Hugging Face's logo

codefuse-ai
/
CodeFuse-CodeLlama-34B

Text Generation
Transformers
PyTorch
Safetensors
English
Chinese
llama
code
text-generation-inference
Model card Files
xet
Community
11

learning

#2
by Tsingke - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+35
-94113
Files changed (26) hide show
  1. .gitattributes +11 -10
  2. LOGO.png +0 -0
  3. README.md +24 -117
  4. config.json +0 -29
  5. generation_config.json +0 -6
  6. model-00001-of-00007.safetensors +0 -3
  7. model-00002-of-00007.safetensors +0 -3
  8. model-00003-of-00007.safetensors +0 -3
  9. model-00004-of-00007.safetensors +0 -3
  10. model-00005-of-00007.safetensors +0 -3
  11. model-00006-of-00007.safetensors +0 -3
  12. model-00007-of-00007.safetensors +0 -3
  13. model.safetensors.index.json +0 -442
  14. pytorch_model-00001-of-00007.bin +0 -3
  15. pytorch_model-00002-of-00007.bin +0 -3
  16. pytorch_model-00003-of-00007.bin +0 -3
  17. pytorch_model-00004-of-00007.bin +0 -3
  18. pytorch_model-00005-of-00007.bin +0 -3
  19. pytorch_model-00006-of-00007.bin +0 -3
  20. pytorch_model-00007-of-00007.bin +0 -3
  21. pytorch_model.bin.index.json +0 -3
  22. requirements.txt +0 -14
  23. special_tokens_map.json +0 -23
  24. tokenizer.json +0 -0
  25. tokenizer.model +0 -3
  26. tokenizer_config.json +0 -33
.gitattributes CHANGED
@@ -1,34 +1,35 @@
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bin.* filter=lfs diff=lfs merge=lfs -text
5
  *.bz2 filter=lfs diff=lfs merge=lfs -text
 
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
7
  *.gz filter=lfs diff=lfs merge=lfs -text
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
 
11
  *.model filter=lfs diff=lfs merge=lfs -text
12
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
 
13
  *.onnx filter=lfs diff=lfs merge=lfs -text
14
  *.ot filter=lfs diff=lfs merge=lfs -text
15
  *.parquet filter=lfs diff=lfs merge=lfs -text
16
  *.pb filter=lfs diff=lfs merge=lfs -text
 
 
17
  *.pt filter=lfs diff=lfs merge=lfs -text
18
  *.pth filter=lfs diff=lfs merge=lfs -text
19
  *.rar filter=lfs diff=lfs merge=lfs -text
 
20
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
  *.tar.* filter=lfs diff=lfs merge=lfs -text
 
22
  *.tflite filter=lfs diff=lfs merge=lfs -text
23
  *.tgz filter=lfs diff=lfs merge=lfs -text
 
24
  *.xz filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
- *.zstandard filter=lfs diff=lfs merge=lfs -text
27
- *.tfevents* filter=lfs diff=lfs merge=lfs -text
28
- *.db* filter=lfs diff=lfs merge=lfs -text
29
- *.ark* filter=lfs diff=lfs merge=lfs -text
30
- **/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
31
- **/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
32
- **/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
33
- *.safetensors filter=lfs diff=lfs merge=lfs -text
34
- *.ckpt filter=lfs diff=lfs merge=lfs -text
 
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
 
4
  *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
7
  *.gz filter=lfs diff=lfs merge=lfs -text
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
  *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
  *.onnx filter=lfs diff=lfs merge=lfs -text
17
  *.ot filter=lfs diff=lfs merge=lfs -text
18
  *.parquet filter=lfs diff=lfs merge=lfs -text
19
  *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
  *.pt filter=lfs diff=lfs merge=lfs -text
23
  *.pth filter=lfs diff=lfs merge=lfs -text
24
  *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
  *.tflite filter=lfs diff=lfs merge=lfs -text
30
  *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
  *.xz 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
 
 
 
 
 
 
 
LOGO.png CHANGED
README.md CHANGED
@@ -1,20 +1,8 @@
1
  ---
2
  license: other
3
- tasks:
4
- - code-generation
5
- datasets:
6
- - codefuse-ai/CodeExercise-Python-27k
7
- - codefuse-ai/Evol-instruction-66k
8
- language:
9
- - en
10
- - zh
11
- pipeline_tag: text-generation
12
- library_name: transformers
13
- tags:
14
- - code
15
  ---
16
  # Model Card for CodeFuse-CodeLlama-34B
17
- ![logo](LOGO.png)
18
 
19
  [[中文]](#chinese) [[English]](#english)
20
 
@@ -30,38 +18,17 @@ The context length of finetuning is 4K while it is able to be finetuned by 16k c
30
 
31
  ## News and Updates
32
 
33
- 🔥🔥🔥 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits) of CodeFuse-CodeLlama-34B. Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
34
-
35
- 🔥🔥🔥 2023-09-11 CodeFuse-CodeLlama34B has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
36
 
37
  <br>
38
 
39
- ## Code Community
40
-
41
- **Homepage**: 🏡 https://github.com/codefuse-ai (**Please give us your support with a Star🌟 + Fork🚀 + Watch👀**)
42
-
43
- + If you wish to fine-tune the model yourself, you can visit ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
44
-
45
- + If you wish to deploy the model yourself, you can visit ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
46
-
47
- + If you wish to see a demo of the model, you can visit ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
48
-
49
-
50
  ## Performance
51
 
52
-
53
- | Model | HumanEval(pass@1) | Date |
54
- |:----------------------------|:-----------------:|:-------:|
55
- | **CodeFuse-CodeLlama-34B** | **74.4%** | 2023.9 |
56
- | WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
57
- | GPT-4(zero-shot) | 67.0% | 2023.3 |
58
- | PanGu-Coder2 15B | 61.6% | 2023.8 |
59
- | CodeLlama-34b-Python | 53.7% | 2023.8 |
60
- | CodeLlama-34b | 48.8% | 2023.8 |
61
- | GPT-3.5(zero-shot) | 48.1% | 2022.11 |
62
- | OctoCoder | 46.2% | 2023.8 |
63
- | StarCoder-15B | 33.6% | 2023.5 |
64
- | LLaMA 2 70B(zero-shot) | 29.9% | 2023.7 |
65
 
66
  <br>
67
 
@@ -103,7 +70,6 @@ pip install -r requirements.txt
103
  ```
104
 
105
  ```python
106
- import torch
107
  from transformers import (
108
  AutoTokenizer,
109
  AutoModelForCausalLM,
@@ -112,13 +78,7 @@ tokenizer = AutoTokenizer.from_pretrained(mode_name_or_path, trust_remote_code=T
112
  tokenizer.padding_side = "left"
113
  tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<unk>")
114
  tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("</s>")
115
- # try 4bit loading if cuda memory not enough
116
- model = AutoModelForCausalLM.from_pretrained(mode_name_or_path,
117
- trust_remote_code=True,
118
- load_in_4bit=False,
119
- device_map="auto",
120
- torch_dtype=torch.bfloat16)
121
- model.eval()
122
 
123
  HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
124
  BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"
@@ -139,32 +99,17 @@ gen_text = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[1]:], ski
139
  print(gen_text)
140
  ```
141
 
142
- ## MD5
143
- We notice that the file may be corrupted during transfer process. Please check MD5 value before use.
144
 
145
- | Model File | MD5 Value |
146
- |:---------------------------------|:--------------------------------:|
147
- | pytorch_model-00001-of-00007.bin | 8d544b1bcb3449934184d4141137329c |
148
- | pytorch_model-00002-of-00007.bin | 9d5dbb30911e48a42fb6d0fcabb322a4 |
149
- | pytorch_model-00003-of-00007.bin | b0d4aecee0457d9332005a187e1fffed |
150
- | pytorch_model-00004-of-00007.bin | 5c7e002de5eab77d0194a2b0f6de0c24 |
151
- | pytorch_model-00005-of-00007.bin | d22a511aa26b5b17117b665a877490ab |
152
- | pytorch_model-00006-of-00007.bin | a5c28ac277fac07d16dd66537e54d109 |
153
- | pytorch_model-00007-of-00007.bin | a967e2c6195477b7407089c0bffa2d53 |
154
 
155
 
156
- ## Citation
157
- If you find our [work](https://arxiv.org/abs/2311.02303) useful or helpful for your R&D works, please feel free to cite our paper as below.
158
- ```
159
- @article{mftcoder2023,
160
- title={MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning},
161
- author={Bingchang Liu and Chaoyu Chen and Cong Liao and Zi Gong and Huan Wang and Zhichao Lei and Ming Liang and Dajun Chen and Min Shen and Hailian Zhou and Hang Yu and Jianguo Li},
162
- year={2023},
163
- journal={arXiv preprint arXiv},
164
- archivePrefix={arXiv},
165
- eprint={2311.02303}
166
- }
167
- ```
168
 
169
  <a id="chinese"></a>
170
 
@@ -179,31 +124,13 @@ CodeFuse-CodeLlama34B-MFT 是一个通过QLoRA对基座模型CodeLlama-34b-Pytho
179
 
180
  <br>
181
 
182
- ## 代码社区
183
- **大本营**： 🏡 https://github.com/codefuse-ai （**欢迎为我们的项目一键三连 Star🌟 + Fork🚀 + Watch👀**）
184
-
185
- + 如果您想自己微调该模型，可以访问 ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
186
-
187
- + 如果您想自己部署该模型，可以访问 ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
188
-
189
- + 如果您想观看该模型示例，可以访问 ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
190
-
191
-
192
  ## 评测表现(代码)
193
 
194
- | 模型 | HumanEval(pass@1) | 日期 |
195
- |:----------------------------|:-----------------:|:-------:|
196
- | **CodeFuse-CodeLlama-34B** | **74.4%** | 2023.9 |
197
- | WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
198
- | GPT-4(zero-shot) | 67.0% | 2023.3 |
199
- | PanGu-Coder2 15B | 61.6% | 2023.8 |
200
- | CodeLlama-34b-Python | 53.7% | 2023.8 |
201
- | CodeLlama-34b | 48.8% | 2023.8 |
202
- | GPT-3.5(zero-shot) | 48.1% | 2022.11 |
203
- | OctoCoder | 46.2% | 2023.8 |
204
- | StarCoder-15B | 33.6% | 2023.5 |
205
- | LLaMA 2 70B(zero-shot) | 29.9% | 2023.7 |
206
-
207
  <br>
208
 
209
  ## Requirements
@@ -246,18 +173,12 @@ tokenizer = AutoTokenizer.from_pretrained(mode_name_or_path, trust_remote_code=T
246
  tokenizer.padding_side = "left"
247
  tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<unk>")
248
  tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("</s>")
249
- # 如果显存不够，可以考虑量化加载
250
- model = AutoModelForCausalLM.from_pretrained(mode_name_or_path,
251
- trust_remote_code=True,
252
- load_in_4bit=False,
253
- device_map="auto",
254
- torch_dtype=torch.bfloat16)
255
- model.eval()
256
 
257
  HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
258
  BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"
259
 
260
- text = f"{HUMAN_ROLE_START_TAG}请用C++实现求解第n个斐波那契数{BOT_ROLE_START_TAG}"
261
  inputs = tokenizer(text, return_tensors='pt', padding=True, add_special_tokens=False).to("cuda")
262
  outputs = model.generate(
263
  inputs=inputs["input_ids"],
@@ -271,18 +192,4 @@ outputs = model.generate(
271
  )
272
  gen_text = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
273
  print(gen_text)
274
- ```
275
-
276
-
277
- ## MD5
278
- 我们发现模型文件可能会在传输过程中损坏，使用前请检查文件MD5值。
279
-
280
- | 模型文件 | MD5值 |
281
- |:---------------------------------|:--------------------------------:|
282
- | pytorch_model-00001-of-00007.bin | 8d544b1bcb3449934184d4141137329c |
283
- | pytorch_model-00002-of-00007.bin | 9d5dbb30911e48a42fb6d0fcabb322a4 |
284
- | pytorch_model-00003-of-00007.bin | b0d4aecee0457d9332005a187e1fffed |
285
- | pytorch_model-00004-of-00007.bin | 5c7e002de5eab77d0194a2b0f6de0c24 |
286
- | pytorch_model-00005-of-00007.bin | d22a511aa26b5b17117b665a877490ab |
287
- | pytorch_model-00006-of-00007.bin | a5c28ac277fac07d16dd66537e54d109 |
288
- | pytorch_model-00007-of-00007.bin | a967e2c6195477b7407089c0bffa2d53 |
 
1
  ---
2
  license: other
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
  # Model Card for CodeFuse-CodeLlama-34B
5
+ ![Creation Approach](LOGO.png)
6
 
7
  [[中文]](#chinese) [[English]](#english)
8
 
 
18
 
19
  ## News and Updates
20
 
21
+ 🔥🔥🔥 CodeFuse-CodeLlama34B-MFT has achived 74.4% of pass@1 on HumanEval, which is SOTA at present.
 
 
22
 
23
  <br>
24
 
 
 
 
 
 
 
 
 
 
 
 
25
  ## Performance
26
 
27
+ | Model | HumanEval(pass@1) |
28
+ | :---------------------------- | :---------------: |
29
+ | CodeLlama-34b | 48.8%(greedy decoding) |
30
+ | CodeLlama-34b-Python | 53.7%(greedy decoding) |
31
+ | **CodeFuse-CodeLlama-34B** | **74.4%**(greedy decoding) |
 
 
 
 
 
 
 
 
32
 
33
  <br>
34
 
 
70
  ```
71
 
72
  ```python
 
73
  from transformers import (
74
  AutoTokenizer,
75
  AutoModelForCausalLM,
 
78
  tokenizer.padding_side = "left"
79
  tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<unk>")
80
  tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("</s>")
81
+ model = AutoModelForCausalLM.from_pretrained(mode_name_or_path, trust_remote_code=True)
 
 
 
 
 
 
82
 
83
  HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
84
  BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"
 
99
  print(gen_text)
100
  ```
101
 
 
 
102
 
 
 
 
 
 
 
 
 
 
103
 
104
 
105
+
106
+
107
+
108
+
109
+
110
+
111
+
112
+
 
 
 
 
113
 
114
  <a id="chinese"></a>
115
 
 
124
 
125
  <br>
126
 
 
 
 
 
 
 
 
 
 
 
127
  ## 评测表现(代码)
128
 
129
+ | 模型 | HumanEval(pass@1) |
130
+ | :---------------------------- | :---------------: |
131
+ | CodeLlama-34b | 48.8%(greedy decoding) |
132
+ | CodeLlama-34b-Python | 53.7%(greedy decoding) |
133
+ | **CodeFuse-CodeLlama-34B** | **74.4%**(greedy decoding) |
 
 
 
 
 
 
 
 
134
  <br>
135
 
136
  ## Requirements
 
173
  tokenizer.padding_side = "left"
174
  tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<unk>")
175
  tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("</s>")
176
+ model = AutoModelForCausalLM.from_pretrained(mode_name_or_path, trust_remote_code=True)
 
 
 
 
 
 
177
 
178
  HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
179
  BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"
180
 
181
+ text = f"{HUMAN_ROLE_START_TAG}write a python function of quick sort.{BOT_ROLE_START_TAG}"
182
  inputs = tokenizer(text, return_tensors='pt', padding=True, add_special_tokens=False).to("cuda")
183
  outputs = model.generate(
184
  inputs=inputs["input_ids"],
 
192
  )
193
  gen_text = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
194
  print(gen_text)
195
+ ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,29 +0,0 @@
1
- {
2
- "_name_or_path": "/mnt/user/qumu/download_models/codellama/CodeLlama-34b-Python-hf",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token": "</s>",
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 8192,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 22016,
13
- "max_position_embeddings": 16384,
14
- "model_type": "llama",
15
- "num_attention_heads": 64,
16
- "num_hidden_layers": 48,
17
- "num_key_value_heads": 8,
18
- "pad_token": "<unk>",
19
- "pad_token_id": 0,
20
- "pretraining_tp": 1,
21
- "rms_norm_eps": 1e-05,
22
- "rope_scaling": null,
23
- "rope_theta": 1000000,
24
- "tie_word_embeddings": false,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.32.0",
27
- "use_cache": true,
28
- "vocab_size": 32000
29
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.32.0"
6
- }
 
 
 
 
 
 
 
model-00001-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d5a54ef32471bb89edbd806822bb1cb26b2625399985d82d7c82bc0bd41a045
3
- size 9852623784
 
 
 
 
model-00002-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:36711f98ab1c35cd12d64cbfad5f32c63c6051635a636c5b0c030c054133417e
3
- size 9689078960
 
 
 
 
model-00003-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb22d378cd68bb5eb96d587b8ccc7154853ea46beb8982b30a2aa864163c7921
3
- size 9689078992
 
 
 
 
model-00004-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5440d42971927b4a1138b3428362258643f450bbb51aea455e87bb2c4fd0c4e1
3
- size 9689078992
 
 
 
 
model-00005-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3a96944cf0d98734b2cbac54c52f5395e38230d9e717c48869bbb30a140baa6
3
- size 9689078992
 
 
 
 
model-00006-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab1c88d8e5538b6981488d5346c25d27ccecbd4da00d02429b4660b91e091d5a
3
- size 9689078992
 
 
 
 
model-00007-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae8d424665e4c257d7a0339193c20d809c5bf6003fa2ba8dffad41c36a232cf
3
- size 9189972688
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,442 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 67487940608
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00007-of-00007.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
242
- "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
243
- "model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
244
- "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
245
- "model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
246
- "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
247
- "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
248
- "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
249
- "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
250
- "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
251
- "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
252
- "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
253
- "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
254
- "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
255
- "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
256
- "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
257
- "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
258
- "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
259
- "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
260
- "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
261
- "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
262
- "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
263
- "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
264
- "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
265
- "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
266
- "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
267
- "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
268
- "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
269
- "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
270
- "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
271
- "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
272
- "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
273
- "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
274
- "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
275
- "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
276
- "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
277
- "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
278
- "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
279
- "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
280
- "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
281
- "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
282
- "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
283
- "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
284
- "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
285
- "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
286
- "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
287
- "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
288
- "model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
289
- "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
290
- "model.layers.37.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
291
- "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
292
- "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
293
- "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
294
- "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
295
- "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
296
- "model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors",
297
- "model.layers.38.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
298
- "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
299
- "model.layers.38.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
300
- "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
301
- "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
302
- "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
303
- "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
304
- "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
305
- "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors",
306
- "model.layers.39.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
307
- "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
308
- "model.layers.39.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
309
- "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
310
- "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
311
- "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
312
- "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
313
- "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
314
- "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
315
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
316
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
317
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
318
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
319
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
320
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
321
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
322
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
323
- "model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors",
324
- "model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
325
- "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
326
- "model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
327
- "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
328
- "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
329
- "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
330
- "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
331
- "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
332
- "model.layers.41.input_layernorm.weight": "model-00007-of-00007.safetensors",
333
- "model.layers.41.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
334
- "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
335
- "model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
336
- "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
337
- "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
338
- "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
339
- "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
340
- "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
341
- "model.layers.42.input_layernorm.weight": "model-00007-of-00007.safetensors",
342
- "model.layers.42.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
343
- "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
344
- "model.layers.42.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
345
- "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
346
- "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
347
- "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
348
- "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
349
- "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
350
- "model.layers.43.input_layernorm.weight": "model-00007-of-00007.safetensors",
351
- "model.layers.43.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
352
- "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
353
- "model.layers.43.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
354
- "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
355
- "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
356
- "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
357
- "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
358
- "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
359
- "model.layers.44.input_layernorm.weight": "model-00007-of-00007.safetensors",
360
- "model.layers.44.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
361
- "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
362
- "model.layers.44.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
363
- "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
364
- "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
365
- "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
366
- "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
367
- "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
368
- "model.layers.45.input_layernorm.weight": "model-00007-of-00007.safetensors",
369
- "model.layers.45.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
370
- "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
371
- "model.layers.45.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
372
- "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
373
- "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
374
- "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
375
- "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
376
- "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
377
- "model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors",
378
- "model.layers.46.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
379
- "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
380
- "model.layers.46.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
381
- "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
382
- "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
383
- "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
384
- "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
385
- "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
386
- "model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors",
387
- "model.layers.47.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
388
- "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
389
- "model.layers.47.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
390
- "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
391
- "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
392
- "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
393
- "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
394
- "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
395
- "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
396
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
397
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
398
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
399
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
400
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
401
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
402
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
403
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
404
- "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
405
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
406
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
407
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
408
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
409
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
410
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
411
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
412
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
413
- "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
414
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
415
- "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
416
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
417
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
418
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
419
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
420
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
421
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
422
- "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
423
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
424
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
425
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
426
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
427
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
428
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
429
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
430
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
431
- "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
432
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
433
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
434
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
435
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
436
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
437
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
438
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
439
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
440
- "model.norm.weight": "model-00007-of-00007.safetensors"
441
- }
442
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
pytorch_model-00001-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb1cd3c944b6dd2ece21c09d7378a77ccc279867dfe4b8b8b7cbfa58e4ffe4a3
3
- size 9852638393
 
 
 
 
pytorch_model-00002-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1641f834b6d3938353873d95b642d0083ca806b7fd32dc8aaea0b3c64752b358
3
- size 9689094033
 
 
 
 
pytorch_model-00003-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:38ce1d749b110332ffbfc237c3271c10229f0913ed3e424aa61c4261af033357
3
- size 9689094033
 
 
 
 
pytorch_model-00004-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5c7a36d9f48fdd4b629f44d6e238085fa727f393c94e6cdf17d4f5da19be613
3
- size 9689094033
 
 
 
 
pytorch_model-00005-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ccdaa07cce1d16ed6d8ca1ca773b075f61c36d04430f8683b6e2bf458be4a72
3
- size 9689094033
 
 
 
 
pytorch_model-00006-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a257280910a701168406cc2114a669a975176ec08a373f7c2b7ba94d22c05215
3
- size 9689094033
 
 
 
 
pytorch_model-00007-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaef8ce33ccbc255d78026458d81fc9a55513a0d1ac3ef4f4f74967300af49e7
3
- size 9189986713
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a714170172282cfbcaa120af13c0df08b06d040ff24dab30229d8a010821d3d
3
- size 35838
 
 
 
 
requirements.txt DELETED
@@ -1,14 +0,0 @@
1
- numpy
2
- pandas
3
- einops
4
- sentencepiece
5
- deepspeed==0.9.3
6
- transformers==4.32.0
7
- accelerate==0.21.0
8
- peft==0.4.0
9
- BitsAndBytes==0.40.2
10
- xformers==0.0.21
11
- ujson
12
- jsonlines
13
- tiktoken
14
- transformers_stream_generator
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
tokenizer_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "legacy": null,
20
- "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
22
- "sp_model_kwargs": {},
23
- "tokenizer_class": "LlamaTokenizer",
24
- "unk_token": {
25
- "__type": "AddedToken",
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "use_default_system_prompt": true
33
- }