|
| 182 |
+
{%- else -%}
|
| 183 |
+
{{ 'Tool Capabilities: disabled' }}
|
| 184 |
+
{%- endif -%}
|
| 185 |
+
{{ end_developer_token }}
|
| 186 |
+
|
| 187 |
+
{%- for message in loop_messages -%}
|
| 188 |
+
{%- if message.role == 'user' -%}
|
| 189 |
+
{%- set ns.in_inner = false -%}
|
| 190 |
+
{%- if ns.in_tool -%}
|
| 191 |
+
{{ ']' }}
|
| 192 |
+
{%- set ns.in_tool = false -%}
|
| 193 |
+
{%- endif -%}
|
| 194 |
+
{%- if ns.in_assistant -%}
|
| 195 |
+
{{ end_assistant_token }}
|
| 196 |
+
{%- set ns.in_assistant = false -%}
|
| 197 |
+
{%- endif -%}
|
| 198 |
+
{%- if "content" in message -%}
|
| 199 |
+
{{ user_token }}
|
| 200 |
+
{%- if message.content is string -%}
|
| 201 |
+
{{ message.content }}
|
| 202 |
+
{%- elif message.content is mapping and "parts" in message.content -%}
|
| 203 |
+
{%- set parts = message.content.parts -%}
|
| 204 |
+
{%- for part in parts -%}
|
| 205 |
+
{%- if part.type == "text" -%}
|
| 206 |
+
{{ part.text }}
|
| 207 |
+
{%- else -%}
|
| 208 |
+
{{- raise_exception("Invalid user part: " + part.type) -}}
|
| 209 |
+
{%- endif -%}
|
| 210 |
+
{%- endfor -%}
|
| 211 |
+
{%- else -%}
|
| 212 |
+
{{- raise_exception("Invalid user message: " + message.role) -}}
|
| 213 |
+
{%- endif -%}
|
| 214 |
+
{{ end_user_token }}
|
| 215 |
+
{%- endif -%}
|
| 216 |
+
{%- elif message.role == 'assistant' -%}
|
| 217 |
+
{%- if not ns.in_assistant -%}
|
| 218 |
+
{{ assistant_token }}
|
| 219 |
+
{%- set ns.in_assistant = true -%}
|
| 220 |
+
{%- endif -%}
|
| 221 |
+
{%- if "content" in message -%}
|
| 222 |
+
{%- if message.content is string and (ns.assistant_format is none or ns.assistant_format == "string") -%}
|
| 223 |
+
{%- if ns.in_tool -%}
|
| 224 |
+
{{ ']' }}
|
| 225 |
+
{%- set ns.in_tool = false -%}
|
| 226 |
+
{%- endif -%}
|
| 227 |
+
{%- set ns.assistant_format = "string" -%}
|
| 228 |
+
{{ message.content }}
|
| 229 |
+
{%- elif message.content is mapping and "blocks" in message.content and (ns.assistant_format is none or ns.assistant_format == "mapping") -%}
|
| 230 |
+
{%- set ns.assistant_format = "mapping" -%}
|
| 231 |
+
{%- set blocks = message.content.blocks -%}
|
| 232 |
+
{%- for block in blocks -%}
|
| 233 |
+
{%- if block.type == 'thoughts' -%}
|
| 234 |
+
{%- if ns.in_tool -%}
|
| 235 |
+
{{ ']' }}
|
| 236 |
+
{%- set ns.in_tool = false -%}
|
| 237 |
+
{%- endif -%}
|
| 238 |
+
{%- if not ns.in_inner -%}
|
| 239 |
+
{%- set ns.in_inner = true -%}
|
| 240 |
+
{{ inner_token }}
|
| 241 |
+
{%- endif -%}
|
| 242 |
+
{{ block.text }}
|
| 243 |
+
{%- elif block.type == 'tool_calls' -%}
|
| 244 |
+
{%- if ns.in_tool -%}
|
| 245 |
+
{{ ']' }}
|
| 246 |
+
{%- set ns.in_tool = false -%}
|
| 247 |
+
{%- endif -%}
|
| 248 |
+
{%- if ns.in_inner and not loop.first and block.calls|length == 1 and block.calls[0].name == 'display_answers' -%}
|
| 249 |
+
{%- set ns.in_inner = false -%}
|
| 250 |
+
{{ outer_token }}
|
| 251 |
+
{%- endif -%}
|
| 252 |
+
{{ tool_calls_token + '[' }}
|
| 253 |
+
{%- for tool_call in block.calls -%}
|
| 254 |
+
{{- '{"' + tool_call.name + '": ' + tool_call.arguments + '}' }}
|
| 255 |
+
{%- if not loop.last -%}
|
| 256 |
+
{{- ", " }}
|
| 257 |
+
{%- endif -%}
|
| 258 |
+
{%- endfor -%}
|
| 259 |
+
{{ ']' + end_tool_calls_token }}
|
| 260 |
+
{%- elif block.type == 'tool_outputs' -%}
|
| 261 |
+
{%- if ns.in_tool -%}
|
| 262 |
+
{{- raise_exception("Cannot have both tool outputs as separate messages and tool outputs as blocks") -}}
|
| 263 |
+
{%- endif -%}
|
| 264 |
+
{{ '[' }}
|
| 265 |
+
{%- for tool_output in block.outputs -%}
|
| 266 |
+
{{- tool_output.output }}
|
| 267 |
+
{%- if not loop.last -%}
|
| 268 |
+
{{- ", " }}
|
| 269 |
+
{%- endif -%}
|
| 270 |
+
{%- endfor -%}
|
| 271 |
+
{{- ']' }}
|
| 272 |
+
{%- elif block.type == 'response' -%}
|
| 273 |
+
{%- if ns.in_tool -%}
|
| 274 |
+
{{ ']' }}
|
| 275 |
+
{%- set ns.in_tool = false -%}
|
| 276 |
+
{%- endif -%}
|
| 277 |
+
{%- if (not loop.first and ns.in_inner) or (ns.in_assistant and ns.in_inner) -%}
|
| 278 |
+
{%- set ns.in_inner = false -%}
|
| 279 |
+
{{ outer_token }}
|
| 280 |
+
{%- endif -%}
|
| 281 |
+
{{ block.text }}
|
| 282 |
+
{%- else -%}
|
| 283 |
+
{{- raise_exception("Invalid assistant block type: " + block.type) -}}
|
| 284 |
+
{%- endif -%}
|
| 285 |
+
{%- endfor -%}
|
| 286 |
+
{%- else -%}
|
| 287 |
+
{{- raise_exception("Invalid assistant content") -}}
|
| 288 |
+
{%- endif -%}
|
| 289 |
+
{%- else -%}
|
| 290 |
+
{{- raise_exception("Invalid assistant message") -}}
|
| 291 |
+
{%- endif -%}
|
| 292 |
+
{%- if "tool_calls" in message and message.tool_calls -%}
|
| 293 |
+
{{ tool_calls_token + '[' }}
|
| 294 |
+
{%- for tool_call in message.tool_calls -%}
|
| 295 |
+
{%- if tool_call.type == 'function' -%}
|
| 296 |
+
{%- set function = tool_call.function -%}
|
| 297 |
+
{{- '{"' + function.name + '": ' + function.arguments + '}' }}
|
| 298 |
+
{%- if not loop.last -%}
|
| 299 |
+
{{- ", " }}
|
| 300 |
+
{%- endif -%}
|
| 301 |
+
{%- else -%}
|
| 302 |
+
{{- raise_exception("Invalid tool call type: " + tool_call.type) -}}
|
| 303 |
+
{%- endif -%}
|
| 304 |
+
{%- endfor -%}
|
| 305 |
+
{{ ']' + end_tool_calls_token }}
|
| 306 |
+
{%- endif -%}
|
| 307 |
+
{%- elif message.role == 'tool' -%}
|
| 308 |
+
{%- if not ns.in_assistant -%}
|
| 309 |
+
{{- raise_exception("Tool message outside of assistant") -}}
|
| 310 |
+
{%- endif -%}
|
| 311 |
+
{%- if not ns.in_tool -%}
|
| 312 |
+
{{ '[' }}
|
| 313 |
+
{%- set ns.in_tool = true -%}
|
| 314 |
+
{%- else -%}
|
| 315 |
+
{{ ", "}}
|
| 316 |
+
{%- endif -%}
|
| 317 |
+
{{ message.content }}
|
| 318 |
+
{%- else -%}
|
| 319 |
+
{{- raise_exception("Invalid message role") -}}
|
| 320 |
+
{%- endif -%}
|
| 321 |
+
{%- endfor -%}
|
| 322 |
+
{%- if ns.in_tool -%}
|
| 323 |
+
{{ ']' }}
|
| 324 |
+
{%- endif -%}
|
| 325 |
+
{%- if add_generation_prompt -%}
|
| 326 |
+
{{ assistant_token }}
|
| 327 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ApertusForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 68,
|
| 10 |
+
"hidden_act": "xielu",
|
| 11 |
+
"hidden_dropout": 0.0,
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 21504,
|
| 15 |
+
"max_position_embeddings": 65536,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "apertus",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 3,
|
| 22 |
+
"post_norm": false,
|
| 23 |
+
"qk_norm": true,
|
| 24 |
+
"quantization_config": {
|
| 25 |
+
"config_groups": {
|
| 26 |
+
"group_0": {
|
| 27 |
+
"format": "pack-quantized",
|
| 28 |
+
"input_activations": null,
|
| 29 |
+
"output_activations": null,
|
| 30 |
+
"targets": [
|
| 31 |
+
"Linear"
|
| 32 |
+
],
|
| 33 |
+
"weights": {
|
| 34 |
+
"actorder": null,
|
| 35 |
+
"block_structure": null,
|
| 36 |
+
"dynamic": false,
|
| 37 |
+
"group_size": 32,
|
| 38 |
+
"num_bits": 4,
|
| 39 |
+
"observer": "mse",
|
| 40 |
+
"observer_kwargs": {},
|
| 41 |
+
"strategy": "group",
|
| 42 |
+
"symmetric": true,
|
| 43 |
+
"type": "int"
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"format": "pack-quantized",
|
| 48 |
+
"global_compression_ratio": null,
|
| 49 |
+
"ignore": [
|
| 50 |
+
"lm_head"
|
| 51 |
+
],
|
| 52 |
+
"kv_cache_scheme": null,
|
| 53 |
+
"quant_method": "compressed-tensors",
|
| 54 |
+
"quantization_status": "compressed",
|
| 55 |
+
"sparsity_config": {},
|
| 56 |
+
"transform_config": {},
|
| 57 |
+
"version": "0.10.3.dev47+ge463fe6"
|
| 58 |
+
},
|
| 59 |
+
"rms_norm_eps": 1e-05,
|
| 60 |
+
"rope_scaling": {
|
| 61 |
+
"factor": 8.0,
|
| 62 |
+
"high_freq_factor": 4.0,
|
| 63 |
+
"low_freq_factor": 1.0,
|
| 64 |
+
"original_max_position_embeddings": 8192,
|
| 65 |
+
"rope_type": "llama3",
|
| 66 |
+
"type": "llama3"
|
| 67 |
+
},
|
| 68 |
+
"rope_theta": 12000000,
|
| 69 |
+
"tie_word_embeddings": false,
|
| 70 |
+
"transformers_version": "4.57.0.dev0",
|
| 71 |
+
"use_cache": false,
|
| 72 |
+
"vocab_size": 131072
|
| 73 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2,
|
| 6 |
+
68,
|
| 7 |
+
72
|
| 8 |
+
],
|
| 9 |
+
"transformers_version": "4.57.0.dev0"
|
| 10 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:925ae36ef0fa4fc062eeb9330e288a1c55396a7e49f2b35153fa595d2f496154
|
| 3 |
+
size 4994725960
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fea0f54b6a75c64189e5e311dae6860c9c8cd74409d166e3588e49f41851070
|
| 3 |
+
size 1079272416
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 2164535744,
|
| 4 |
+
"total_size": 6073904384
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.1.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.1.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.1.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.1.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.10.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.10.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.10.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.10.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.10.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.10.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.10.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.10.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.11.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.11.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.11.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.11.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.11.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.11.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.11.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.11.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.12.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.12.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.12.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.12.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.12.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.12.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.12.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.12.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.13.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.13.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.13.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.13.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.13.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.13.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.13.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.13.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.14.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.14.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.14.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.14.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.14.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.14.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.14.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.14.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.14.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.14.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.14.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.14.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.15.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.15.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.15.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.15.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.15.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.15.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.15.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.15.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.16.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.16.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.16.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.16.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.16.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.16.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.16.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.16.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.16.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.16.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.16.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.16.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.17.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.17.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.17.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.17.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.17.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.17.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.17.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.17.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.17.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.17.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.17.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.17.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.18.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.18.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.18.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.18.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.18.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.18.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.18.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.18.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.18.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.18.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.18.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.18.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.18.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.18.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.19.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.19.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.19.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.19.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.19.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.19.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.19.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.19.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.19.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.19.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.2.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.2.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.2.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.2.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.20.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.20.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.20.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.20.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.20.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.20.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.20.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.20.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.20.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.20.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.20.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.20.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.20.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.20.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.21.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.21.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.21.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.21.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.21.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.21.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.21.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.21.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.21.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.21.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.21.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.21.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.21.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.21.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.22.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.22.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.22.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.22.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.22.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.22.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.22.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.22.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.22.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.22.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.22.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.22.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.22.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.22.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.23.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.23.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.23.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.23.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.23.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.23.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.23.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.23.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.23.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.23.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.24.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.24.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.24.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.24.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.24.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.24.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.24.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.layers.24.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.layers.24.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.layers.24.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.24.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.layers.24.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.24.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.layers.24.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.25.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.layers.25.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.layers.25.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.layers.25.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.layers.25.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.layers.25.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.layers.25.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.layers.25.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.layers.25.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.layers.25.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.25.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.layers.25.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.25.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.layers.25.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.26.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.layers.26.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.layers.26.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.layers.26.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.26.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.26.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.26.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.layers.26.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.layers.26.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.26.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.26.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.26.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.layers.26.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.layers.26.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.layers.26.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.26.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.layers.26.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.layers.26.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.layers.27.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.layers.27.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.layers.27.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.layers.27.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.layers.27.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.layers.27.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.layers.27.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.layers.27.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.layers.27.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.layers.27.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.layers.27.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.layers.27.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.layers.27.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.layers.27.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.layers.27.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.layers.27.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.layers.27.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.layers.27.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.layers.28.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.layers.28.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.layers.28.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.layers.28.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.layers.28.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.layers.28.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.layers.28.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.layers.28.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.layers.28.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.layers.28.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.layers.28.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.layers.28.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.layers.28.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.layers.28.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.layers.28.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.layers.28.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.layers.28.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.layers.28.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.layers.28.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.layers.28.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.layers.28.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.layers.28.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.layers.28.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.layers.28.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.layers.29.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.layers.29.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.layers.29.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.layers.29.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.layers.29.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.layers.29.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.layers.29.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.layers.29.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.layers.29.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.layers.29.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.layers.29.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.layers.29.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.layers.29.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.layers.29.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.layers.29.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.layers.29.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.layers.29.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.layers.29.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.layers.29.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.layers.29.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.layers.29.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.layers.29.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.layers.29.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.layers.29.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.layers.3.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.layers.3.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.layers.3.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.layers.3.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.layers.30.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.layers.30.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.layers.30.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.layers.30.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.layers.30.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.layers.30.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.layers.30.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.layers.30.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.layers.30.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.layers.30.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.layers.30.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.layers.30.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.layers.30.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.layers.30.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.layers.30.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.layers.30.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.layers.30.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.layers.30.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.layers.30.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.layers.30.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.layers.30.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.layers.30.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.layers.30.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.layers.30.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.layers.31.attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.layers.31.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.layers.31.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.layers.31.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.layers.31.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.layers.31.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.layers.31.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.layers.31.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.layers.31.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.layers.31.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.layers.31.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.layers.31.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.layers.31.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.layers.31.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.layers.31.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.layers.31.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.layers.31.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.layers.31.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.layers.31.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.layers.31.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.layers.31.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.layers.31.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.layers.31.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.layers.4.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.layers.4.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.layers.4.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.layers.4.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.layers.5.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.layers.5.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.layers.5.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.layers.5.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 721 |
+
"model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 722 |
+
"model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 723 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 725 |
+
"model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 726 |
+
"model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 727 |
+
"model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 728 |
+
"model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 729 |
+
"model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 730 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 731 |
+
"model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 732 |
+
"model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 733 |
+
"model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 734 |
+
"model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 735 |
+
"model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 736 |
+
"model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 737 |
+
"model.layers.6.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"model.layers.6.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 740 |
+
"model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 741 |
+
"model.layers.6.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 742 |
+
"model.layers.6.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 743 |
+
"model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 744 |
+
"model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 745 |
+
"model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 746 |
+
"model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 747 |
+
"model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 748 |
+
"model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 749 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 751 |
+
"model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 752 |
+
"model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 753 |
+
"model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 754 |
+
"model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 755 |
+
"model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 756 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 757 |
+
"model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 758 |
+
"model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 759 |
+
"model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 760 |
+
"model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 761 |
+
"model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 762 |
+
"model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 763 |
+
"model.layers.7.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"model.layers.7.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 766 |
+
"model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 767 |
+
"model.layers.7.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 768 |
+
"model.layers.7.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 769 |
+
"model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 770 |
+
"model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 771 |
+
"model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 772 |
+
"model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 773 |
+
"model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 774 |
+
"model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 775 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 777 |
+
"model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 778 |
+
"model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 779 |
+
"model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 780 |
+
"model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 781 |
+
"model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 782 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 783 |
+
"model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 784 |
+
"model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 785 |
+
"model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 786 |
+
"model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 787 |
+
"model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 788 |
+
"model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 789 |
+
"model.layers.8.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"model.layers.8.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 791 |
+
"model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 792 |
+
"model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 793 |
+
"model.layers.8.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 794 |
+
"model.layers.8.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 795 |
+
"model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 796 |
+
"model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 797 |
+
"model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 798 |
+
"model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 799 |
+
"model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 800 |
+
"model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 801 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 803 |
+
"model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 804 |
+
"model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 805 |
+
"model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 806 |
+
"model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 807 |
+
"model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 808 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 809 |
+
"model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 810 |
+
"model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 811 |
+
"model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 812 |
+
"model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 813 |
+
"model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 814 |
+
"model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 815 |
+
"model.layers.9.attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 816 |
+
"model.layers.9.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 817 |
+
"model.layers.9.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
|
| 818 |
+
"model.layers.9.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
|
| 819 |
+
"model.layers.9.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
|
| 820 |
+
"model.layers.9.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
|
| 821 |
+
"model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 822 |
+
"model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 823 |
+
"model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 824 |
+
"model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 825 |
+
"model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 826 |
+
"model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 827 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 828 |
+
"model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 829 |
+
"model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 830 |
+
"model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 831 |
+
"model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 832 |
+
"model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 833 |
+
"model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 834 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 835 |
+
"model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 836 |
+
"model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 837 |
+
"model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 838 |
+
"model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
|
| 839 |
+
"model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 840 |
+
"model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
|
| 841 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 842 |
+
}
|
| 843 |
+
}
|
recipe.yaml
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
quant_stage:
|
| 2 |
+
quant_modifiers:
|
| 3 |
+
GPTQModifier:
|
| 4 |
+
config_groups:
|
| 5 |
+
group_0:
|
| 6 |
+
targets: [Linear]
|
| 7 |
+
weights:
|
| 8 |
+
num_bits: 4
|
| 9 |
+
type: int
|
| 10 |
+
symmetric: true
|
| 11 |
+
group_size: 32
|
| 12 |
+
strategy: group
|
| 13 |
+
block_structure: null
|
| 14 |
+
dynamic: false
|
| 15 |
+
actorder: null
|
| 16 |
+
observer: mse
|
| 17 |
+
observer_kwargs: {}
|
| 18 |
+
input_activations: null
|
| 19 |
+
output_activations: null
|
| 20 |
+
format: null
|
| 21 |
+
targets: [Linear]
|
| 22 |
+
ignore: [lm_head, model.embed_tokens, 're:.*attention_layernorm$', 're:.*feedforward_layernorm$',
|
| 23 |
+
're:.*act_fn.*', model.norm]
|
| 24 |
+
sequential_update: true
|
| 25 |
+
block_size: 128
|
| 26 |
+
dampening_frac: 0.01
|
| 27 |
+
offload_hessians: false
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|assistant_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb201fb226cde11f66c3cf51c5344fb37b1611f00c21e75c324546d854eff2e1
|
| 3 |
+
size 17078480
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|