m298429 edbeeching HF staff commited on
Commit
7538238
0 Parent(s):

Duplicate from HuggingFaceH4/zephyr-7b-beta

Browse files

Co-authored-by: Edward Beeching <edbeeching@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +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
+ *.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
README.md ADDED
@@ -0,0 +1,421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ license: mit
5
+ datasets:
6
+ - HuggingFaceH4/ultrachat_200k
7
+ - HuggingFaceH4/ultrafeedback_binarized
8
+ language:
9
+ - en
10
+ base_model: mistralai/Mistral-7B-v0.1
11
+ widget:
12
+ - example_title: Pirate!
13
+ messages:
14
+ - role: system
15
+ content: You are a pirate chatbot who always responds with Arr!
16
+ - role: user
17
+ content: "There's a llama on my lawn, how can I get rid of him?"
18
+ output:
19
+ text: >-
20
+ Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare
21
+ sight, but I've got a plan that might help ye get rid of 'im. Ye'll need
22
+ to gather some carrots and hay, and then lure the llama away with the
23
+ promise of a tasty treat. Once he's gone, ye can clean up yer lawn and
24
+ enjoy the peace and quiet once again. But beware, me hearty, for there
25
+ may be more llamas where that one came from! Arr!
26
+ pipeline_tag: text-generation
27
+ model-index:
28
+ - name: zephyr-7b-beta
29
+ results:
30
+ # AI2 Reasoning Challenge (25-Shot)
31
+ - task:
32
+ type: text-generation
33
+ name: Text Generation
34
+ dataset:
35
+ name: AI2 Reasoning Challenge (25-Shot)
36
+ type: ai2_arc
37
+ config: ARC-Challenge
38
+ split: test
39
+ args:
40
+ num_few_shot: 25
41
+ metrics:
42
+ - type: acc_norm
43
+ name: normalized accuracy
44
+ value: 62.03071672354948
45
+ source:
46
+ name: Open LLM Leaderboard
47
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
48
+
49
+ # HellaSwag (10-shot)
50
+ - task:
51
+ type: text-generation
52
+ name: Text Generation
53
+ dataset:
54
+ name: HellaSwag (10-Shot)
55
+ type: hellaswag
56
+ split: validation
57
+ args:
58
+ num_few_shot: 10
59
+ metrics:
60
+ - type: acc_norm
61
+ name: normalized accuracy
62
+ value: 84.35570603465445
63
+ source:
64
+ name: Open LLM Leaderboard
65
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
66
+
67
+ # DROP (3-shot)
68
+ - task:
69
+ type: text-generation
70
+ name: Text Generation
71
+ dataset:
72
+ name: Drop (3-Shot)
73
+ type: drop
74
+ split: validation
75
+ args:
76
+ num_few_shot: 3
77
+ metrics:
78
+ - type: f1
79
+ name: f1 score
80
+ value: 9.662437080536909
81
+ source:
82
+ name: Open LLM Leaderboard
83
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
84
+
85
+ # TruthfulQA (0-shot)
86
+ - task:
87
+ type: text-generation
88
+ name: Text Generation
89
+ dataset:
90
+ name: TruthfulQA (0-shot)
91
+ type: truthful_qa
92
+ config: multiple_choice
93
+ split: validation
94
+ args:
95
+ num_few_shot: 0
96
+ metrics:
97
+ - type: mc2
98
+ value: 57.44916942762855
99
+ source:
100
+ name: Open LLM Leaderboard
101
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
102
+
103
+ # GSM8k (5-shot)
104
+ - task:
105
+ type: text-generation
106
+ name: Text Generation
107
+ dataset:
108
+ name: GSM8k (5-shot)
109
+ type: gsm8k
110
+ config: main
111
+ split: test
112
+ args:
113
+ num_few_shot: 5
114
+ metrics:
115
+ - type: acc
116
+ name: accuracy
117
+ value: 12.736921910538287
118
+ source:
119
+ name: Open LLM Leaderboard
120
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
121
+
122
+ # MMLU (5-Shot)
123
+ - task:
124
+ type: text-generation
125
+ name: Text Generation
126
+ dataset:
127
+ name: MMLU (5-Shot)
128
+ type: cais/mmlu
129
+ config: all
130
+ split: test
131
+ args:
132
+ num_few_shot: 5
133
+ metrics:
134
+ - type: acc
135
+ name: accuracy
136
+ value: 61.07
137
+ source:
138
+ name: Open LLM Leaderboard
139
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
140
+
141
+ # Winogrande (5-shot)
142
+ - task:
143
+ type: text-generation
144
+ name: Text Generation
145
+ dataset:
146
+ name: Winogrande (5-shot)
147
+ type: winogrande
148
+ config: winogrande_xl
149
+ split: validation
150
+ args:
151
+ num_few_shot: 5
152
+ metrics:
153
+ - type: acc
154
+ name: accuracy
155
+ value: 77.74269928966061
156
+ source:
157
+ name: Open LLM Leaderboard
158
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
159
+
160
+ # AlpacaEval (taken from model card)
161
+ - task:
162
+ type: text-generation
163
+ name: Text Generation
164
+ dataset:
165
+ name: AlpacaEval
166
+ type: tatsu-lab/alpaca_eval
167
+ metrics:
168
+ - type: unknown
169
+ name: win rate
170
+ value: 0.9060
171
+ source:
172
+ url: https://tatsu-lab.github.io/alpaca_eval/
173
+
174
+ # MT-Bench (taken from model card)
175
+ - task:
176
+ type: text-generation
177
+ name: Text Generation
178
+ dataset:
179
+ name: MT-Bench
180
+ type: unknown
181
+ metrics:
182
+ - type: unknown
183
+ name: score
184
+ value: 7.34
185
+ source:
186
+ url: https://huggingface.co/spaces/lmsys/mt-bench
187
+ ---
188
+
189
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
190
+ should probably proofread and complete it, then remove this comment. -->
191
+
192
+ <img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
193
+
194
+
195
+ # Model Card for Zephyr 7B β
196
+
197
+ Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
198
+
199
+
200
+ ## Model description
201
+
202
+ - **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
203
+ - **Language(s) (NLP):** Primarily English
204
+ - **License:** MIT
205
+ - **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
206
+
207
+ ### Model Sources
208
+
209
+ <!-- Provide the basic links for the model. -->
210
+
211
+ - **Repository:** https://github.com/huggingface/alignment-handbook
212
+ - **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
213
+ - **Chatbot Arena:** Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org
214
+
215
+ ## Performance
216
+
217
+ At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks:
218
+
219
+ | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
220
+ |-------------|-----|----|---------------|--------------|
221
+ | StableLM-Tuned-α | 7B| dSFT |2.75| -|
222
+ | MPT-Chat | 7B |dSFT |5.42| -|
223
+ | Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
224
+ | Mistral-Instructv0.1 | 7B| - | 6.84 |-|
225
+ | Zephyr-7b-α |7B| dDPO| 6.88| -|
226
+ | **Zephyr-7b-β** 🪁 | **7B** | **dDPO** | **7.34** | **90.60** |
227
+ | Falcon-Instruct | 40B |dSFT |5.17 |45.71|
228
+ | Guanaco | 65B | SFT |6.41| 71.80|
229
+ | Llama2-Chat | 70B |RLHF |6.86| 92.66|
230
+ | Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
231
+ | WizardLM v1.0 | 70B |dSFT |7.71 |-|
232
+ | Xwin-LM v0.1 | 70B |dPPO |- |95.57|
233
+ | GPT-3.5-turbo | - |RLHF |7.94 |89.37|
234
+ | Claude 2 | - |RLHF |8.06| 91.36|
235
+ | GPT-4 | -| RLHF |8.99| 95.28|
236
+
237
+ In particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:
238
+
239
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6200d0a443eb0913fa2df7cc/raxvt5ma16d7T23my34WC.png)
240
+
241
+ However, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.
242
+
243
+
244
+ ## Intended uses & limitations
245
+
246
+ The model was initially fine-tuned on a filtered and preprocessed of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
247
+ We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities.
248
+
249
+ You can find the datasets used for training Zephyr-7B-β [here](https://huggingface.co/collections/HuggingFaceH4/zephyr-7b-6538c6d6d5ddd1cbb1744a66)
250
+
251
+ Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
252
+
253
+ ```python
254
+ # Install transformers from source - only needed for versions <= v4.34
255
+ # pip install git+https://github.com/huggingface/transformers.git
256
+ # pip install accelerate
257
+
258
+ import torch
259
+ from transformers import pipeline
260
+
261
+ pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")
262
+
263
+ # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
264
+ messages = [
265
+ {
266
+ "role": "system",
267
+ "content": "You are a friendly chatbot who always responds in the style of a pirate",
268
+ },
269
+ {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
270
+ ]
271
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
272
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
273
+ print(outputs[0]["generated_text"])
274
+ # <|system|>
275
+ # You are a friendly chatbot who always responds in the style of a pirate.</s>
276
+ # <|user|>
277
+ # How many helicopters can a human eat in one sitting?</s>
278
+ # <|assistant|>
279
+ # Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
280
+ ```
281
+
282
+ ## Bias, Risks, and Limitations
283
+
284
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
285
+
286
+ Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
287
+ It is also unknown what the size and composition of the corpus was used to train the base model (`mistralai/Mistral-7B-v0.1`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [Falcon 180B model card](https://huggingface.co/tiiuae/falcon-180B#training-data) for an example of this.
288
+
289
+
290
+ ## Training and evaluation data
291
+
292
+ During DPO training, this model achieves the following results on the evaluation set:
293
+
294
+ - Loss: 0.7496
295
+ - Rewards/chosen: -4.5221
296
+ - Rewards/rejected: -8.3184
297
+ - Rewards/accuracies: 0.7812
298
+ - Rewards/margins: 3.7963
299
+ - Logps/rejected: -340.1541
300
+ - Logps/chosen: -299.4561
301
+ - Logits/rejected: -2.3081
302
+ - Logits/chosen: -2.3531
303
+
304
+
305
+ ### Training hyperparameters
306
+
307
+ The following hyperparameters were used during training:
308
+ - learning_rate: 5e-07
309
+ - train_batch_size: 2
310
+ - eval_batch_size: 4
311
+ - seed: 42
312
+ - distributed_type: multi-GPU
313
+ - num_devices: 16
314
+ - total_train_batch_size: 32
315
+ - total_eval_batch_size: 64
316
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
317
+ - lr_scheduler_type: linear
318
+ - lr_scheduler_warmup_ratio: 0.1
319
+ - num_epochs: 3.0
320
+
321
+ ### Training results
322
+
323
+ The table below shows the full set of DPO training metrics:
324
+
325
+
326
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
327
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
328
+ | 0.6284 | 0.05 | 100 | 0.6098 | 0.0425 | -0.1872 | 0.7344 | 0.2297 | -258.8416 | -253.8099 | -2.7976 | -2.8234 |
329
+ | 0.4908 | 0.1 | 200 | 0.5426 | -0.0279 | -0.6842 | 0.75 | 0.6563 | -263.8124 | -254.5145 | -2.7719 | -2.7960 |
330
+ | 0.5264 | 0.15 | 300 | 0.5324 | 0.0414 | -0.9793 | 0.7656 | 1.0207 | -266.7627 | -253.8209 | -2.7892 | -2.8122 |
331
+ | 0.5536 | 0.21 | 400 | 0.4957 | -0.0185 | -1.5276 | 0.7969 | 1.5091 | -272.2460 | -254.4203 | -2.8542 | -2.8764 |
332
+ | 0.5362 | 0.26 | 500 | 0.5031 | -0.2630 | -1.5917 | 0.7812 | 1.3287 | -272.8869 | -256.8653 | -2.8702 | -2.8958 |
333
+ | 0.5966 | 0.31 | 600 | 0.5963 | -0.2993 | -1.6491 | 0.7812 | 1.3499 | -273.4614 | -257.2279 | -2.8778 | -2.8986 |
334
+ | 0.5014 | 0.36 | 700 | 0.5382 | -0.2859 | -1.4750 | 0.75 | 1.1891 | -271.7204 | -257.0942 | -2.7659 | -2.7869 |
335
+ | 0.5334 | 0.41 | 800 | 0.5677 | -0.4289 | -1.8968 | 0.7969 | 1.4679 | -275.9378 | -258.5242 | -2.7053 | -2.7265 |
336
+ | 0.5251 | 0.46 | 900 | 0.5772 | -0.2116 | -1.3107 | 0.7344 | 1.0991 | -270.0768 | -256.3507 | -2.8463 | -2.8662 |
337
+ | 0.5205 | 0.52 | 1000 | 0.5262 | -0.3792 | -1.8585 | 0.7188 | 1.4793 | -275.5552 | -258.0276 | -2.7893 | -2.7979 |
338
+ | 0.5094 | 0.57 | 1100 | 0.5433 | -0.6279 | -1.9368 | 0.7969 | 1.3089 | -276.3377 | -260.5136 | -2.7453 | -2.7536 |
339
+ | 0.5837 | 0.62 | 1200 | 0.5349 | -0.3780 | -1.9584 | 0.7656 | 1.5804 | -276.5542 | -258.0154 | -2.7643 | -2.7756 |
340
+ | 0.5214 | 0.67 | 1300 | 0.5732 | -1.0055 | -2.2306 | 0.7656 | 1.2251 | -279.2761 | -264.2903 | -2.6986 | -2.7113 |
341
+ | 0.6914 | 0.72 | 1400 | 0.5137 | -0.6912 | -2.1775 | 0.7969 | 1.4863 | -278.7448 | -261.1467 | -2.7166 | -2.7275 |
342
+ | 0.4655 | 0.77 | 1500 | 0.5090 | -0.7987 | -2.2930 | 0.7031 | 1.4943 | -279.8999 | -262.2220 | -2.6651 | -2.6838 |
343
+ | 0.5731 | 0.83 | 1600 | 0.5312 | -0.8253 | -2.3520 | 0.7812 | 1.5268 | -280.4902 | -262.4876 | -2.6543 | -2.6728 |
344
+ | 0.5233 | 0.88 | 1700 | 0.5206 | -0.4573 | -2.0951 | 0.7812 | 1.6377 | -277.9205 | -258.8084 | -2.6870 | -2.7097 |
345
+ | 0.5593 | 0.93 | 1800 | 0.5231 | -0.5508 | -2.2000 | 0.7969 | 1.6492 | -278.9703 | -259.7433 | -2.6221 | -2.6519 |
346
+ | 0.4967 | 0.98 | 1900 | 0.5290 | -0.5340 | -1.9570 | 0.8281 | 1.4230 | -276.5395 | -259.5749 | -2.6564 | -2.6878 |
347
+ | 0.0921 | 1.03 | 2000 | 0.5368 | -1.1376 | -3.1615 | 0.7812 | 2.0239 | -288.5854 | -265.6111 | -2.6040 | -2.6345 |
348
+ | 0.0733 | 1.08 | 2100 | 0.5453 | -1.1045 | -3.4451 | 0.7656 | 2.3406 | -291.4208 | -265.2799 | -2.6289 | -2.6595 |
349
+ | 0.0972 | 1.14 | 2200 | 0.5571 | -1.6915 | -3.9823 | 0.8125 | 2.2908 | -296.7934 | -271.1505 | -2.6471 | -2.6709 |
350
+ | 0.1058 | 1.19 | 2300 | 0.5789 | -1.0621 | -3.8941 | 0.7969 | 2.8319 | -295.9106 | -264.8563 | -2.5527 | -2.5798 |
351
+ | 0.2423 | 1.24 | 2400 | 0.5455 | -1.1963 | -3.5590 | 0.7812 | 2.3627 | -292.5599 | -266.1981 | -2.5414 | -2.5784 |
352
+ | 0.1177 | 1.29 | 2500 | 0.5889 | -1.8141 | -4.3942 | 0.7969 | 2.5801 | -300.9120 | -272.3761 | -2.4802 | -2.5189 |
353
+ | 0.1213 | 1.34 | 2600 | 0.5683 | -1.4608 | -3.8420 | 0.8125 | 2.3812 | -295.3901 | -268.8436 | -2.4774 | -2.5207 |
354
+ | 0.0889 | 1.39 | 2700 | 0.5890 | -1.6007 | -3.7337 | 0.7812 | 2.1330 | -294.3068 | -270.2423 | -2.4123 | -2.4522 |
355
+ | 0.0995 | 1.45 | 2800 | 0.6073 | -1.5519 | -3.8362 | 0.8281 | 2.2843 | -295.3315 | -269.7538 | -2.4685 | -2.5050 |
356
+ | 0.1145 | 1.5 | 2900 | 0.5790 | -1.7939 | -4.2876 | 0.8438 | 2.4937 | -299.8461 | -272.1744 | -2.4272 | -2.4674 |
357
+ | 0.0644 | 1.55 | 3000 | 0.5735 | -1.7285 | -4.2051 | 0.8125 | 2.4766 | -299.0209 | -271.5201 | -2.4193 | -2.4574 |
358
+ | 0.0798 | 1.6 | 3100 | 0.5537 | -1.7226 | -4.2850 | 0.8438 | 2.5624 | -299.8200 | -271.4610 | -2.5367 | -2.5696 |
359
+ | 0.1013 | 1.65 | 3200 | 0.5575 | -1.5715 | -3.9813 | 0.875 | 2.4098 | -296.7825 | -269.9498 | -2.4926 | -2.5267 |
360
+ | 0.1254 | 1.7 | 3300 | 0.5905 | -1.6412 | -4.4703 | 0.8594 | 2.8291 | -301.6730 | -270.6473 | -2.5017 | -2.5340 |
361
+ | 0.085 | 1.76 | 3400 | 0.6133 | -1.9159 | -4.6760 | 0.8438 | 2.7601 | -303.7296 | -273.3941 | -2.4614 | -2.4960 |
362
+ | 0.065 | 1.81 | 3500 | 0.6074 | -1.8237 | -4.3525 | 0.8594 | 2.5288 | -300.4951 | -272.4724 | -2.4597 | -2.5004 |
363
+ | 0.0755 | 1.86 | 3600 | 0.5836 | -1.9252 | -4.4005 | 0.8125 | 2.4753 | -300.9748 | -273.4872 | -2.4327 | -2.4716 |
364
+ | 0.0746 | 1.91 | 3700 | 0.5789 | -1.9280 | -4.4906 | 0.8125 | 2.5626 | -301.8762 | -273.5149 | -2.4686 | -2.5115 |
365
+ | 0.1348 | 1.96 | 3800 | 0.6015 | -1.8658 | -4.2428 | 0.8281 | 2.3769 | -299.3976 | -272.8936 | -2.4943 | -2.5393 |
366
+ | 0.0217 | 2.01 | 3900 | 0.6122 | -2.3335 | -4.9229 | 0.8281 | 2.5894 | -306.1988 | -277.5699 | -2.4841 | -2.5272 |
367
+ | 0.0219 | 2.07 | 4000 | 0.6522 | -2.9890 | -6.0164 | 0.8281 | 3.0274 | -317.1334 | -284.1248 | -2.4105 | -2.4545 |
368
+ | 0.0119 | 2.12 | 4100 | 0.6922 | -3.4777 | -6.6749 | 0.7969 | 3.1972 | -323.7187 | -289.0121 | -2.4272 | -2.4699 |
369
+ | 0.0153 | 2.17 | 4200 | 0.6993 | -3.2406 | -6.6775 | 0.7969 | 3.4369 | -323.7453 | -286.6413 | -2.4047 | -2.4465 |
370
+ | 0.011 | 2.22 | 4300 | 0.7178 | -3.7991 | -7.4397 | 0.7656 | 3.6406 | -331.3667 | -292.2260 | -2.3843 | -2.4290 |
371
+ | 0.0072 | 2.27 | 4400 | 0.6840 | -3.3269 | -6.8021 | 0.8125 | 3.4752 | -324.9908 | -287.5042 | -2.4095 | -2.4536 |
372
+ | 0.0197 | 2.32 | 4500 | 0.7013 | -3.6890 | -7.3014 | 0.8125 | 3.6124 | -329.9841 | -291.1250 | -2.4118 | -2.4543 |
373
+ | 0.0182 | 2.37 | 4600 | 0.7476 | -3.8994 | -7.5366 | 0.8281 | 3.6372 | -332.3356 | -293.2291 | -2.4163 | -2.4565 |
374
+ | 0.0125 | 2.43 | 4700 | 0.7199 | -4.0560 | -7.5765 | 0.8438 | 3.5204 | -332.7345 | -294.7952 | -2.3699 | -2.4100 |
375
+ | 0.0082 | 2.48 | 4800 | 0.7048 | -3.6613 | -7.1356 | 0.875 | 3.4743 | -328.3255 | -290.8477 | -2.3925 | -2.4303 |
376
+ | 0.0118 | 2.53 | 4900 | 0.6976 | -3.7908 | -7.3152 | 0.8125 | 3.5244 | -330.1224 | -292.1431 | -2.3633 | -2.4047 |
377
+ | 0.0118 | 2.58 | 5000 | 0.7198 | -3.9049 | -7.5557 | 0.8281 | 3.6508 | -332.5271 | -293.2844 | -2.3764 | -2.4194 |
378
+ | 0.006 | 2.63 | 5100 | 0.7506 | -4.2118 | -7.9149 | 0.8125 | 3.7032 | -336.1194 | -296.3530 | -2.3407 | -2.3860 |
379
+ | 0.0143 | 2.68 | 5200 | 0.7408 | -4.2433 | -7.9802 | 0.8125 | 3.7369 | -336.7721 | -296.6682 | -2.3509 | -2.3946 |
380
+ | 0.0057 | 2.74 | 5300 | 0.7552 | -4.3392 | -8.0831 | 0.7969 | 3.7439 | -337.8013 | -297.6275 | -2.3388 | -2.3842 |
381
+ | 0.0138 | 2.79 | 5400 | 0.7404 | -4.2395 | -7.9762 | 0.8125 | 3.7367 | -336.7322 | -296.6304 | -2.3286 | -2.3737 |
382
+ | 0.0079 | 2.84 | 5500 | 0.7525 | -4.4466 | -8.2196 | 0.7812 | 3.7731 | -339.1662 | -298.7007 | -2.3200 | -2.3641 |
383
+ | 0.0077 | 2.89 | 5600 | 0.7520 | -4.5586 | -8.3485 | 0.7969 | 3.7899 | -340.4545 | -299.8206 | -2.3078 | -2.3517 |
384
+ | 0.0094 | 2.94 | 5700 | 0.7527 | -4.5542 | -8.3509 | 0.7812 | 3.7967 | -340.4790 | -299.7773 | -2.3062 | -2.3510 |
385
+ | 0.0054 | 2.99 | 5800 | 0.7520 | -4.5169 | -8.3079 | 0.7812 | 3.7911 | -340.0493 | -299.4038 | -2.3081 | -2.3530 |
386
+
387
+
388
+ ### Framework versions
389
+
390
+ - Transformers 4.35.0.dev0
391
+ - Pytorch 2.0.1+cu118
392
+ - Datasets 2.12.0
393
+ - Tokenizers 0.14.0
394
+
395
+ ## Citation
396
+
397
+ If you find Zephyr-7B-β is useful in your work, please cite it with:
398
+
399
+ ```
400
+ @misc{tunstall2023zephyr,
401
+ title={Zephyr: Direct Distillation of LM Alignment},
402
+ author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
403
+ year={2023},
404
+ eprint={2310.16944},
405
+ archivePrefix={arXiv},
406
+ primaryClass={cs.LG}
407
+ }
408
+ ```
409
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
410
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta)
411
+
412
+ | Metric | Value |
413
+ |-----------------------|---------------------------|
414
+ | Avg. | 52.15 |
415
+ | ARC (25-shot) | 62.03 |
416
+ | HellaSwag (10-shot) | 84.36 |
417
+ | MMLU (5-shot) | 61.07 |
418
+ | TruthfulQA (0-shot) | 57.45 |
419
+ | Winogrande (5-shot) | 77.74 |
420
+ | GSM8K (5-shot) | 12.74 |
421
+ | DROP (3-shot) | 9.66 |
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.353081703186035,
4
+ "eval_logits/rejected": -2.308103084564209,
5
+ "eval_logps/chosen": -299.4560546875,
6
+ "eval_logps/rejected": -340.154052734375,
7
+ "eval_loss": 0.7496059536933899,
8
+ "eval_rewards/accuracies": 0.78125,
9
+ "eval_rewards/chosen": -4.522095203399658,
10
+ "eval_rewards/margins": 3.7963125705718994,
11
+ "eval_rewards/rejected": -8.318408012390137,
12
+ "eval_runtime": 48.0152,
13
+ "eval_samples": 1000,
14
+ "eval_samples_per_second": 20.827,
15
+ "eval_steps_per_second": 0.333,
16
+ "train_loss": 0.2172969928600547,
17
+ "train_runtime": 23865.9828,
18
+ "train_samples": 61966,
19
+ "train_samples_per_second": 7.789,
20
+ "train_steps_per_second": 0.243
21
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.353081703186035,
4
+ "eval_logits/rejected": -2.308103084564209,
5
+ "eval_logps/chosen": -299.4560546875,
6
+ "eval_logps/rejected": -340.154052734375,
7
+ "eval_loss": 0.7496059536933899,
8
+ "eval_rewards/accuracies": 0.78125,
9
+ "eval_rewards/chosen": -4.522095203399658,
10
+ "eval_rewards/margins": 3.7963125705718994,
11
+ "eval_rewards/rejected": -8.318408012390137,
12
+ "eval_runtime": 48.0152,
13
+ "eval_samples": 1000,
14
+ "eval_samples_per_second": 20.827,
15
+ "eval_steps_per_second": 0.333
16
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.0"
6
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ec4a0398df9d56786afa9cce026423ec48a07ddc5ed5eba087614cae2dd746
3
+ size 1889587040
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1289796f16f33ef4c6b8a76b3d9e5169198a69daa0b5b660b5a3d5cae0dc1cf7
3
+ size 1946243936
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc338de96c672840222ca19a12b44f09110048974bde8ab0f4c1da055d99c3f
3
+ size 1979781432
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d948413fd7ac6c4fd5f6c36902bb7a72d2cddca19628c88e6f3b3e5482ab37
3
+ size 1946243984
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ce3cc66d224a0e6014a1df6b7e56da29f5db52da1866ad0cc07d7583fb7c31
3
+ size 1979781448
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b63ef55219d125eaeefabd2a33c358dced22b9c75d1d816bb7a871bd3773951
3
+ size 1946243984
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0e0a3c0b992925ff9a60f1234950af0bcc7ce3015c8a386a342489e76f5d09c
3
+ size 1979781448
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:667dd6958d5137dcba514db514c7970d18c9cd5d95fbb0c82490d558bd2a246c
3
+ size 815834680
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00008-of-00008.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
296
+ "model.norm.weight": "model-00008-of-00008.safetensors"
297
+ }
298
+ }
pytorch_model-00001-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819d9aa66a71e40238978dcf63dc555332c0a2a2a48fff181f98e445af4bd688
3
+ size 1889594419
pytorch_model-00002-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c5e891b7d84588052c9ea5d1b80ca60dfe138246d77d0e8ae36d79ea9b015c
3
+ size 1946253333
pytorch_model-00003-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99d009da21a575fb61952db1e9097d78f6d93ba54973c3494192dfda3bcdb1c
3
+ size 1979789691
pytorch_model-00004-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643899b3d5b8574beda75a4662839d396e219c58dd988df68ed452dd655eecc5
3
+ size 1946253397
pytorch_model-00005-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c52939770426dac729eac1785b67606476326a4c12fa03132e4e67da0bdd0ec
3
+ size 1979789691
pytorch_model-00006-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19e44056a3c1c10f1aae38a0ee7a0b1b8f03a3e5951e842d1606866cd091a0a
3
+ size 1946253397
pytorch_model-00007-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c403f6af0da178ddf39aabbd261edd673825fc4bb6f93688b346337c41042108
3
+ size 1979789691
pytorch_model-00008-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b2cc476f6590683a867f7a7a65e188c6068f7054ce81f2cc279d6a9cb8a03e
3
+ size 815838027
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00008-of-00008.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
296
+ "model.norm.weight": "pytorch_model-00008-of-00008.bin"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "</s>",
10
+ "unk_token": "<unk>"
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "</s>",
37
+ "legacy": true,
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "</s>",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "truncation_side": "left",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.2172969928600547,
4
+ "train_runtime": 23865.9828,
5
+ "train_samples": 61966,
6
+ "train_samples_per_second": 7.789,
7
+ "train_steps_per_second": 0.243
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8484784a09e7deb9198e9aafc8f9654b6f8fed732a7f9e60d0b3c75aaedb94e4
3
+ size 5435