Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +225 -0
- added_tokens.json +3 -0
- chat_template.jinja +6 -0
- config.json +87 -0
- generation_config.json +13 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +634 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +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 +1,225 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- translation
|
| 5 |
+
license: gemma
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
- es
|
| 9 |
+
- fr
|
| 10 |
+
- de
|
| 11 |
+
- pt
|
| 12 |
+
- ja
|
| 13 |
+
- ko
|
| 14 |
+
- zh
|
| 15 |
+
- ar
|
| 16 |
+
- ru
|
| 17 |
+
- hi
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# YanoljaNEXT-Rosetta-12B
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [`google/gemma-3-12b-pt`](https://huggingface.co/google/gemma-3-12b-pt). As it is intended solely for text generation, we have extracted and utilized only the `Gemma3ForCausalLM` component from the original architecture.
|
| 23 |
+
|
| 24 |
+
Different from our previous EEVE models, this model does not feature an expanded tokenizer.
|
| 25 |
+
|
| 26 |
+
- **Model Name:** `yanolja/YanoljaNEXT-Rosetta-12B`
|
| 27 |
+
- **Base Model:** `google/gemma-3-12b-pt`
|
| 28 |
+
|
| 29 |
+
## Model Description
|
| 30 |
+
|
| 31 |
+
This model is a 12-billion parameter, decoder-only language model built on the Gemma3 architecture and fine-tuned by Yanolja NEXT. It is specifically designed to translate structured data (JSON format) while preserving the original data structure.
|
| 32 |
+
|
| 33 |
+
The model was trained on a multilingual dataset covering the following languages:
|
| 34 |
+
- English
|
| 35 |
+
- Spanish
|
| 36 |
+
- French
|
| 37 |
+
- German
|
| 38 |
+
- Portuguese
|
| 39 |
+
- Japanese
|
| 40 |
+
- Korean
|
| 41 |
+
- Chinese
|
| 42 |
+
- Arabic
|
| 43 |
+
- Russian
|
| 44 |
+
- Hindi
|
| 45 |
+
|
| 46 |
+
While optimized for these languages, it may also perform effectively on other languages supported by the base Gemma3 model.
|
| 47 |
+
|
| 48 |
+
## How to use
|
| 49 |
+
|
| 50 |
+
You can use this model with the `transformers` library as follows:
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
import json
|
| 54 |
+
import torch
|
| 55 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 56 |
+
|
| 57 |
+
# model_id = "yanolja/YanoljaNEXT-Rosetta-12B"
|
| 58 |
+
model_id = "/data/nas-2/seungduk/eeve2/babel/datasets/gemma-3-12b-rosetta-revision4-stage2"
|
| 59 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 60 |
+
model_id,
|
| 61 |
+
dtype=torch.bfloat16,
|
| 62 |
+
device_map="auto",
|
| 63 |
+
max_memory={0: "47GB"},
|
| 64 |
+
)
|
| 65 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 66 |
+
|
| 67 |
+
target_language = "Korean"
|
| 68 |
+
context = {
|
| 69 |
+
"context": "Simple introduction about a tech company.",
|
| 70 |
+
"tone": "Informative and helpful",
|
| 71 |
+
"glossary": {
|
| 72 |
+
"Yanolja NEXT": "야놀자넥스트",
|
| 73 |
+
"travel industry": "여행 산업",
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
|
| 77 |
+
system = [f"Translate the user's text to {target_language}."]
|
| 78 |
+
for key, value in context.items():
|
| 79 |
+
key_pascal = key.capitalize()
|
| 80 |
+
if isinstance(value, dict):
|
| 81 |
+
system.append(f"{key_pascal}:")
|
| 82 |
+
for f, t in value.items():
|
| 83 |
+
system.append(f"- {f} -> {t}")
|
| 84 |
+
else:
|
| 85 |
+
system.append(f"{key_pascal}: {value}")
|
| 86 |
+
|
| 87 |
+
system.append("Provide the final translation immediately without any other text.")
|
| 88 |
+
|
| 89 |
+
source = {
|
| 90 |
+
"company_name": "Yanolja NEXT",
|
| 91 |
+
"description": "Yanolja NEXT is a company that provides cutting-edge "
|
| 92 |
+
"technology for the global travel industry.",
|
| 93 |
+
}
|
| 94 |
+
|
| 95 |
+
messages = [
|
| 96 |
+
{"role": "system", "content": "\n".join(system)},
|
| 97 |
+
{"role": "user", "content": json.dumps(source, ensure_ascii=False)},
|
| 98 |
+
]
|
| 99 |
+
|
| 100 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 101 |
+
print(prompt)
|
| 102 |
+
# <bos><start_of_turn>instruction
|
| 103 |
+
# Translate the user's text to Korean.
|
| 104 |
+
# Context: Simple introduction about a tech company.
|
| 105 |
+
# Tone: Informative and helpful
|
| 106 |
+
# Glossary:
|
| 107 |
+
# - Yanolja NEXT -> 야놀자넥스트
|
| 108 |
+
# - travel industry -> 여행 산업
|
| 109 |
+
# Provide the final translation immediately without any other text.<end_of_turn>
|
| 110 |
+
# <start_of_turn>source
|
| 111 |
+
# {"company_name": "Yanolja NEXT", "description": "Yanolja NEXT is a company that provides cutting-edge technology for the global travel industry."}<end_of_turn>
|
| 112 |
+
# <start_of_turn>translation
|
| 113 |
+
|
| 114 |
+
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
| 115 |
+
input_length = inputs["input_ids"].shape[1]
|
| 116 |
+
|
| 117 |
+
with torch.inference_mode():
|
| 118 |
+
outputs = model.generate(
|
| 119 |
+
**inputs,
|
| 120 |
+
max_new_tokens=64,
|
| 121 |
+
)
|
| 122 |
+
|
| 123 |
+
generated_tokens = outputs[0][input_length:]
|
| 124 |
+
translation = tokenizer.decode(generated_tokens, skip_special_tokens=True)
|
| 125 |
+
|
| 126 |
+
print(json.dumps(json.loads(translation), indent=2, ensure_ascii=False))
|
| 127 |
+
# {
|
| 128 |
+
# "company_name": "야놀자넥스트",
|
| 129 |
+
# "description": "야놀자넥스트는 글로벌 여행 산업에 최첨단 기술을 제공하는 회사입니다."
|
| 130 |
+
# }
|
| 131 |
+
```
|
| 132 |
+
|
| 133 |
+
The model outputs the final translation in JSON format when appropriate, or plain text for simple translations.
|
| 134 |
+
|
| 135 |
+
## Training Procedure
|
| 136 |
+
|
| 137 |
+
### Training Data
|
| 138 |
+
The translation datasets were compiled from several sources, including:
|
| 139 |
+
- [AI Hub](https://aihub.or.kr/)
|
| 140 |
+
- [Europarl](https://www.statmt.org/europarl/)
|
| 141 |
+
|
| 142 |
+
The model was fine-tuned on multilingual translation data to optimize performance across the supported language pairs.
|
| 143 |
+
|
| 144 |
+
| Language | Portion (%) | Language | Portion (%) |
|
| 145 |
+
|----------|-------------|----------|-------------|
|
| 146 |
+
| Korean | 24.2 | French | 2.8 |
|
| 147 |
+
| English | 16.2 | German | 2.5 |
|
| 148 |
+
| Japanese | 5.8 | Russian | 2.4 |
|
| 149 |
+
| Italian | 5.3 | Arabic | 2.3 |
|
| 150 |
+
| Chinese | 4.4 | Other | 30.2 |
|
| 151 |
+
| Spanish | 3.9 | | |
|
| 152 |
+
|
| 153 |
+
## Performance
|
| 154 |
+
|
| 155 |
+
### Translation Quality Benchmarks
|
| 156 |
+
|
| 157 |
+
The following CHrF++ scores demonstrate the model's competitive performance compared to other state-of-the-art translation models on English to Korean translation:
|
| 158 |
+
|
| 159 |
+
| Model | CHrF++ Score |
|
| 160 |
+
|------------------------------------|--------------|
|
| 161 |
+
| openai/gpt-4o | 36.08 |
|
| 162 |
+
| google/gemini-2.5-flash | 35.25 |
|
| 163 |
+
| **yanolja/YanoljaNEXT-Rosetta-12B** | **34.75** |
|
| 164 |
+
| yanolja/YanoljaNEXT-Rosetta-20B | 33.87 |
|
| 165 |
+
| google/gemini-2.0-flash-001 | 33.81 |
|
| 166 |
+
| openai/gpt-oss-120b | 31.51 |
|
| 167 |
+
| google/gemma-3-27b-it | 30.05 |
|
| 168 |
+
| google/gemma-3-12b-pt | 29.31 |
|
| 169 |
+
|
| 170 |
+
YanoljaNEXT-Rosetta-12B achieves competitive translation quality while maintaining the efficiency of a 12B parameter model.
|
| 171 |
+
|
| 172 |
+
## Intended Uses & Limitations
|
| 173 |
+
|
| 174 |
+
This model is intended for translating structured data (JSON format) while preserving the original structure. It is particularly well-suited for tasks such as localizing product catalogs, translating hotel reviews, or handling any other structured content that requires accurate translation.
|
| 175 |
+
|
| 176 |
+
### Limitations
|
| 177 |
+
The model's primary focus is on JSON data. Performance on unstructured text or other data formats may vary.
|
| 178 |
+
|
| 179 |
+
### License
|
| 180 |
+
This model is released under the Gemma license, inherited from its base model, [`google/gemma-3-12b-pt`](https://huggingface.co/google/gemma-3-12b-pt). Please consult the official [Gemma license terms](https://ai.google.dev/gemma/terms) for detailed usage guidelines.
|
| 181 |
+
|
| 182 |
+
## Citation
|
| 183 |
+
|
| 184 |
+
If you use this model, please consider citing:
|
| 185 |
+
|
| 186 |
+
```
|
| 187 |
+
@misc{yanolja2025yanoljanextrosetta,
|
| 188 |
+
author = {Yanolja NEXT Co., Ltd.},
|
| 189 |
+
title = {YanoljaNEXT-Rosetta-12B},
|
| 190 |
+
year = {2025},
|
| 191 |
+
publisher = {Hugging Face},
|
| 192 |
+
journal = {Hugging Face repository},
|
| 193 |
+
howpublished = {\\url{https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-12B}}
|
| 194 |
+
}
|
| 195 |
+
```
|
| 196 |
+
|
| 197 |
+
## References
|
| 198 |
+
|
| 199 |
+
This work utilizes several models and datasets. We would like to acknowledge the original authors for their valuable contributions to the field.
|
| 200 |
+
|
| 201 |
+
```
|
| 202 |
+
@misc{gemma3,
|
| 203 |
+
author = {Google},
|
| 204 |
+
title = {Gemma 3},
|
| 205 |
+
year = {2024},
|
| 206 |
+
publisher = {Google DeepMind},
|
| 207 |
+
howpublished = {\\url{https://deepmind.google/models/gemma/gemma-3/}}
|
| 208 |
+
}
|
| 209 |
+
|
| 210 |
+
@misc{aihub,
|
| 211 |
+
author = {National Information Society Agency (NIA)},
|
| 212 |
+
title = {AI-Hub: AI Integrated Platform},
|
| 213 |
+
year = {2025},
|
| 214 |
+
publisher = {National Information Society Agency},
|
| 215 |
+
howpublished = {\\url{https://aihub.or.kr}}
|
| 216 |
+
}
|
| 217 |
+
|
| 218 |
+
@article{europarl,
|
| 219 |
+
author = {Koehn, Philipp},
|
| 220 |
+
title = {Europarl: A Parallel Corpus for Statistical Machine Translation},
|
| 221 |
+
journal = {MT Summit},
|
| 222 |
+
year = {2005},
|
| 223 |
+
pages = {79--86}
|
| 224 |
+
}
|
| 225 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}<start_of_turn>{% if message['role']=='system' %}instruction
|
| 2 |
+
{% elif message['role']=='user' %}source
|
| 3 |
+
{% elif message['role']=='assistant' %}translation
|
| 4 |
+
{% endif %}{{ message['content'] | trim }}<end_of_turn>
|
| 5 |
+
{% endfor %}{% if add_generation_prompt %}<start_of_turn>translation
|
| 6 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"cache_implementation": "hybrid",
|
| 11 |
+
"eos_token_id": 106,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 3840,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 15360,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"sliding_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"full_attention"
|
| 67 |
+
],
|
| 68 |
+
"max_position_embeddings": 131072,
|
| 69 |
+
"model_type": "gemma3_text",
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_hidden_layers": 48,
|
| 72 |
+
"num_key_value_heads": 8,
|
| 73 |
+
"pad_token_id": 0,
|
| 74 |
+
"query_pre_attn_scalar": 256,
|
| 75 |
+
"rms_norm_eps": 1e-06,
|
| 76 |
+
"rope_local_base_freq": 10000.0,
|
| 77 |
+
"rope_scaling": {
|
| 78 |
+
"factor": 8.0,
|
| 79 |
+
"rope_type": "linear"
|
| 80 |
+
},
|
| 81 |
+
"rope_theta": 1000000.0,
|
| 82 |
+
"sliding_window": 1024,
|
| 83 |
+
"torch_dtype": "bfloat16",
|
| 84 |
+
"transformers_version": "4.55.2",
|
| 85 |
+
"use_cache": false,
|
| 86 |
+
"vocab_size": 262208
|
| 87 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.55.2"
|
| 13 |
+
}
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52de5d57dd49ac220d946d4a5c4d20e829d936063b91c444bc16115abd40a402
|
| 3 |
+
size 2013757584
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd7d667446af82c76987feb91b945e27b8ba72cfefb2513972197f36ffbbdbc0
|
| 3 |
+
size 4994209296
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba3ae0f1deeb9ab0471f677794816718cea7d78b2956cea0fc126e3ab2f50c00
|
| 3 |
+
size 4962753168
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1fa03bd99fb0e2367ce0e4499f9a569691b192723248c30005d2bdf903c0e04
|
| 3 |
+
size 4931294528
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01617d89033fc48a942b7983317df42037eb304e43637cb135b16241ece54c7f
|
| 3 |
+
size 4931294528
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3575071e1280e2874b447d46b09c14df86df2bd66de224bf7a23689ea1b22f9
|
| 3 |
+
size 1698832208
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,634 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 11766034176,
|
| 4 |
+
"total_size": 45048847872
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 13 |
+
"model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 14 |
+
"model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 26 |
+
"model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 27 |
+
"model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 33 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 34 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 35 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 36 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 37 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 38 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 39 |
+
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 40 |
+
"model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 45 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 46 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 47 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 48 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 49 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 50 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 51 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 52 |
+
"model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 53 |
+
"model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 57 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 58 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 59 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 60 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 61 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 62 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 63 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 64 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 65 |
+
"model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 66 |
+
"model.layers.12.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 69 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 70 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 71 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 72 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 73 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 74 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 75 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 76 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 77 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 78 |
+
"model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 79 |
+
"model.layers.13.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 81 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 82 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 83 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 84 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 85 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 86 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 87 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 88 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 89 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 90 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 91 |
+
"model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 92 |
+
"model.layers.14.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 93 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 94 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 95 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 96 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 97 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 98 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 99 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 100 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 101 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 102 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 103 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 104 |
+
"model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 105 |
+
"model.layers.15.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 106 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 107 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 108 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 109 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 110 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 111 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 112 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 113 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 114 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 115 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 116 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 117 |
+
"model.layers.16.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 118 |
+
"model.layers.16.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 119 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 120 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 121 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 122 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 123 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 124 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 125 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 126 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 127 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 128 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 129 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 130 |
+
"model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 131 |
+
"model.layers.17.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 132 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 133 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 134 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 135 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 136 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 137 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 138 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 139 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 140 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 141 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 142 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 143 |
+
"model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 144 |
+
"model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 145 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 146 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 147 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 148 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 149 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 150 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 151 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 152 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 153 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 154 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 155 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 156 |
+
"model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 157 |
+
"model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 158 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 159 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 160 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 161 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 162 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 163 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 164 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 165 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 166 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 167 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 168 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 169 |
+
"model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 170 |
+
"model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 171 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 172 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 173 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 174 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 175 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 176 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 177 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 178 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 179 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 180 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 181 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 182 |
+
"model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 183 |
+
"model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 184 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 185 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 186 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 187 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 188 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 189 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 190 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 191 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 192 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 193 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 194 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 195 |
+
"model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 196 |
+
"model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 197 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 198 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 199 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 200 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 201 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 202 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 203 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 204 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 205 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 206 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 207 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 208 |
+
"model.layers.22.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 209 |
+
"model.layers.22.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 210 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 211 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 212 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 213 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 214 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 215 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 216 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 217 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 218 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 219 |
+
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 220 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 221 |
+
"model.layers.23.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 222 |
+
"model.layers.23.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 223 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 224 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 225 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 226 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 227 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 228 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 229 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 230 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 231 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 232 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 233 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 234 |
+
"model.layers.24.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 235 |
+
"model.layers.24.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 236 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 237 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 238 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 239 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 240 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 241 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 242 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 243 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 244 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 245 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 246 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 247 |
+
"model.layers.25.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 248 |
+
"model.layers.25.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 249 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 250 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 251 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 252 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 253 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 254 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 255 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 256 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 257 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 258 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 259 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 260 |
+
"model.layers.26.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 261 |
+
"model.layers.26.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 262 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 263 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 264 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 265 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 266 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 267 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 268 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 269 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 270 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 271 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 272 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 273 |
+
"model.layers.27.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 274 |
+
"model.layers.27.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 275 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 276 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 277 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 278 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 279 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 280 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 281 |
+
"model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 282 |
+
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 283 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 284 |
+
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 285 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 286 |
+
"model.layers.28.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 287 |
+
"model.layers.28.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 288 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 289 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 290 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 291 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 292 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 293 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 294 |
+
"model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 295 |
+
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 296 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 297 |
+
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 298 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 299 |
+
"model.layers.29.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 300 |
+
"model.layers.29.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 301 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 302 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 303 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 304 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 305 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 306 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 307 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 308 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 309 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 310 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 311 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 312 |
+
"model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 313 |
+
"model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 314 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 315 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 316 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 317 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 318 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 319 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 320 |
+
"model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 321 |
+
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 322 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 323 |
+
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 324 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 325 |
+
"model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 326 |
+
"model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 327 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 328 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 329 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 330 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 331 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 332 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 333 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 334 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 335 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 336 |
+
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 337 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 338 |
+
"model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 339 |
+
"model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 340 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 341 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 342 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 343 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 344 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 345 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 346 |
+
"model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 347 |
+
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 348 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 349 |
+
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 350 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 351 |
+
"model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 352 |
+
"model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 353 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 354 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 355 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 356 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 357 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 358 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 359 |
+
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 360 |
+
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 361 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 362 |
+
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 363 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 364 |
+
"model.layers.33.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 365 |
+
"model.layers.33.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 366 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 367 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 368 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 369 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 370 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 371 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 372 |
+
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 373 |
+
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 374 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 375 |
+
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 376 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 377 |
+
"model.layers.34.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 378 |
+
"model.layers.34.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 379 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 380 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 381 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 382 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 383 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 384 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 385 |
+
"model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 386 |
+
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 387 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 388 |
+
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 389 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 390 |
+
"model.layers.35.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 391 |
+
"model.layers.35.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 392 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 393 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 394 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 395 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 396 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 397 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 398 |
+
"model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 399 |
+
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 400 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 401 |
+
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 402 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 403 |
+
"model.layers.36.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 404 |
+
"model.layers.36.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 405 |
+
"model.layers.36.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 406 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 407 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 408 |
+
"model.layers.36.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 409 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 410 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 411 |
+
"model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 412 |
+
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 413 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 414 |
+
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 415 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 416 |
+
"model.layers.37.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 417 |
+
"model.layers.37.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 418 |
+
"model.layers.37.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 419 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 420 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 421 |
+
"model.layers.37.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 422 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 423 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 424 |
+
"model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 425 |
+
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 426 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 427 |
+
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 428 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 429 |
+
"model.layers.38.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 430 |
+
"model.layers.38.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 431 |
+
"model.layers.38.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 432 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 433 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 434 |
+
"model.layers.38.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 435 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 436 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 437 |
+
"model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 438 |
+
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 439 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 440 |
+
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 441 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 442 |
+
"model.layers.39.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 443 |
+
"model.layers.39.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 444 |
+
"model.layers.39.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 445 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 446 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 447 |
+
"model.layers.39.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 448 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 449 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 450 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 451 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 452 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 453 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 454 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 455 |
+
"model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 456 |
+
"model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 457 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 458 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 459 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 460 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 461 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 462 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 463 |
+
"model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 464 |
+
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 465 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 466 |
+
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 467 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 468 |
+
"model.layers.40.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 469 |
+
"model.layers.40.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 470 |
+
"model.layers.40.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 471 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 472 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 473 |
+
"model.layers.40.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 474 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 475 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 476 |
+
"model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 477 |
+
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 478 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 479 |
+
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 480 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 481 |
+
"model.layers.41.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 482 |
+
"model.layers.41.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 483 |
+
"model.layers.41.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 484 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 485 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 486 |
+
"model.layers.41.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 487 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 488 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 489 |
+
"model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 490 |
+
"model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 491 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 492 |
+
"model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 493 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 494 |
+
"model.layers.42.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 495 |
+
"model.layers.42.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 496 |
+
"model.layers.42.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 497 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 498 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 499 |
+
"model.layers.42.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 500 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 501 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 502 |
+
"model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 503 |
+
"model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 504 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 505 |
+
"model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 506 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 507 |
+
"model.layers.43.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 508 |
+
"model.layers.43.pre_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 509 |
+
"model.layers.43.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 510 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 511 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 512 |
+
"model.layers.43.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 513 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 514 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 515 |
+
"model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 516 |
+
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 517 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 518 |
+
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 519 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 520 |
+
"model.layers.44.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 521 |
+
"model.layers.44.pre_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 522 |
+
"model.layers.44.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 523 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 524 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 525 |
+
"model.layers.44.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 526 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 527 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 528 |
+
"model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 529 |
+
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 530 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 531 |
+
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 532 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 533 |
+
"model.layers.45.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 534 |
+
"model.layers.45.pre_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 535 |
+
"model.layers.45.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 536 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 537 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 538 |
+
"model.layers.45.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 539 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 540 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 541 |
+
"model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 542 |
+
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 543 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 544 |
+
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 545 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 546 |
+
"model.layers.46.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 547 |
+
"model.layers.46.pre_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 548 |
+
"model.layers.46.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 549 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 550 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 551 |
+
"model.layers.46.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 552 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 553 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 554 |
+
"model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 555 |
+
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 556 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 557 |
+
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 558 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 559 |
+
"model.layers.47.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 560 |
+
"model.layers.47.pre_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 561 |
+
"model.layers.47.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 562 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 563 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 564 |
+
"model.layers.47.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 565 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 566 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 567 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 568 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 569 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 570 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 571 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 572 |
+
"model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 573 |
+
"model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 574 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 575 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 576 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 577 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 578 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 579 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 580 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 581 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 582 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 583 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 584 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 585 |
+
"model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 586 |
+
"model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 587 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 588 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 589 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 590 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 591 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 592 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 593 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 594 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 595 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 596 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 597 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 598 |
+
"model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 599 |
+
"model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 600 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 601 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 602 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 603 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 604 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 605 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 606 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 607 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 608 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 609 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 610 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 611 |
+
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 612 |
+
"model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 613 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 614 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 615 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 616 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 617 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 618 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 619 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 620 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 621 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 622 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 623 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 624 |
+
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 625 |
+
"model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 626 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 627 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 628 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 629 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 630 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 631 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 632 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
| 633 |
+
}
|
| 634 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<bos>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<end_of_turn>",
|
| 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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|