Crystalcareai commited on
Commit
cb7b401
1 Parent(s): e16211f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/mixtral-1x22b-base
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: 1x22b-out
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
14
+ <details><summary>See axolotl config</summary>
15
+
16
+ axolotl version: `0.4.0`
17
+ ```yaml
18
+ base_model: cognitivecomputations/mixtral-1x22b-base
19
+ model_type: AutoModelForCausalLM
20
+ tokenizer_type: AutoTokenizer
21
+
22
+ # trust_remote_code: true
23
+
24
+ # load_in_8bit: true
25
+ # load_in_4bit: true
26
+ # strict: false
27
+
28
+ datasets:
29
+ - path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
30
+ type: sharegpt
31
+ conversation: chatml
32
+ - path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
33
+ type: sharegpt
34
+ conversation: chatml
35
+ - path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
36
+ type: sharegpt
37
+ conversation: chatml
38
+ - path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
39
+ type: sharegpt
40
+ conversation: chatml
41
+ - path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
42
+ type: sharegpt
43
+ conversation: chatml
44
+ - path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
45
+ type: sharegpt
46
+ conversation: chatml
47
+ - path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
48
+ type: sharegpt
49
+ conversation: chatml
50
+ - path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
51
+ type: sharegpt
52
+ conversation: chatml
53
+ - path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
54
+ type: sharegpt
55
+ conversation: chatml
56
+ - path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
57
+ type: sharegpt
58
+ conversation: chatml
59
+ - path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
60
+ type: sharegpt
61
+ conversation: chatml
62
+ - path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
63
+ type: sharegpt
64
+ conversation: chatml
65
+ - path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
66
+ type: sharegpt
67
+ conversation: chatml
68
+
69
+ chat_template: chatml
70
+ dataset_prepared_path: yi34b-prepared
71
+ val_set_size: 0.01
72
+ output_dir: ./1x22b-out
73
+
74
+ # adapter: qlora
75
+ # lora_r: 16
76
+ # lora_alpha: 16
77
+ # lora_modules_to_save: [embed_tokens, lm_head]
78
+ # lora_dropout: 0.05
79
+ # lora_target_linear: true
80
+
81
+ # unfrozen_parameters:
82
+ # - ^lm_head.weight$
83
+ # - ^model.embed_tokens.weight$
84
+ # # input_layernorm layers
85
+ # - model.layers.0.input_layernorm
86
+ # - model.layers.1.input_layernorm
87
+ # - model.layers.2.input_layernorm
88
+ # - model.layers.3.input_layernorm
89
+ # - model.layers.4.input_layernorm
90
+ # - model.layers.5.input_layernorm
91
+ # - model.layers.6.input_layernorm
92
+ # - model.layers.7.input_layernorm
93
+ # - model.layers.8.input_layernorm
94
+ # - model.layers.9.input_layernorm
95
+ # - model.layers.10.input_layernorm
96
+ # - model.layers.11.input_layernorm
97
+ # - model.layers.12.input_layernorm
98
+ # - model.layers.13.input_layernorm
99
+ # - model.layers.14.input_layernorm
100
+ # - model.layers.15.input_layernorm
101
+ # - model.layers.16.input_layernorm
102
+ # - model.layers.17.input_layernorm
103
+ # - model.layers.18.input_layernorm
104
+ # - model.layers.19.input_layernorm
105
+ # - model.layers.20.input_layernorm
106
+ # - model.layers.21.input_layernorm
107
+ # - model.layers.22.input_layernorm
108
+ # - model.layers.23.input_layernorm
109
+ # # lm_head layers
110
+ # # mlp.down_proj layers
111
+ # - model.layers.17.mlp.down_proj
112
+ # - model.layers.18.mlp.down_proj
113
+ # - model.layers.19.mlp.down_proj
114
+ # - model.layers.20.mlp.down_proj
115
+ # - model.layers.21.mlp.down_proj
116
+ # - model.layers.22.mlp.down_proj
117
+ # - model.layers.23.mlp.down_proj
118
+ # - model.layers.24.mlp.down_proj
119
+ # - model.layers.25.mlp.down_proj
120
+ # - model.layers.26.mlp.down_proj
121
+ # - model.layers.27.mlp.down_proj
122
+ # - model.layers.28.mlp.down_proj
123
+ # - model.layers.29.mlp.down_proj
124
+ # - model.layers.30.mlp.down_proj
125
+ # - model.layers.31.mlp.down_proj
126
+ # - model.layers.32.mlp.down_proj
127
+ # - model.layers.33.mlp.down_proj
128
+ # - model.layers.34.mlp.down_proj
129
+ # - model.layers.35.mlp.down_proj
130
+ # - model.layers.36.mlp.down_proj
131
+ # - model.layers.37.mlp.down_proj
132
+ # - model.layers.38.mlp.down_proj
133
+ # - model.layers.39.mlp.down_proj
134
+ # - model.layers.40.mlp.down_proj
135
+ # # mlp.gate_proj layers
136
+ # - model.layers.51.mlp.gate_proj
137
+ # - model.layers.50.mlp.gate_proj
138
+ # - model.layers.53.mlp.gate_proj
139
+ # - model.layers.52.mlp.gate_proj
140
+ # - model.layers.49.mlp.gate_proj
141
+ # - model.layers.45.mlp.gate_proj
142
+ # - model.layers.46.mlp.gate_proj
143
+ # - model.layers.47.mlp.gate_proj
144
+ # - model.layers.57.mlp.gate_proj
145
+ # - model.layers.48.mlp.gate_proj
146
+ # - model.layers.56.mlp.gate_proj
147
+ # - model.layers.41.mlp.gate_proj
148
+ # - model.layers.54.mlp.gate_proj
149
+ # - model.layers.43.mlp.gate_proj
150
+ # - model.layers.44.mlp.gate_proj
151
+ # - model.layers.60.mlp.gate_proj
152
+ # - model.layers.55.mlp.gate_proj
153
+ # - model.layers.40.mlp.gate_proj
154
+ # - model.layers.42.mlp.gate_proj
155
+ # - model.layers.58.mlp.gate_proj
156
+ # - model.layers.36.mlp.gate_proj
157
+ # - model.layers.37.mlp.gate_proj
158
+ # - model.layers.38.mlp.gate_proj
159
+ # - model.layers.39.mlp.gate_proj
160
+ # # mlp.up_proj layers
161
+ # - model.layers.50.mlp.up_proj
162
+ # - model.layers.51.mlp.up_proj
163
+ # - model.layers.41.mlp.up_proj
164
+ # - model.layers.49.mlp.up_proj
165
+ # - model.layers.43.mlp.up_proj
166
+ # - model.layers.44.mlp.up_proj
167
+ # - model.layers.40.mlp.up_proj
168
+ # - model.layers.45.mlp.up_proj
169
+ # - model.layers.47.mlp.up_proj
170
+ # - model.layers.48.mlp.up_proj
171
+ # - model.layers.46.mlp.up_proj
172
+ # - model.layers.42.mlp.up_proj
173
+ # - model.layers.39.mlp.up_proj
174
+ # - model.layers.36.mlp.up_proj
175
+ # - model.layers.37.mlp.up_proj
176
+ # - model.layers.38.mlp.up_proj
177
+ # - model.layers.56.mlp.up_proj
178
+ # - model.layers.57.mlp.up_proj
179
+ # - model.layers.53.mlp.up_proj
180
+ # - model.layers.31.mlp.up_proj
181
+ # - model.layers.32.mlp.up_proj
182
+ # - model.layers.34.mlp.up_proj
183
+ # - model.layers.35.mlp.up_proj
184
+ # - model.layers.33.mlp.up_proj
185
+ # # model.embed_tokens layers
186
+ # # model.norm layers
187
+ # # post_attention_layernorm layers
188
+ # - model.layers.0.post_attention_layernorm
189
+ # - model.layers.1.post_attention_layernorm
190
+ # - model.layers.2.post_attention_layernorm
191
+ # - model.layers.3.post_attention_layernorm
192
+ # - model.layers.4.post_attention_layernorm
193
+ # - model.layers.5.post_attention_layernorm
194
+ # - model.layers.6.post_attention_layernorm
195
+ # - model.layers.7.post_attention_layernorm
196
+ # - model.layers.8.post_attention_layernorm
197
+ # - model.layers.9.post_attention_layernorm
198
+ # - model.layers.10.post_attention_layernorm
199
+ # - model.layers.11.post_attention_layernorm
200
+ # - model.layers.12.post_attention_layernorm
201
+ # - model.layers.13.post_attention_layernorm
202
+ # - model.layers.14.post_attention_layernorm
203
+ # - model.layers.15.post_attention_layernorm
204
+ # - model.layers.16.post_attention_layernorm
205
+ # - model.layers.17.post_attention_layernorm
206
+ # - model.layers.18.post_attention_layernorm
207
+ # - model.layers.19.post_attention_layernorm
208
+ # - model.layers.20.post_attention_layernorm
209
+ # - model.layers.21.post_attention_layernorm
210
+ # - model.layers.22.post_attention_layernorm
211
+ # - model.layers.23.post_attention_layernorm
212
+ # # self_attn.k_proj layers
213
+ # - model.layers.42.self_attn.k_proj
214
+ # - model.layers.41.self_attn.k_proj
215
+ # - model.layers.39.self_attn.k_proj
216
+ # - model.layers.35.self_attn.k_proj
217
+ # - model.layers.28.self_attn.k_proj
218
+ # - model.layers.79.self_attn.k_proj
219
+ # - model.layers.43.self_attn.k_proj
220
+ # - model.layers.32.self_attn.k_proj
221
+ # - model.layers.73.self_attn.k_proj
222
+ # - model.layers.31.self_attn.k_proj
223
+ # - model.layers.29.self_attn.k_proj
224
+ # - model.layers.76.self_attn.k_proj
225
+ # - model.layers.30.self_attn.k_proj
226
+ # - model.layers.40.self_attn.k_proj
227
+ # - model.layers.33.self_attn.k_proj
228
+ # - model.layers.78.self_attn.k_proj
229
+ # - model.layers.34.self_attn.k_proj
230
+ # - model.layers.37.self_attn.k_proj
231
+ # - model.layers.45.self_attn.k_proj
232
+ # - model.layers.44.self_attn.k_proj
233
+ # - model.layers.71.self_attn.k_proj
234
+ # - model.layers.26.self_attn.k_proj
235
+ # - model.layers.74.self_attn.k_proj
236
+ # - model.layers.27.self_attn.k_proj
237
+ # # self_attn.o_proj layers
238
+ # - model.layers.35.self_attn.o_proj
239
+ # - model.layers.34.self_attn.o_proj
240
+ # - model.layers.37.self_attn.o_proj
241
+ # - model.layers.33.self_attn.o_proj
242
+ # - model.layers.31.self_attn.o_proj
243
+ # - model.layers.27.self_attn.o_proj
244
+ # - model.layers.38.self_attn.o_proj
245
+ # - model.layers.24.self_attn.o_proj
246
+ # - model.layers.39.self_attn.o_proj
247
+ # - model.layers.43.self_attn.o_proj
248
+ # - model.layers.29.self_attn.o_proj
249
+ # - model.layers.0.self_attn.o_proj
250
+ # - model.layers.50.self_attn.o_proj
251
+ # - model.layers.32.self_attn.o_proj
252
+ # - model.layers.45.self_attn.o_proj
253
+ # - model.layers.30.self_attn.o_proj
254
+ # - model.layers.60.self_attn.o_proj
255
+ # - model.layers.23.self_attn.o_proj
256
+ # - model.layers.18.self_attn.o_proj
257
+ # - model.layers.67.self_attn.o_proj
258
+ # - model.layers.57.self_attn.o_proj
259
+ # - model.layers.20.self_attn.o_proj
260
+ # - model.layers.76.self_attn.o_proj
261
+ # - model.layers.28.self_attn.o_proj
262
+ # # self_attn.q_proj layers
263
+ # - model.layers.1.self_attn.q_proj
264
+ # - model.layers.6.self_attn.q_proj
265
+ # - model.layers.0.self_attn.q_proj
266
+ # - model.layers.5.self_attn.q_proj
267
+ # - model.layers.2.self_attn.q_proj
268
+ # - model.layers.7.self_attn.q_proj
269
+ # - model.layers.3.self_attn.q_proj
270
+ # - model.layers.4.self_attn.q_proj
271
+ # - model.layers.8.self_attn.q_proj
272
+ # - model.layers.9.self_attn.q_proj
273
+ # - model.layers.61.self_attn.q_proj
274
+ # - model.layers.10.self_attn.q_proj
275
+ # - model.layers.62.self_attn.q_proj
276
+ # - model.layers.36.self_attn.q_proj
277
+ # - model.layers.15.self_attn.q_proj
278
+ # - model.layers.11.self_attn.q_proj
279
+ # - model.layers.17.self_attn.q_proj
280
+ # - model.layers.60.self_attn.q_proj
281
+ # - model.layers.63.self_attn.q_proj
282
+ # - model.layers.64.self_attn.q_proj
283
+ # - model.layers.29.self_attn.q_proj
284
+ # - model.layers.30.self_attn.q_proj
285
+ # - model.layers.55.self_attn.q_proj
286
+ # - model.layers.34.self_attn.q_proj
287
+ # # self_attn.v_proj layers
288
+ # - model.layers.12.self_attn.v_proj
289
+ # - model.layers.16.self_attn.v_proj
290
+ # - model.layers.18.self_attn.v_proj
291
+ # - model.layers.19.self_attn.v_proj
292
+ # - model.layers.20.self_attn.v_proj
293
+ # - model.layers.21.self_attn.v_proj
294
+ # - model.layers.22.self_attn.v_proj
295
+ # - model.layers.23.self_attn.v_proj
296
+ # - model.layers.24.self_attn.v_proj
297
+ # - model.layers.25.self_attn.v_proj
298
+ # - model.layers.26.self_attn.v_proj
299
+ # - model.layers.27.self_attn.v_proj
300
+ # - model.layers.28.self_attn.v_proj
301
+ # - model.layers.29.self_attn.v_proj
302
+ # - model.layers.30.self_attn.v_proj
303
+ # - model.layers.31.self_attn.v_proj
304
+ # - model.layers.32.self_attn.v_proj
305
+ # - model.layers.33.self_attn.v_proj
306
+ # - model.layers.34.self_attn.v_proj
307
+ # - model.layers.35.self_attn.v_proj
308
+ # - model.layers.36.self_attn.v_proj
309
+ # - model.layers.37.self_attn.v_proj
310
+ # - model.layers.38.self_attn.v_proj
311
+ # - model.layers.39.self_attn.v_proj
312
+
313
+
314
+
315
+ sequence_len: 16384
316
+ sample_packing: true
317
+ pad_to_sequence_len: true
318
+
319
+ # adapter: lora
320
+ # lora_model_dir:
321
+ # lora_r: 32
322
+ # lora_alpha: 16
323
+ # lora_dropout: 0.05
324
+ # lora_target_linear: true
325
+ # lora_fan_in_fan_out:
326
+
327
+ wandb_project: dolphin-mixtral1x22b
328
+ wandb_entity:
329
+ wandb_watch:
330
+ wandb_name:
331
+ wandb_log_model:
332
+
333
+ gradient_accumulation_steps: 8
334
+ micro_batch_size: 1
335
+ num_epochs: 3
336
+ optimizer: adamw_8bit
337
+ lr_scheduler: cosine
338
+ learning_rate: 1e-5
339
+
340
+ train_on_inputs: false
341
+ group_by_length: false
342
+ bf16: auto
343
+ fp16:
344
+ tf32: false
345
+
346
+ gradient_checkpointing: true
347
+ early_stopping_patience:
348
+ resume_from_checkpoint: /workspace/axolotl2/axolotl/1x22b-out/checkpoint-507
349
+ local_rank:
350
+ logging_steps: 1
351
+ xformers_attention:
352
+ flash_attention: true
353
+
354
+ warmup_steps: 10
355
+ evals_per_epoch: 4
356
+ eval_table_size:
357
+ eval_max_new_tokens: 128
358
+ saves_per_epoch: 4
359
+ save_total_limit: 2
360
+ debug:
361
+ deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
362
+ weight_decay: 0.01
363
+ fsdp:
364
+ fsdp_config:
365
+ special_tokens:
366
+ eos_token: "<|im_end|>"
367
+ bos_token: "<s>"
368
+ # pad_token: "<unk>"
369
+ unk_token: "<unk>"
370
+ tokens:
371
+ - "<|im_start|>"
372
+
373
+
374
+
375
+
376
+
377
+ ```
378
+
379
+ </details><br>
380
+
381
+ # 1x22b-out
382
+
383
+ This model is a fine-tuned version of [cognitivecomputations/mixtral-1x22b-base](https://huggingface.co/cognitivecomputations/mixtral-1x22b-base) on the None dataset.
384
+ It achieves the following results on the evaluation set:
385
+ - Loss: 0.4572
386
+
387
+ ## Model description
388
+
389
+ More information needed
390
+
391
+ ## Intended uses & limitations
392
+
393
+ More information needed
394
+
395
+ ## Training and evaluation data
396
+
397
+ More information needed
398
+
399
+ ## Training procedure
400
+
401
+ ### Training hyperparameters
402
+
403
+ The following hyperparameters were used during training:
404
+ - learning_rate: 1e-05
405
+ - train_batch_size: 1
406
+ - eval_batch_size: 1
407
+ - seed: 42
408
+ - distributed_type: multi-GPU
409
+ - num_devices: 8
410
+ - gradient_accumulation_steps: 8
411
+ - total_train_batch_size: 64
412
+ - total_eval_batch_size: 8
413
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
414
+ - lr_scheduler_type: cosine
415
+ - lr_scheduler_warmup_steps: 10
416
+ - num_epochs: 3
417
+
418
+ ### Training results
419
+
420
+ | Training Loss | Epoch | Step | Validation Loss |
421
+ |:-------------:|:------:|:----:|:---------------:|
422
+ | 0.9818 | 0.0015 | 1 | 0.9854 |
423
+ | 0.4783 | 0.2499 | 169 | 0.5042 |
424
+ | 0.464 | 0.4997 | 338 | 0.4755 |
425
+ | 0.4561 | 0.7496 | 507 | 0.4593 |
426
+ | 0.3981 | 0.9994 | 676 | 0.4553 |
427
+ | 0.3725 | 1.2378 | 845 | 0.4525 |
428
+ | 0.3624 | 1.4877 | 1014 | 0.4457 |
429
+ | 0.359 | 1.7376 | 1183 | 0.4393 |
430
+ | 0.375 | 1.9874 | 1352 | 0.4345 |
431
+ | 0.2899 | 2.2260 | 1521 | 0.4488 |
432
+ | 0.2848 | 2.4759 | 1690 | 0.4473 |
433
+ | 0.2935 | 2.7257 | 1859 | 0.4470 |
434
+ | 0.2065 | 2.9756 | 2028 | 0.4572 |
435
+
436
+
437
+ ### Framework versions
438
+
439
+ - Transformers 4.40.2
440
+ - Pytorch 2.3.0+cu121
441
+ - Datasets 2.19.1
442
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/mixtral-1x22b-base",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 65536,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 48,
16
+ "num_experts_per_tok": 1,
17
+ "num_hidden_layers": 56,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 1,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000,
23
+ "router_aux_loss_coef": 0.001,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.40.2",
29
+ "use_cache": false,
30
+ "vocab_size": 32002
31
+ }
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": "4.40.2"
7
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3704f9bccdfc363e4989926d1f8f71a8ef4f0b820c51d1db889fcbd7ec41b2c
3
+ size 4872960888
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029203f4aafd98c578d0fe61a8c206c13e91d1466bbb9c09ab04d6199239d927
3
+ size 4983086928
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3814c459e0bf7d4e9bbc92e2de7a7411331cd0a72c35f9b514992efa1be1ed5
3
+ size 4957908512
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c643f2ea113bad9746f4d90652a4d7eb9f685fdf093d1e768f507124e6b8970
3
+ size 4882398520
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064a7a0be62f8942793c7db2cef411ef57c3c6fad833d050a84507372065c900
3
+ size 4983086968
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b53668553431b352a8b938f0ade6d9782d1c675e88878ca964fc9420b694ae
3
+ size 4957908512
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003043dc14cd60e1c79d303633fe7c01f98f0dafe7c645815c2e93480053e648
3
+ size 4882398520
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607a419e9f2670bc309d07bceef47198098bb8ff04fea4f28f4a16837c4362a0
3
+ size 4983086968
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161133dd22e88ff9148f02ca27cc720b1aa6263a2a8ea17044d2438e38d661a1
3
+ size 4973661192
model.safetensors.index.json ADDED
@@ -0,0 +1,570 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 44476428288
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00009-of-00009.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
18
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
20
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
22
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
24
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
25
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
28
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
29
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
30
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
31
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
34
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
35
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
36
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
38
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
39
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
40
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
41
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
43
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
44
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
45
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
46
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
48
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
49
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
50
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
51
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
53
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
54
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
55
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
56
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
58
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
59
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
60
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
61
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
62
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
63
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
64
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
65
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
66
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
68
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
69
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
70
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
71
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
72
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
73
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
74
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
75
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
76
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
78
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
79
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
80
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
81
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
82
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
83
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
84
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
85
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
86
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
88
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
89
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
90
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
91
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
92
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
93
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
94
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
95
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
96
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
98
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
99
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
100
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
101
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
102
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
103
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
104
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
105
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
106
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
108
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
109
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
110
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
111
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
112
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
113
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
114
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
115
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
116
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
118
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
119
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
120
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
121
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
122
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
123
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
124
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
125
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
126
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
128
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
129
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
130
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
131
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
132
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
133
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
134
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
135
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
136
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
138
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
139
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
140
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
141
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
142
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
143
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
144
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
145
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
146
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
148
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
149
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
150
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
151
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
152
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
153
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
154
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
155
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
156
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
158
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
159
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
160
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
161
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
162
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
163
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
164
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
165
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
166
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
168
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
169
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
170
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
171
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
172
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
173
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
174
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
175
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
176
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
178
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
179
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
180
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
181
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
182
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
183
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
184
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
185
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
186
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
188
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
189
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
190
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
191
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
192
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
193
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
194
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
195
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
196
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
198
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
199
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
200
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
201
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
202
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
203
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
204
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
205
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
206
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
208
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
209
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
210
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
211
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
212
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
213
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
214
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
215
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
216
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
218
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
219
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
220
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
221
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
222
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
223
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
224
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
225
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
226
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
228
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
229
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
230
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
231
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
232
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
233
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
234
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
235
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
236
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
238
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
239
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
240
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
241
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
242
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
243
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
244
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
245
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
246
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
248
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
249
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
250
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
251
+ "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
252
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
253
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
254
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
255
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
256
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
258
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
259
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
260
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
261
+ "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
262
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
263
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
264
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
265
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
266
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
268
+ "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
269
+ "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
270
+ "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
271
+ "model.layers.32.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
272
+ "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
273
+ "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
274
+ "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
275
+ "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
276
+ "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
277
+ "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
278
+ "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
279
+ "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
280
+ "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
281
+ "model.layers.33.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
282
+ "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
283
+ "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
284
+ "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
285
+ "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
286
+ "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
287
+ "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
288
+ "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
289
+ "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
290
+ "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
291
+ "model.layers.34.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
292
+ "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
293
+ "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
294
+ "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
295
+ "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
296
+ "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
297
+ "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
298
+ "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
299
+ "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
300
+ "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
301
+ "model.layers.35.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
302
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
303
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
304
+ "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
305
+ "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
306
+ "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
307
+ "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
308
+ "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
309
+ "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
310
+ "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
311
+ "model.layers.36.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
312
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
313
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
314
+ "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
315
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
316
+ "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
317
+ "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
318
+ "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
319
+ "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
320
+ "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
321
+ "model.layers.37.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
322
+ "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
323
+ "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
324
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
325
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
326
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
327
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
328
+ "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
329
+ "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
330
+ "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
331
+ "model.layers.38.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
332
+ "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors",
333
+ "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
334
+ "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
335
+ "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
336
+ "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
337
+ "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
338
+ "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
339
+ "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
340
+ "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
341
+ "model.layers.39.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
342
+ "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
343
+ "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
344
+ "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
345
+ "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
346
+ "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
347
+ "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
348
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
349
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
350
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
351
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
352
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
353
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
354
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
355
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
356
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
357
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
358
+ "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
359
+ "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
360
+ "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
361
+ "model.layers.40.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
362
+ "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors",
363
+ "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
364
+ "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
365
+ "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
366
+ "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
367
+ "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
368
+ "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
369
+ "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
370
+ "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
371
+ "model.layers.41.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
372
+ "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
373
+ "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
374
+ "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
375
+ "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
376
+ "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
377
+ "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
378
+ "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
379
+ "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
380
+ "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
381
+ "model.layers.42.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
382
+ "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
383
+ "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
384
+ "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
385
+ "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
386
+ "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
387
+ "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
388
+ "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
389
+ "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
390
+ "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
391
+ "model.layers.43.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
392
+ "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
393
+ "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
394
+ "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
395
+ "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
396
+ "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
397
+ "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
398
+ "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
399
+ "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
400
+ "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
401
+ "model.layers.44.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
402
+ "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors",
403
+ "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
404
+ "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
405
+ "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
406
+ "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
407
+ "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
408
+ "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
409
+ "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
410
+ "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
411
+ "model.layers.45.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
412
+ "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
413
+ "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
414
+ "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
415
+ "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
416
+ "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
417
+ "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
418
+ "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
419
+ "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
420
+ "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
421
+ "model.layers.46.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
422
+ "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
423
+ "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
424
+ "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
425
+ "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
426
+ "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
427
+ "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
428
+ "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
429
+ "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
430
+ "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
431
+ "model.layers.47.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
432
+ "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
433
+ "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
434
+ "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
435
+ "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
436
+ "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
437
+ "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
438
+ "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
439
+ "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
440
+ "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
441
+ "model.layers.48.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
442
+ "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
443
+ "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
444
+ "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
445
+ "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
446
+ "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
447
+ "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
448
+ "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
449
+ "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
450
+ "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
451
+ "model.layers.49.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
452
+ "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
453
+ "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
454
+ "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
455
+ "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
456
+ "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
457
+ "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
458
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
459
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
460
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
461
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
462
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
463
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
464
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
465
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
466
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
467
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
468
+ "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
469
+ "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
470
+ "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
471
+ "model.layers.50.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
472
+ "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors",
473
+ "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
474
+ "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
475
+ "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
476
+ "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
477
+ "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
478
+ "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
479
+ "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
480
+ "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
481
+ "model.layers.51.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
482
+ "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
483
+ "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
484
+ "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
485
+ "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
486
+ "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
487
+ "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
488
+ "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
489
+ "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
490
+ "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
491
+ "model.layers.52.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
492
+ "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
493
+ "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
494
+ "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
495
+ "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
496
+ "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
497
+ "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
498
+ "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
499
+ "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
500
+ "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
501
+ "model.layers.53.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
502
+ "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
503
+ "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
504
+ "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
505
+ "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
506
+ "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
507
+ "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
508
+ "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
509
+ "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
510
+ "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
511
+ "model.layers.54.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
512
+ "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
513
+ "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
514
+ "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
515
+ "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
516
+ "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
517
+ "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
518
+ "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
519
+ "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
520
+ "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
521
+ "model.layers.55.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
522
+ "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
523
+ "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
524
+ "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
525
+ "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
526
+ "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
527
+ "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
528
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
529
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
530
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
531
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
532
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
533
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
534
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
535
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
536
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
537
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
538
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
539
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
540
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
541
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
542
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
543
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
544
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
545
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
546
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
547
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
548
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
549
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
550
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
551
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
552
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
553
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
554
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
555
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
556
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
557
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
558
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
559
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
560
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
561
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
562
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
563
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
564
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
565
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
566
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
567
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
568
+ "model.norm.weight": "model-00009-of-00009.safetensors"
569
+ }
570
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ }
45
+ },
46
+ "additional_special_tokens": [],
47
+ "bos_token": "<s>",
48
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "<|im_end|>",
51
+ "legacy": true,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "</s>",
54
+ "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": false
59
+ }