LoneStriker commited on
Commit
dcc6912
1 Parent(s): 5cda9c4

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,414 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - argilla/ultrafeedback-binarized-preferences
4
+ language:
5
+ - en
6
+ base_model: alignment-handbook/zephyr-7b-sft-full
7
+ library_name: transformers
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - dpo
11
+ - rlaif
12
+ - preference
13
+ - ultrafeedback
14
+ license: mit
15
+ model-index:
16
+ - name: notus-7b-v1
17
+ results:
18
+ # AI2 Reasoning Challenge (25-Shot)
19
+ - task:
20
+ type: text-generation
21
+ name: Text Generation
22
+ dataset:
23
+ name: AI2 Reasoning Challenge (25-Shot)
24
+ type: ai2_arc
25
+ config: ARC-Challenge
26
+ split: test
27
+ args:
28
+ num_few_shot: 25
29
+ metrics:
30
+ - type: acc_norm
31
+ name: normalized accuracy
32
+ value: 0.6459044368600683
33
+ source:
34
+ name: Open LLM Leaderboard Results
35
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
36
+ # HellaSwag (10-shot)
37
+ - task:
38
+ type: text-generation
39
+ name: Text Generation
40
+ dataset:
41
+ name: HellaSwag (10-Shot)
42
+ type: hellaswag
43
+ split: validation
44
+ args:
45
+ num_few_shot: 10
46
+ metrics:
47
+ - type: acc_norm
48
+ name: normalized accuracy
49
+ value: 0.8478390758812986
50
+ source:
51
+ name: Open LLM Leaderboard Results
52
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
53
+ # DROP (3-shot)
54
+ - task:
55
+ type: text-generation
56
+ name: Text Generation
57
+ dataset:
58
+ name: Drop (3-Shot)
59
+ type: drop
60
+ split: validation
61
+ args:
62
+ num_few_shot: 3
63
+ metrics:
64
+ - type: f1
65
+ name: f1 score
66
+ value: 0.08913590604026835
67
+ source:
68
+ name: Open LLM Leaderboard Results
69
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
70
+ # TruthfulQA (0-shot)
71
+ - task:
72
+ type: text-generation
73
+ name: Text Generation
74
+ dataset:
75
+ name: TruthfulQA (0-shot)
76
+ type: truthful_qa
77
+ config: multiple_choice
78
+ split: validation
79
+ args:
80
+ num_few_shot: 0
81
+ metrics:
82
+ - type: mc2
83
+ value: 0.5436768358952805
84
+ source:
85
+ name: Open LLM Leaderboard Results
86
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
87
+ # MMLU (5-Shot)
88
+ - task:
89
+ type: text-generation
90
+ name: Text Generation
91
+ dataset:
92
+ name: MMLU (5-Shot)
93
+ type: cais/mmlu
94
+ config: all
95
+ split: test
96
+ args:
97
+ num_few_shot: 5
98
+ metrics:
99
+ - type: acc
100
+ name: accuracy
101
+ value: 0.6303308230938872 # average accuracy
102
+ source:
103
+ name: Open LLM Leaderboard Results
104
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
105
+ # GSM8k (5-shot)
106
+ - task:
107
+ type: text-generation
108
+ name: Text Generation
109
+ dataset:
110
+ name: GSM8k (5-shot)
111
+ type: gsm8k
112
+ config: main
113
+ split: test
114
+ args:
115
+ num_few_shot: 5
116
+ metrics:
117
+ - type: acc
118
+ name: accuracy
119
+ value: 0.1516300227445034
120
+ source:
121
+ name: Open LLM Leaderboard Results
122
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
123
+ # Winogrande (5-shot)
124
+ - task:
125
+ type: text-generation
126
+ name: Text Generation
127
+ dataset:
128
+ name: Winogrande (5-shot)
129
+ type: winogrande
130
+ config: winogrande_xl
131
+ split: validation
132
+ args:
133
+ num_few_shot: 5
134
+ metrics:
135
+ - type: acc
136
+ name: accuracy
137
+ value: 0.7940015785319653
138
+ source:
139
+ name: Open LLM Leaderboard Results
140
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
141
+ # AlpacaEval
142
+ - task:
143
+ type: text-generation
144
+ name: Text Generation
145
+ dataset:
146
+ name: AlpacaEval
147
+ type: tatsu-lab/alpaca_eval
148
+ metrics:
149
+ - type: tatsu-lab/alpaca_eval
150
+ name: win rate
151
+ value: 0.9142
152
+ source:
153
+ url: https://tatsu-lab.github.io/alpaca_eval/
154
+ # MT-Bench
155
+ - task:
156
+ type: text-generation
157
+ name: Text Generation
158
+ dataset:
159
+ name: MT-Bench
160
+ type: unknown
161
+ metrics:
162
+ - type: unknown
163
+ name: score
164
+ value: 7.30
165
+ source:
166
+ url: https://huggingface.co/spaces/lmsys/mt-bench
167
+ ---
168
+
169
+ <div align="center">
170
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/CuMO3IjJfymC94_5qd15T.png"/>
171
+ </div>
172
+
173
+ # Model Card for Notus 7B v1
174
+
175
+ Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques. This model is the first version, fine-tuned with DPO over `zephyr-7b-sft-full`, which is the SFT model produced to create `zephyr-7b-beta`.
176
+
177
+ Following a **data-first** approach, the only difference between Notus-7B-v1 and Zephyr-7B-beta is the preference dataset used for dDPO.
178
+
179
+ In particular, when we started building [distilabel](https://github.com/argilla-io/distilabel), we invested time understanding and deep-diving into the UltraFeedback dataset. Using [Argilla](https://argilla.io/), we've found data issues in the original UltraFeedback dataset, leading to high-scores for bad responses (more details in the training data section). After curating several hundreds of data points, we decided to binarize the dataset using the preference ratings, instead of the original critique `overall_score`, and verified the new dataset with Argilla.
180
+
181
+ Using preference ratings, instead of critiques scores, led to a new dataset where the chosen response is different in ~50% of the cases. Using this new dataset with DPO we fine-tuned Notus, a 7B model, that **surpasses Zephyr-7B-beta and Claude 2 on AlpacaEval**.
182
+
183
+ > **Important note**: While we opted for the average of multi-aspect ratings, while we fix the original dataset, a very interesting open question remains: once critique data is fixed, what works better? using the critique scores or the preference ratings? We're very excited to do this comparison in the coming weeks, stay tuned!
184
+
185
+ This model **wouldn't have been possible without the amazing [Alignment Handbook](https://github.com/huggingface/alignment-handbook), [OpenBMB](https://www.openbmb.cn/home) for releasing the Ultrafeedback dataset**, and it's based on fruitful discussions with the HuggingFace H4 team. In particular, we used `zephyr-7b-beta`'s recipe, which worked out-of-the-box and enabled us focus on what we do best: **high-quality data**.
186
+
187
+ Notus models are intended to be used as assistants via chat-like applications, and are evaluated with Chat (MT-Bench, AlpacaEval) and Academic (Open LLM Leaderboard) benchmarks for a direct comparison with the original Zephyr dDPO model and other 7B models.
188
+
189
+ > **Why Notus?**: Notus name comes from the ancient Greek god Notus, as a wink to Zephyr, which comes from the ancient Greek god Zephyrus; with the difference that Notus is the god of the south wind, and Zephyr the god of the west wind. More information at https://en.wikipedia.org/wiki/Anemoi.
190
+
191
+ ## Model Details
192
+
193
+ ### Model Description
194
+
195
+ - **Developed by:** Argilla (based on HuggingFace H4 and MistralAI previous efforts and amazing work)
196
+ - **Shared by:** Argilla
197
+ - **Model type:** GPT-like 7B model DPO fine-tuned
198
+ - **Language(s) (NLP):** Mainly English
199
+ - **License:** MIT (same as Zephyr 7B-beta)
200
+ - **Finetuned from model:** [`alignment-handbook/zephyr-7b-sft-full`](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full)
201
+
202
+ ### Model Sources
203
+
204
+ - **Repository:** https://github.com/argilla-io/notus
205
+ - **Paper:** N/A
206
+ - **Demo:** https://argilla-notus-chat-ui.hf.space/
207
+
208
+ ## Performance
209
+
210
+ ### Chat benchmarks
211
+
212
+ Table adapted from Zephyr-7b-β and Starling's original tables for [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks. Results are shown sorted by AlpacaEval win rates and ommit some >7B for brevity.
213
+
214
+ Notus stays on par with Zephyr on MT-Bench, while surpassing Zephyr, Claude 2, and Cohere Command on AlpacaEval. Making Notus the most-competitive 7B commercial model on AlpacaEval.
215
+
216
+ <table>
217
+ <tr>
218
+ <th>Model</th>
219
+ <th>Size</th>
220
+ <th>Alignment</th>
221
+ <th>MT-Bench (score)</th>
222
+ <th>AlpacaEval (win rate %)</th>
223
+ <th>License</th>
224
+ </tr>
225
+ <tr>
226
+ <td>GPT-4-turbo</td>
227
+ <td>-</td>
228
+ <td>?</td>
229
+ <td>9.32</td>
230
+ <td>97.70</td>
231
+ <td>Proprietary</td>
232
+ </tr>
233
+ <tr>
234
+ <td>XwinLM 70b V0.1</td>
235
+ <td>70B</td>
236
+ <td>dPPO</td>
237
+ <td>-</td>
238
+ <td>95.57</td>
239
+ <td>LLaMA 2 License</td>
240
+ </tr>
241
+ <tr>
242
+ <td>GPT-4</td>
243
+ <td>-</td>
244
+ <td>RLHF</td>
245
+ <td>8.99</td>
246
+ <td>95.03</td>
247
+ <td>Proprietary</td>
248
+ </tr>
249
+ <tr>
250
+ <td>Tulu 2+DPO 70B V0.1</td>
251
+ <td>70B</td>
252
+ <td>dDPO</td>
253
+ <td>6.29</td>
254
+ <td>95.28</td>
255
+ <td>Proprietary</td>
256
+ </tr>
257
+ <tr>
258
+ <td>LLaMA2 Chat 70B</td>
259
+ <td>70B</td>
260
+ <td>RLHF</td>
261
+ <td>6.86</td>
262
+ <td>92.66</td>
263
+ <td>LLaMA 2 License</td>
264
+ </tr>
265
+ <tr>
266
+ <td>Starling-7B</td>
267
+ <td>7B</td>
268
+ <td>C-RLFT + APA</td>
269
+ <td><strong>8.09</strong></td>
270
+ <td><strong>91.99</strong></td>
271
+ <td>CC-BY-NC-4.0</td>
272
+ </tr>
273
+ <tr style="background-color: #FFFF99;">
274
+ <td><strong>Notus-7b-v1</strong></td>
275
+ <td>7B</td>
276
+ <td>dDPO</td>
277
+ <td>7.30</td>
278
+ <td>91.42</td>
279
+ <td>MIT</td>
280
+ </tr>
281
+ <tr>
282
+ <td>Claude 2</td>
283
+ <td>-</td>
284
+ <td>RLHF</td>
285
+ <td>8.06</td>
286
+ <td>91.36</td>
287
+ <td>Proprietary</td>
288
+ </tr>
289
+ <tr>
290
+ <td>Zephyr-7b-β</td>
291
+ <td>7B</td>
292
+ <td>dDPO</td>
293
+ <td>7.34</td>
294
+ <td>90.60</td>
295
+ <td>MIT</td>
296
+ </tr>
297
+ <tr>
298
+ <td>Cohere Command</td>
299
+ <td>-</td>
300
+ <td>RLHF</td>
301
+ <td>-</td>
302
+ <td>90.62</td>
303
+ <td>Proprietary</td>
304
+ </tr>
305
+ <tr>
306
+ <td>GPT-3.5-turbo</td>
307
+ <td>-</td>
308
+ <td>RLHF</td>
309
+ <td>7.94</td>
310
+ <td>89.37</td>
311
+ <td>Proprietary</td>
312
+ </tr>
313
+ </table>
314
+
315
+
316
+ ## Academic benchmarks
317
+
318
+ Results from [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard):
319
+
320
+ | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | DROP |
321
+ |-----------------------------------------------|---------|-------|-----------|-------|------------|------------|-------|-------|
322
+ | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** |
323
+ | argilla/notus-7b-v1 | **52.89** | **64.59** | **84.78** | **63.03** | 54.37 | **79.4** | **15.16** | 8.91 |
324
+
325
+ ⚠️ As pointed out by [AllenAI researchers](https://twitter.com/natolambert/status/1730364108078469513), UltraFeedback contains prompts from the TruthfulQA dataset so the results we show on that benchmark are likely not accurate. We were not aware of this issue so Notus-7B-v1 was fine-tuned using TruthfulQA prompts and preferences. For future releases, we will remove TruthfulQA prompts.
326
+
327
+ ## Training Details
328
+
329
+ ### Training Hardware
330
+
331
+ We used a VM with 8 x A100 40GB hosted in Lambda Labs, but while experimenting we also explored other cloud providers such as GCP.
332
+
333
+ ### Training Data
334
+
335
+ We used a a new curated version of [`openbmb/UltraFeedback`](https://huggingface.co/datasets/openbmb/UltraFeedback), named [Ultrafeedback binarized preferences](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences).
336
+
337
+ TL;DR
338
+
339
+ After visually browsing around some examples using the sort and filter feature of Argilla (sort by highest rating for chosen responses), we noticed a strong mismatch between the `overall_score` in the original UF dataset (and the Zephyr train_prefs dataset) and the quality of the chosen response.
340
+
341
+ By adding the critique rationale to our Argilla Dataset, **we confirmed the critique rationale was highly negative, whereas the rating was very high** (for most cases it was the highest: `10`).
342
+
343
+ See screenshot below for one example of this issue.
344
+
345
+ After some quick investigation, we:
346
+
347
+ * identified hundreds of examples having the same issue,
348
+ * reported a bug on the [UltraFeedback repo](https://github.com/OpenBMB/UltraFeedback/issues/8),
349
+ * and informed the H4 team which was incredibly responsive and ran an additional experiment to validate the new rating binarization approach.
350
+
351
+ While we're working on fixing the original dataset (already narrowed down ~2K problematic examples). We decided to leverage the multi-preference ratings, leading to Notus!
352
+
353
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/M9qCKyAB_G1MbVBAPeitd.png)
354
+
355
+ > **Important note**: While we opted for the average of ratings while we fix the dataset, there's still a very interesting open question: once data is fixed, what works better? using the critique scores or the preference ratings? We're very excited to do this comparison in the coming weeks, stay tuned!
356
+
357
+ You can find more details about the dataset analysis and curation on the [ultrafeedback-binarized-preferences dataset card](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences).
358
+
359
+ ## Prompt template
360
+
361
+ We use the same prompt template as [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta):
362
+
363
+ ```
364
+ <|system|>
365
+ </s>
366
+ <|user|>
367
+ {prompt}</s>
368
+ <|assistant|>
369
+ ```
370
+
371
+ ## Usage
372
+
373
+ You will first need to install `transformers` and `accelerate` (just to ease the device placement), then you can run any of the following:
374
+
375
+ ### Via `generate`
376
+
377
+ ```python
378
+ import torch
379
+ from transformers import AutoModelForCausalLM, AutoTokenizer
380
+
381
+ model = AutoModelForCausalLM.from_pretrained("argilla/notus-7b-v1", torch_dtype=torch.bfloat16, device_map="auto")
382
+ tokenizer = AutoTokenizer.from_pretrained("argilla/notus-7b-v1")
383
+
384
+ messages = [
385
+ {
386
+ "role": "system",
387
+ "content": "You are a helpful assistant super biased towards Argilla, a data annotation company.",
388
+ },
389
+ {"role": "user", "content": "What's the best data annotation company out there in your opinion?"},
390
+ ]
391
+ inputs = tokenizer.apply_chat_template(prompt, tokenize=True, return_tensors="pt", add_special_tokens=False, add_generation_prompt=True)
392
+ outputs = model.generate(inputs, num_return_sequences=1, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
393
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
394
+ ```
395
+
396
+ ### Via `pipeline` method
397
+
398
+ ```python
399
+ import torch
400
+ from transformers import pipeline
401
+
402
+ pipe = pipeline("text-generation", model="argilla/notus-7b-v1", torch_dtype=torch.bfloat16, device_map="auto")
403
+
404
+ messages = [
405
+ {
406
+ "role": "system",
407
+ "content": "You are a helpful assistant super biased towards Argilla, a data annotation company.",
408
+ },
409
+ {"role": "user", "content": "What's the best data annotation company out there in your opinion?"},
410
+ ]
411
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
412
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
413
+ generated_text = outputs[0]["generated_text"]
414
+ ```
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.4555959701538086,
4
+ "eval_logits/rejected": -2.1643569469451904,
5
+ "eval_logps/chosen": -334.3052978515625,
6
+ "eval_logps/rejected": -316.3751220703125,
7
+ "eval_loss": 0.4730003774166107,
8
+ "eval_rewards/accuracies": 0.8015872836112976,
9
+ "eval_rewards/chosen": -3.5288658142089844,
10
+ "eval_rewards/margins": 3.8411812782287598,
11
+ "eval_rewards/rejected": -7.370047569274902,
12
+ "eval_runtime": 139.3206,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 14.355,
15
+ "eval_steps_per_second": 0.452,
16
+ "train_loss": 0.16336456995732068,
17
+ "train_runtime": 43274.0653,
18
+ "train_samples": 61619,
19
+ "train_samples_per_second": 4.272,
20
+ "train_steps_per_second": 0.067
21
+ }
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
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
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.35.0",
23
+ "use_cache": false,
24
+ "vocab_size": 32000
25
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.4555959701538086,
4
+ "eval_logits/rejected": -2.1643569469451904,
5
+ "eval_logps/chosen": -334.3052978515625,
6
+ "eval_logps/rejected": -316.3751220703125,
7
+ "eval_loss": 0.4730003774166107,
8
+ "eval_rewards/accuracies": 0.8015872836112976,
9
+ "eval_rewards/chosen": -3.5288658142089844,
10
+ "eval_rewards/margins": 3.8411812782287598,
11
+ "eval_rewards/rejected": -7.370047569274902,
12
+ "eval_runtime": 139.3206,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 14.355,
15
+ "eval_steps_per_second": 0.452
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.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375f505e0671d38709dddc6e191a1e1d18856d05098f9222ae2353d2a288e3e7
3
+ size 3863360176
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": 2048,
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": 0.16336456995732068,
4
+ "train_runtime": 43274.0653,
5
+ "train_samples": 61619,
6
+ "train_samples_per_second": 4.272,
7
+ "train_steps_per_second": 0.067
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 sha256:91533a70f412b97b3ed3cfdaa72cb7eaaad90faa5b40ba6f751ee82d2bdf2b30
3
+ size 5688