NeoChen1024 commited on
Commit
dced483
1 Parent(s): c574d78

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,485 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-Nemo-Base-2407
4
+ tags:
5
+ - generated_from_trainer
6
+ - axolotl
7
+ datasets:
8
+ - cognitivecomputations/Dolphin-2.9
9
+ - teknium/OpenHermes-2.5
10
+ - m-a-p/CodeFeedback-Filtered-Instruction
11
+ - cognitivecomputations/dolphin-coder
12
+ - cognitivecomputations/samantha-data
13
+ - microsoft/orca-math-word-problems-200k
14
+ - Locutusque/function-calling-chatml
15
+ - internlm/Agent-FLAN
16
+ ---
17
+
18
+ # Dolphin 2.9.3 Mistral Nemo 12b 🐬
19
+
20
+ Curated and trained by Eric Hartford and Cognitive Computations
21
+
22
+ [![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/h3K4XGj2RH)
23
+ Discord: https://discord.gg/h3K4XGj2RH
24
+
25
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
26
+
27
+ Our appreciation for the sponsors of Dolphin 2.9.3:
28
+ - [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xL40S node
29
+
30
+ This model is based on mistralai/Mistral-Nemo-Base-2407, and is governed by the apache 2.0 license.
31
+
32
+ The base model has 128K context, and our finetuning used 8192 sequence length.
33
+
34
+ Dolphin 2.9.3 uses ChatML prompt template format.
35
+
36
+ example:
37
+
38
+ ```
39
+ <|im_start|>system
40
+ You are Dolphin, a helpful AI assistant.<|im_end|>
41
+ <|im_start|>user
42
+ {prompt}<|im_end|>
43
+ <|im_start|>assistant
44
+
45
+ ```
46
+
47
+ Dolphin-2.9.3 has a variety of instruction following, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
48
+
49
+ Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
50
+
51
+ Dolphin is licensed according to apache 2.0 license. We grant permission for any use, including commercial. Dolphin was trained on data generated from GPT4, among other models.
52
+
53
+ ## Evals
54
+
55
+ <details><summary>See evals</summary>
56
+
57
+ ```
58
+ | Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
59
+ |-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
60
+ |leaderboard |N/A |none | 0|acc |↑ |0.3437|± |0.0043|
61
+ | | |none | 0|acc_norm |↑ |0.5076|± |0.0053|
62
+ | | |none | 0|exact_match |↑ |0.0536|± |0.0061|
63
+ | | |none | 0|inst_level_loose_acc |↑ |0.4388|± |N/A |
64
+ | | |none | 0|inst_level_strict_acc |↑ |0.3741|± |N/A |
65
+ | | |none | 0|prompt_level_loose_acc |↑ |0.3105|± |0.0199|
66
+ | | |none | 0|prompt_level_strict_acc|↑ |0.2477|± |0.0186|
67
+ | - leaderboard_bbh |N/A |none | 3|acc_norm |↑ |0.5549|± |0.0061|
68
+ | - leaderboard_bbh_boolean_expressions | 0|none | 3|acc_norm |↑ |0.8640|± |0.0217|
69
+ | - leaderboard_bbh_causal_judgement | 0|none | 3|acc_norm |↑ |0.6417|± |0.0352|
70
+ | - leaderboard_bbh_date_understanding | 0|none | 3|acc_norm |↑ |0.6080|± |0.0309|
71
+ | - leaderboard_bbh_disambiguation_qa | 0|none | 3|acc_norm |↑ |0.6480|± |0.0303|
72
+ | - leaderboard_bbh_formal_fallacies | 0|none | 3|acc_norm |↑ |0.5360|± |0.0316|
73
+ | - leaderboard_bbh_geometric_shapes | 0|none | 3|acc_norm |↑ |0.5240|± |0.0316|
74
+ | - leaderboard_bbh_hyperbaton | 0|none | 3|acc_norm |↑ |0.6440|± |0.0303|
75
+ | - leaderboard_bbh_logical_deduction_five_objects | 0|none | 3|acc_norm |↑ |0.4600|± |0.0316|
76
+ | - leaderboard_bbh_logical_deduction_seven_objects | 0|none | 3|acc_norm |↑ |0.4680|± |0.0316|
77
+ | - leaderboard_bbh_logical_deduction_three_objects | 0|none | 3|acc_norm |↑ |0.7000|± |0.0290|
78
+ | - leaderboard_bbh_movie_recommendation | 0|none | 3|acc_norm |↑ |0.8160|± |0.0246|
79
+ | - leaderboard_bbh_navigate | 0|none | 3|acc_norm |↑ |0.6040|± |0.0310|
80
+ | - leaderboard_bbh_object_counting | 0|none | 3|acc_norm |↑ |0.3680|± |0.0306|
81
+ | - leaderboard_bbh_penguins_in_a_table | 0|none | 3|acc_norm |↑ |0.5548|± |0.0413|
82
+ | - leaderboard_bbh_reasoning_about_colored_objects | 0|none | 3|acc_norm |↑ |0.6320|± |0.0306|
83
+ | - leaderboard_bbh_ruin_names | 0|none | 3|acc_norm |↑ |0.7440|± |0.0277|
84
+ | - leaderboard_bbh_salient_translation_error_detection | 0|none | 3|acc_norm |↑ |0.5280|± |0.0316|
85
+ | - leaderboard_bbh_snarks | 0|none | 3|acc_norm |↑ |0.6292|± |0.0363|
86
+ | - leaderboard_bbh_sports_understanding | 0|none | 3|acc_norm |↑ |0.8040|± |0.0252|
87
+ | - leaderboard_bbh_temporal_sequences | 0|none | 3|acc_norm |↑ |0.4680|± |0.0316|
88
+ | - leaderboard_bbh_tracking_shuffled_objects_five_objects | 0|none | 3|acc_norm |↑ |0.2160|± |0.0261|
89
+ | - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 0|none | 3|acc_norm |↑ |0.1160|± |0.0203|
90
+ | - leaderboard_bbh_tracking_shuffled_objects_three_objects| 0|none | 3|acc_norm |↑ |0.3000|± |0.0290|
91
+ | - leaderboard_bbh_web_of_lies | 0|none | 3|acc_norm |↑ |0.4880|± |0.0317|
92
+ | - leaderboard_gpqa |N/A |none | 0|acc_norm |↑ |0.3146|± |0.0135|
93
+ | - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.3182|± |0.0332|
94
+ | - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.3187|± |0.0200|
95
+ | - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.3080|± |0.0218|
96
+ | - leaderboard_ifeval | 2|none | 0|inst_level_loose_acc |↑ |0.4388|± |N/A |
97
+ | | |none | 0|inst_level_strict_acc |↑ |0.3741|± |N/A |
98
+ | | |none | 0|prompt_level_loose_acc |↑ |0.3105|± |0.0199|
99
+ | | |none | 0|prompt_level_strict_acc|↑ |0.2477|± |0.0186|
100
+ | - leaderboard_math_algebra_hard | 1|none | 4|exact_match |↑ |0.0749|± |0.0150|
101
+ | - leaderboard_math_counting_and_prob_hard | 1|none | 4|exact_match |↑ |0.0244|± |0.0140|
102
+ | - leaderboard_math_geometry_hard | 1|none | 4|exact_match |↑ |0.0227|± |0.0130|
103
+ | - leaderboard_math_hard |N/A |none | 4|exact_match |↑ |0.0536|± |0.0061|
104
+ | - leaderboard_math_intermediate_algebra_hard | 1|none | 4|exact_match |↑ |0.0250|± |0.0093|
105
+ | - leaderboard_math_num_theory_hard | 1|none | 4|exact_match |↑ |0.0390|± |0.0156|
106
+ | - leaderboard_math_prealgebra_hard | 1|none | 4|exact_match |↑ |0.1295|± |0.0242|
107
+ | - leaderboard_math_precalculus_hard | 1|none | 4|exact_match |↑ |0.0296|± |0.0146|
108
+ | - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.3437|± |0.0043|
109
+ | - leaderboard_musr |N/A |none | 0|acc_norm |↑ |0.4511|± |0.0178|
110
+ | - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5880|± |0.0312|
111
+ | - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.3438|± |0.0297|
112
+ | - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.4240|± |0.0313|
113
+
114
+ | Groups |Version|Filter|n-shot| Metric | |Value | |Stderr|
115
+ |------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
116
+ |leaderboard |N/A |none | 0|acc |↑ |0.3437|± |0.0043|
117
+ | | |none | 0|acc_norm |↑ |0.5076|± |0.0053|
118
+ | | |none | 0|exact_match |↑ |0.0536|± |0.0061|
119
+ | | |none | 0|inst_level_loose_acc |↑ |0.4388|± |N/A |
120
+ | | |none | 0|inst_level_strict_acc |↑ |0.3741|± |N/A |
121
+ | | |none | 0|prompt_level_loose_acc |↑ |0.3105|± |0.0199|
122
+ | | |none | 0|prompt_level_strict_acc|↑ |0.2477|± |0.0186|
123
+ | - leaderboard_bbh |N/A |none | 3|acc_norm |↑ |0.5549|± |0.0061|
124
+ | - leaderboard_gpqa |N/A |none | 0|acc_norm |↑ |0.3146|± |0.0135|
125
+ | - leaderboard_math_hard|N/A |none | 4|exact_match |↑ |0.0536|± |0.0061|
126
+ | - leaderboard_musr |N/A |none | 0|acc_norm |↑ |0.4511|± |0.0178|
127
+ ```
128
+
129
+ </details><br>
130
+
131
+ ## Training
132
+
133
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
134
+ should probably proofread and complete it, then remove this comment. -->
135
+
136
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
137
+ <details><summary>See axolotl config</summary>
138
+
139
+ axolotl version: `0.4.1`
140
+ ```yaml
141
+ base_model: /workspace/models/Mistral-Nemo-Base-2407
142
+ model_type: AutoModelForCausalLM
143
+ tokenizer_type: AutoTokenizer
144
+
145
+ load_in_8bit: false
146
+ # load_in_4bit: true
147
+ strict: false
148
+
149
+ datasets:
150
+ - path: /workspace/datasets/dolphin-2.9.3/dolphin201-sharegpt2.jsonl
151
+ type: sharegpt
152
+ conversation: chatml
153
+ - path: /workspace/datasets/dolphin-2.9.3/SystemChat_filtered_sharegpt.jsonl
154
+ type: sharegpt
155
+ conversation: chatml
156
+ - path: /workspace/datasets/dolphin-2.9.3/SystemChat_multilingual_sharegpt.jsonl
157
+ type: sharegpt
158
+ conversation: chatml
159
+ - path: /workspace/datasets/dolphin-2.9.3/dolphin-coder-translate-sharegpt2.jsonl
160
+ type: sharegpt
161
+ conversation: chatml
162
+ - path: /workspace/datasets/dolphin-2.9.3/dolphin-coder-codegen-sharegpt2.jsonl
163
+ type: sharegpt
164
+ conversation: chatml
165
+ - path: /workspace/datasets/dolphin-2.9.3/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
166
+ type: sharegpt
167
+ conversation: chatml
168
+ - path: /workspace/datasets/dolphin-2.9.3/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
169
+ type: sharegpt
170
+ conversation: chatml
171
+ - path: /workspace/datasets/dolphin-2.9.3/not_samantha_norefusals.jsonl
172
+ type: sharegpt
173
+ conversation: chatml
174
+ - path: /workspace/datasets/dolphin-2.9.3/Orca-Math-resort-unfiltered.jsonl
175
+ type: sharegpt
176
+ conversation: chatml
177
+ - path: /workspace/datasets/dolphin-2.9.3/agent_instruct_react_unfiltered.jsonl
178
+ type: sharegpt
179
+ conversation: chatml
180
+ - path: /workspace/datasets/dolphin-2.9.3/toolbench_instruct_j1s1_3k_unfiltered.jsonl
181
+ type: sharegpt
182
+ conversation: chatml
183
+ - path: /workspace/datasets/dolphin-2.9.3/toolbench_negative_unfiltered.jsonl
184
+ type: sharegpt
185
+ conversation: chatml
186
+ - path: /workspace/datasets/dolphin-2.9.3/toolbench_react_10p_unfiltered.jsonl
187
+ type: sharegpt
188
+ conversation: chatml
189
+ - path: /workspace/datasets/dolphin-2.9.3/toolbench_tflan_cot_30p_unfiltered.jsonl
190
+ type: sharegpt
191
+ conversation: chatml
192
+ - path: /workspace/datasets/dolphin-2.9.3/openhermes200k_unfiltered.jsonl
193
+ type: sharegpt
194
+ conversation: chatml
195
+
196
+ chat_template: chatml
197
+ # adapter: qlora
198
+ # lora_r: 128
199
+ # lora_alpha: 16
200
+ # lora_modules_to_save: [embed_tokens, lm_head]
201
+ # lora_dropout: 0.05
202
+ # lora_target_linear: true
203
+
204
+
205
+ unfrozen_parameters:
206
+ - ^lm_head.weight$
207
+ - ^model.embed_tokens.weight$
208
+ - input_layernorm
209
+ - model.norm
210
+ - post_attention_layernorm
211
+ - self_attn.rotary_emb
212
+ # mlp.down_proj layers
213
+ - model.layers.0.mlp.down_proj
214
+ - model.layers.1.mlp.down_proj
215
+ - model.layers.4.mlp.down_proj
216
+ - model.layers.37.mlp.down_proj
217
+ - model.layers.24.mlp.down_proj
218
+ - model.layers.2.mlp.down_proj
219
+ - model.layers.38.mlp.down_proj
220
+ - model.layers.35.mlp.down_proj
221
+ - model.layers.25.mlp.down_proj
222
+ - model.layers.6.mlp.down_proj
223
+ - model.layers.22.mlp.down_proj
224
+ - model.layers.23.mlp.down_proj
225
+ - model.layers.3.mlp.down_proj
226
+ - model.layers.21.mlp.down_proj
227
+ - model.layers.5.mlp.down_proj
228
+ - model.layers.28.mlp.down_proj
229
+ - model.layers.20.mlp.down_proj
230
+ - model.layers.26.mlp.down_proj
231
+ - model.layers.19.mlp.down_proj
232
+ - model.layers.34.mlp.down_proj
233
+ # mlp.gate_proj layers
234
+ - model.layers.2.mlp.gate_proj
235
+ - model.layers.1.mlp.gate_proj
236
+ - model.layers.3.mlp.gate_proj
237
+ - model.layers.5.mlp.gate_proj
238
+ - model.layers.4.mlp.gate_proj
239
+ - model.layers.35.mlp.gate_proj
240
+ - model.layers.36.mlp.gate_proj
241
+ - model.layers.37.mlp.gate_proj
242
+ - model.layers.38.mlp.gate_proj
243
+ - model.layers.34.mlp.gate_proj
244
+ - model.layers.33.mlp.gate_proj
245
+ - model.layers.8.mlp.gate_proj
246
+ - model.layers.32.mlp.gate_proj
247
+ - model.layers.6.mlp.gate_proj
248
+ - model.layers.28.mlp.gate_proj
249
+ - model.layers.26.mlp.gate_proj
250
+ - model.layers.30.mlp.gate_proj
251
+ - model.layers.23.mlp.gate_proj
252
+ - model.layers.29.mlp.gate_proj
253
+ - model.layers.27.mlp.gate_proj
254
+ # mlp.up_proj layers
255
+ - model.layers.3.mlp.up_proj
256
+ - model.layers.4.mlp.up_proj
257
+ - model.layers.6.mlp.up_proj
258
+ - model.layers.2.mlp.up_proj
259
+ - model.layers.5.mlp.up_proj
260
+ - model.layers.8.mlp.up_proj
261
+ - model.layers.10.mlp.up_proj
262
+ - model.layers.9.mlp.up_proj
263
+ - model.layers.7.mlp.up_proj
264
+ - model.layers.0.mlp.up_proj
265
+ - model.layers.17.mlp.up_proj
266
+ - model.layers.15.mlp.up_proj
267
+ - model.layers.22.mlp.up_proj
268
+ - model.layers.18.mlp.up_proj
269
+ - model.layers.16.mlp.up_proj
270
+ - model.layers.11.mlp.up_proj
271
+ - model.layers.21.mlp.up_proj
272
+ - model.layers.23.mlp.up_proj
273
+ - model.layers.20.mlp.up_proj
274
+ - model.layers.27.mlp.up_proj
275
+ # self_attn.k_proj layers
276
+ - model.layers.30.self_attn.k_proj
277
+ - model.layers.27.self_attn.k_proj
278
+ - model.layers.25.self_attn.k_proj
279
+ - model.layers.33.self_attn.k_proj
280
+ - model.layers.26.self_attn.k_proj
281
+ - model.layers.31.self_attn.k_proj
282
+ - model.layers.35.self_attn.k_proj
283
+ - model.layers.39.self_attn.k_proj
284
+ - model.layers.22.self_attn.k_proj
285
+ - model.layers.24.self_attn.k_proj
286
+ - model.layers.21.self_attn.k_proj
287
+ - model.layers.28.self_attn.k_proj
288
+ - model.layers.23.self_attn.k_proj
289
+ - model.layers.36.self_attn.k_proj
290
+ - model.layers.20.self_attn.k_proj
291
+ - model.layers.37.self_attn.k_proj
292
+ - model.layers.29.self_attn.k_proj
293
+ - model.layers.32.self_attn.k_proj
294
+ - model.layers.16.self_attn.k_proj
295
+ - model.layers.18.self_attn.k_proj
296
+ # self_attn.o_proj layers
297
+ - model.layers.7.self_attn.o_proj
298
+ - model.layers.6.self_attn.o_proj
299
+ - model.layers.9.self_attn.o_proj
300
+ - model.layers.5.self_attn.o_proj
301
+ - model.layers.27.self_attn.o_proj
302
+ - model.layers.26.self_attn.o_proj
303
+ - model.layers.4.self_attn.o_proj
304
+ - model.layers.31.self_attn.o_proj
305
+ - model.layers.8.self_attn.o_proj
306
+ - model.layers.16.self_attn.o_proj
307
+ - model.layers.3.self_attn.o_proj
308
+ - model.layers.10.self_attn.o_proj
309
+ - model.layers.18.self_attn.o_proj
310
+ - model.layers.33.self_attn.o_proj
311
+ - model.layers.17.self_attn.o_proj
312
+ - model.layers.32.self_attn.o_proj
313
+ - model.layers.30.self_attn.o_proj
314
+ - model.layers.2.self_attn.o_proj
315
+ - model.layers.15.self_attn.o_proj
316
+ - model.layers.11.self_attn.o_proj
317
+ # self_attn.q_proj layers
318
+ - model.layers.14.self_attn.q_proj
319
+ - model.layers.11.self_attn.q_proj
320
+ - model.layers.15.self_attn.q_proj
321
+ - model.layers.9.self_attn.q_proj
322
+ - model.layers.8.self_attn.q_proj
323
+ - model.layers.18.self_attn.q_proj
324
+ - model.layers.12.self_attn.q_proj
325
+ - model.layers.13.self_attn.q_proj
326
+ - model.layers.19.self_attn.q_proj
327
+ - model.layers.16.self_attn.q_proj
328
+ - model.layers.10.self_attn.q_proj
329
+ - model.layers.17.self_attn.q_proj
330
+ - model.layers.7.self_attn.q_proj
331
+ - model.layers.5.self_attn.q_proj
332
+ - model.layers.20.self_attn.q_proj
333
+ - model.layers.3.self_attn.q_proj
334
+ - model.layers.26.self_attn.q_proj
335
+ - model.layers.27.self_attn.q_proj
336
+ - model.layers.28.self_attn.q_proj
337
+ - model.layers.33.self_attn.q_proj
338
+ # self_attn.v_proj layers
339
+ - model.layers.27.self_attn.v_proj
340
+ - model.layers.20.self_attn.v_proj
341
+ - model.layers.24.self_attn.v_proj
342
+ - model.layers.25.self_attn.v_proj
343
+ - model.layers.30.self_attn.v_proj
344
+ - model.layers.2.self_attn.v_proj
345
+ - model.layers.23.self_attn.v_proj
346
+ - model.layers.22.self_attn.v_proj
347
+ - model.layers.26.self_attn.v_proj
348
+ - model.layers.33.self_attn.v_proj
349
+ - model.layers.37.self_attn.v_proj
350
+ - model.layers.7.self_attn.v_proj
351
+ - model.layers.4.self_attn.v_proj
352
+ - model.layers.18.self_attn.v_proj
353
+ - model.layers.31.self_attn.v_proj
354
+ - model.layers.17.self_attn.v_proj
355
+ - model.layers.35.self_attn.v_proj
356
+ - model.layers.32.self_attn.v_proj
357
+ - model.layers.21.self_attn.v_proj
358
+ - model.layers.3.self_attn.v_proj
359
+
360
+
361
+
362
+ dataset_prepared_path: /workspace/axolotl/dolph-2.9.3-nemo-prepared
363
+ val_set_size: 0.01
364
+ output_dir: /workspace/axolotl/dolphin-2.9.3-mistral-nemo
365
+
366
+ sequence_len: 8192
367
+ sample_packing: true
368
+ pad_to_sequence_len: true
369
+
370
+ wandb_project: dolphin-2.9.3-Mistral-nemo
371
+ wandb_watch:
372
+ wandb_run_id:
373
+ wandb_log_model:
374
+
375
+ gradient_accumulation_steps: 16
376
+ micro_batch_size: 1
377
+ num_epochs: 3
378
+ optimizer: adamw_torch
379
+ lr_scheduler: cosine
380
+ learning_rate: 5e-6
381
+ train_on_inputs: false
382
+ group_by_length: false
383
+ bf16: auto
384
+ fp16:
385
+ tf32:
386
+
387
+ gradient_checkpointing: true
388
+ gradient_checkpointing_kwargs:
389
+ use_reentrant: false
390
+ early_stopping_patience:
391
+ resume_from_checkpoint:
392
+ logging_steps: 1
393
+ xformers_attention:
394
+ flash_attention: true
395
+
396
+ warmup_steps: 100
397
+ # evals_per_epoch: 4
398
+ eval_table_size:
399
+ saves_per_epoch: 1
400
+ save_total_limit: 2
401
+ save_steps:
402
+ debug:
403
+ deepspeed: deepspeed_configs/zero3_bf16.json
404
+ weight_decay: 0.1
405
+ special_tokens:
406
+ eos_token: "<|im_end|>"
407
+ pad_token: "<pad>"
408
+ bos_token: "<s>"
409
+ unk_token: "<unk>"
410
+ tokens:
411
+ - "<|im_start|>"
412
+
413
+
414
+ # fsdp:
415
+ # - full_shard
416
+ # - auto_wrap
417
+ # fsdp_config:
418
+ # fsdp_limit_all_gathers: true
419
+ # fsdp_sync_module_states: true
420
+ # fsdp_offload_params: true
421
+ # fsdp_use_orig_params: false
422
+ # fsdp_cpu_ram_efficient_loading: true
423
+ # fsdp_transformer_layer_cls_to_wrap: MixtralSparseMoeBlock
424
+ # fsdp_state_dict_type: FULL_STATE_DICT
425
+ # fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
426
+ # fsdp_sharding_strategy: FULL_SHARD
427
+ # fsdp_forward_prefetch: false
428
+ # fsdp_backward_prefetch: BACKWARD_PRE
429
+ ```
430
+
431
+ </details><br>
432
+
433
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ehartford/dolphin-2.9.3-Mistral-nemo/runs/c23odyoj)
434
+ # workspace/axolotl/dolphin-2.9.3-mistral-nemo
435
+
436
+ This model was trained from scratch on the None dataset.
437
+ It achieves the following results on the evaluation set:
438
+ - Loss: 0.5605
439
+
440
+ ## Model description
441
+
442
+ More information needed
443
+
444
+ ## Intended uses & limitations
445
+
446
+ More information needed
447
+
448
+ ## Training and evaluation data
449
+
450
+ More information needed
451
+
452
+ ## Training procedure
453
+
454
+ ### Training hyperparameters
455
+
456
+ The following hyperparameters were used during training:
457
+ - learning_rate: 5e-06
458
+ - train_batch_size: 1
459
+ - eval_batch_size: 1
460
+ - seed: 42
461
+ - distributed_type: multi-GPU
462
+ - num_devices: 8
463
+ - gradient_accumulation_steps: 16
464
+ - total_train_batch_size: 128
465
+ - total_eval_batch_size: 8
466
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
467
+ - lr_scheduler_type: cosine
468
+ - lr_scheduler_warmup_steps: 100
469
+ - num_epochs: 3
470
+
471
+ ### Training results
472
+
473
+ | Training Loss | Epoch | Step | Validation Loss |
474
+ |:-------------:|:------:|:----:|:---------------:|
475
+ | 0.5691 | 1.0162 | 983 | 0.5734 |
476
+ | 0.5335 | 2.0174 | 1968 | 0.5609 |
477
+ | 0.5297 | 2.9639 | 2901 | 0.5605 |
478
+
479
+
480
+ ### Framework versions
481
+
482
+ - Transformers 4.43.0.dev0
483
+ - Pytorch 2.2.2+cu121
484
+ - Datasets 2.19.1
485
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 131072,
3
+ "<|im_start|>": 131073
4
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 131072,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.43.0.dev0",
25
+ "use_cache": false,
26
+ "vocab_size": 131074,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.2.2",
30
+ "bits": 4.5,
31
+ "head_bits": 8,
32
+ "calibration": {
33
+ "rows": 115,
34
+ "length": 2048,
35
+ "dataset": "(default)"
36
+ }
37
+ }
38
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.43.0.dev0"
7
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24495605760
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
368
+ "model.norm.weight": "model-00005-of-00005.safetensors"
369
+ }
370
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ce31fa14eac00a6e67f2f23f18ce812e0e3961a2bcae4a9928d1843b284de7
3
+ size 8150244828
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff