Hugging Face's logo

mao1207
/
demo-0627-book-7500

Safetensors
go1
custom_code
Model card Files
xet
 Community
mao1207 commited on
Commit
452bc7a
·
verified ·
1 Parent(s): 380bf9c

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. added_tokens.json +11 -0
  2. config.json +488 -0
  3. latest +1 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +1091 -0
  7. rng_state_0.pth +3 -0
  8. rng_state_1.pth +3 -0
  9. rng_state_2.pth +3 -0
  10. rng_state_3.pth +3 -0
  11. rng_state_4.pth +3 -0
  12. rng_state_5.pth +3 -0
  13. rng_state_6.pth +3 -0
  14. rng_state_7.pth +3 -0
  15. special_tokens_map.json +47 -0
  16. tokenization_internlm2.py +235 -0
  17. tokenizer.model +3 -0
  18. tokenizer_config.json +179 -0
  19. trainer_state.json +0 -0
  20. training_args.bin +3 -0
  21. zero_to_fp32.py +674 -0
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<quad>": 92547,
10
+ "<ref>": 92549
11
+ }
config.json ADDED
@@ -0,0 +1,488 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/workspace/aether_vla/Go-1-training/AgiBot-World/pretrained/GO-1",
4
+ "action_chunk_size": 30,
5
+ "action_config": {
6
+ "_attn_implementation_autoset": true,
7
+ "_name_or_path": "",
8
+ "action_chunk_size": 30,
9
+ "action_dim": 16,
10
+ "add_cross_attention": false,
11
+ "architectures": [
12
+ "ActionExpertModel"
13
+ ],
14
+ "attn_implementation": "eager",
15
+ "auto_map": {
16
+ "AutoConfig": "configuration_action_expert.ActionExpertConfig",
17
+ "AutoModel": "modeling_action_expert.ActionExpertModel"
18
+ },
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bias": false,
22
+ "bos_token_id": null,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": null,
31
+ "exponential_decay_length_penalty": null,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "head_dim": 64,
36
+ "hidden_act": "silu",
37
+ "hidden_size": 1024,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "input_hidden_size": 2048,
44
+ "intermediate_size": 4096,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 32768,
54
+ "min_length": 0,
55
+ "model_type": "action_expert",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 16,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 8,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 2,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "rms_norm_eps": 1e-05,
75
+ "rope_scaling": {
76
+ "factor": 2.0,
77
+ "type": "dynamic"
78
+ },
79
+ "rope_theta": 1000000,
80
+ "sep_token_id": null,
81
+ "state_dim": 16,
82
+ "state_token_num": 3,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": true,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": "bfloat16",
93
+ "torchscript": false,
94
+ "transformers_version": "4.46.3",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": true,
97
+ "use_cache": true,
98
+ "use_flash_attn": false
99
+ },
100
+ "architectures": [
101
+ "GO1Model"
102
+ ],
103
+ "auto_map": {
104
+ "AutoConfig": "configuration_go1.GO1ModelConfig",
105
+ "AutoModel": "modeling_go1.GO1Model",
106
+ "AutoModelForCausalLM": "modeling_internlm2_go1.py.InternLM2ForCausalLMGO1"
107
+ },
108
+ "downsample_ratio": 0.5,
109
+ "dynamic_image_size": false,
110
+ "force_image_size": 448,
111
+ "img_context_token_id": 92546,
112
+ "latent_action_config": {
113
+ "_attn_implementation_autoset": false,
114
+ "_name_or_path": "",
115
+ "action_dim": 1,
116
+ "action_horizon": 30,
117
+ "add_cross_attention": false,
118
+ "architectures": null,
119
+ "attn_implementation": "eager",
120
+ "bad_words_ids": null,
121
+ "begin_suppress_tokens": null,
122
+ "bias": false,
123
+ "bos_token_id": null,
124
+ "chunk_size_feed_forward": 0,
125
+ "cross_attention_hidden_size": null,
126
+ "decoder_start_token_id": null,
127
+ "diffusion": false,
128
+ "discrete": true,
129
+ "diversity_penalty": 0.0,
130
+ "do_sample": false,
131
+ "early_stopping": false,
132
+ "enable_act_training": true,
133
+ "enable_ntp_training": false,
134
+ "encoder_no_repeat_ngram_size": 0,
135
+ "eos_token_id": null,
136
+ "exponential_decay_length_penalty": null,
137
+ "final_use_diffusion": true,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "head_dim": 64,
142
+ "hidden_act": "silu",
143
+ "hidden_size": 1024,
144
+ "id2label": {
145
+ "0": "LABEL_0",
146
+ "1": "LABEL_1"
147
+ },
148
+ "img_context_token_id": 92546,
149
+ "initializer_range": 0.02,
150
+ "input_hidden_size": 2048,
151
+ "intermediate_size": 2048,
152
+ "is_decoder": false,
153
+ "is_encoder_decoder": false,
154
+ "label2id": {
155
+ "LABEL_0": 0,
156
+ "LABEL_1": 1
157
+ },
158
+ "length_penalty": 1.0,
159
+ "llm_stop_token_ids": 92542,
160
+ "mask_vision_head_prob": 0.0,
161
+ "mask_vision_wrist_prob": 0.0,
162
+ "max_length": 20,
163
+ "max_position_embeddings": 2048,
164
+ "min_length": 0,
165
+ "model_type": "intermidiate_action_expert",
166
+ "no_repeat_ngram_size": 0,
167
+ "ntp_loss_weight": 0.1,
168
+ "num_attention_heads": 16,
169
+ "num_beam_groups": 1,
170
+ "num_beams": 1,
171
+ "num_hidden_layers": 24,
172
+ "num_key_value_heads": 8,
173
+ "num_return_sequences": 1,
174
+ "output_attentions": false,
175
+ "output_hidden_states": false,
176
+ "output_scores": false,
177
+ "pad_token_id": null,
178
+ "prefix": null,
179
+ "problem_type": null,
180
+ "pruned_heads": {},
181
+ "remove_invalid_values": false,
182
+ "repetition_penalty": 1.0,
183
+ "return_dict": true,
184
+ "return_dict_in_generate": false,
185
+ "rms_norm_eps": 1e-06,
186
+ "rope_scaling": null,
187
+ "rope_theta": 10000,
188
+ "sep_token_id": null,
189
+ "state_token_num": 0,
190
+ "suppress_tokens": null,
191
+ "task_specific_params": null,
192
+ "temperature": 1.0,
193
+ "tf_legacy_loss": false,
194
+ "tie_encoder_decoder": false,
195
+ "tie_word_embeddings": true,
196
+ "tokenizer_class": null,
197
+ "top_k": 50,
198
+ "top_p": 1.0,
199
+ "torch_dtype": null,
200
+ "torchscript": false,
201
+ "transformers_version": "4.46.3",
202
+ "typical_p": 1.0,
203
+ "use_bfloat16": false,
204
+ "use_cache": true,
205
+ "vocab_size": 32
206
+ },
207
+ "latent_planner_config": {
208
+ "_attn_implementation_autoset": false,
209
+ "_name_or_path": "",
210
+ "action_dim": 1,
211
+ "add_cross_attention": false,
212
+ "architectures": null,
213
+ "attn_implementation": "eager",
214
+ "bad_words_ids": null,
215
+ "begin_suppress_tokens": null,
216
+ "bias": false,
217
+ "bos_token_id": null,
218
+ "chunk_size_feed_forward": 0,
219
+ "cross_attention_hidden_size": null,
220
+ "decoder_start_token_id": null,
221
+ "diversity_penalty": 0.0,
222
+ "do_sample": false,
223
+ "early_stopping": false,
224
+ "encoder_no_repeat_ngram_size": 0,
225
+ "eos_token_id": null,
226
+ "exponential_decay_length_penalty": null,
227
+ "finetuning_task": null,
228
+ "forced_bos_token_id": null,
229
+ "forced_eos_token_id": null,
230
+ "head_dim": 64,
231
+ "hidden_act": "silu",
232
+ "hidden_size": 1024,
233
+ "id2label": {
234
+ "0": "LABEL_0",
235
+ "1": "LABEL_1"
236
+ },
237
+ "initializer_range": 0.02,
238
+ "input_hidden_size": 2048,
239
+ "intermediate_size": 2048,
240
+ "is_decoder": false,
241
+ "is_encoder_decoder": false,
242
+ "label2id": {
243
+ "LABEL_0": 0,
244
+ "LABEL_1": 1
245
+ },
246
+ "length_penalty": 1.0,
247
+ "max_length": 20,
248
+ "max_position_embeddings": 2048,
249
+ "min_length": 0,
250
+ "model_type": "intermidiate_action_expert",
251
+ "no_repeat_ngram_size": 0,
252
+ "num_attention_heads": 16,
253
+ "num_beam_groups": 1,
254
+ "num_beams": 1,
255
+ "num_hidden_layers": 24,
256
+ "num_key_value_heads": 8,
257
+ "num_return_sequences": 1,
258
+ "output_attentions": false,
259
+ "output_hidden_states": false,
260
+ "output_scores": false,
261
+ "pad_token_id": null,
262
+ "prefix": null,
263
+ "problem_type": null,
264
+ "pruned_heads": {},
265
+ "remove_invalid_values": false,
266
+ "repetition_penalty": 1.0,
267
+ "return_dict": true,
268
+ "return_dict_in_generate": false,
269
+ "rms_norm_eps": 1e-06,
270
+ "rope_scaling": null,
271
+ "rope_theta": 10000,
272
+ "sep_token_id": null,
273
+ "state_token_num": 0,
274
+ "suppress_tokens": null,
275
+ "task_specific_params": null,
276
+ "temperature": 1.0,
277
+ "tf_legacy_loss": false,
278
+ "tie_encoder_decoder": false,
279
+ "tie_word_embeddings": true,
280
+ "tokenizer_class": null,
281
+ "top_k": 50,
282
+ "top_p": 1.0,
283
+ "torch_dtype": null,
284
+ "torchscript": false,
285
+ "transformers_version": "4.46.3",
286
+ "typical_p": 1.0,
287
+ "use_bfloat16": false,
288
+ "use_cache": true,
289
+ "vocab_size": 32
290
+ },
291
+ "latent_planning": true,
292
+ "llm_config": {
293
+ "_attn_implementation_autoset": true,
294
+ "_name_or_path": "",
295
+ "add_cross_attention": false,
296
+ "architectures": [
297
+ "InternLM2ForCausalLMGO1"
298
+ ],
299
+ "attn_implementation": "flash_attention_2",
300
+ "auto_map": {
301
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
302
+ "AutoModel": "modeling_internlm2_go1.InternLM2ForCausalLMGO1",
303
+ "AutoModelForCausalLM": "modeling_internlm2_go1.py.InternLM2ForCausalLMGO1"
304
+ },
305
+ "bad_words_ids": null,
306
+ "begin_suppress_tokens": null,
307
+ "bias": false,
308
+ "bos_token_id": 1,
309
+ "chunk_size_feed_forward": 0,
310
+ "cross_attention_hidden_size": null,
311
+ "decoder_start_token_id": null,
312
+ "diversity_penalty": 0.0,
313
+ "do_sample": false,
314
+ "early_stopping": false,
315
+ "encoder_no_repeat_ngram_size": 0,
316
+ "eos_token_id": 2,
317
+ "exponential_decay_length_penalty": null,
318
+ "finetuning_task": null,
319
+ "forced_bos_token_id": null,
320
+ "forced_eos_token_id": null,
321
+ "hidden_act": "silu",
322
+ "hidden_size": 2048,
323
+ "id2label": {
324
+ "0": "LABEL_0",
325
+ "1": "LABEL_1"
326
+ },
327
+ "initializer_range": 0.02,
328
+ "intermediate_size": 8192,
329
+ "is_decoder": false,
330
+ "is_encoder_decoder": false,
331
+ "label2id": {
332
+ "LABEL_0": 0,
333
+ "LABEL_1": 1
334
+ },
335
+ "length_penalty": 1.0,
336
+ "max_length": 20,
337
+ "max_position_embeddings": 32768,
338
+ "min_length": 0,
339
+ "model_type": "internlm2",
340
+ "no_repeat_ngram_size": 0,
341
+ "num_attention_heads": 16,
342
+ "num_beam_groups": 1,
343
+ "num_beams": 1,
344
+ "num_hidden_layers": 24,
345
+ "num_key_value_heads": 8,
346
+ "num_return_sequences": 1,
347
+ "output_attentions": false,
348
+ "output_hidden_states": false,
349
+ "output_scores": false,
350
+ "pad_token_id": 2,
351
+ "prefix": null,
352
+ "problem_type": null,
353
+ "pruned_heads": {},
354
+ "remove_invalid_values": false,
355
+ "repetition_penalty": 1.0,
356
+ "return_dict": true,
357
+ "return_dict_in_generate": false,
358
+ "rms_norm_eps": 1e-05,
359
+ "rope_scaling": {
360
+ "factor": 2.0,
361
+ "type": "dynamic"
362
+ },
363
+ "rope_theta": 1000000,
364
+ "sep_token_id": null,
365
+ "suppress_tokens": null,
366
+ "task_specific_params": null,
367
+ "temperature": 1.0,
368
+ "tf_legacy_loss": false,
369
+ "tie_encoder_decoder": false,
370
+ "tie_word_embeddings": false,
371
+ "tokenizer_class": null,
372
+ "top_k": 50,
373
+ "top_p": 1.0,
374
+ "torch_dtype": "bfloat16",
375
+ "torchscript": false,
376
+ "transformers_version": "4.46.3",
377
+ "typical_p": 1.0,
378
+ "use_bfloat16": true,
379
+ "use_cache": true,
380
+ "vocab_size": 92553
381
+ },
382
+ "max_dynamic_patch": 6,
383
+ "min_dynamic_patch": 1,
384
+ "model_type": "go1",
385
+ "noise_scheduler_config": {
386
+ "beta_schedule": "squaredcos_cap_v2",
387
+ "clip_sample": false,
388
+ "num_inference_timesteps": 5,
389
+ "num_train_timesteps": 1000,
390
+ "prediction_type": "sample"
391
+ },
392
+ "norm": true,
393
+ "pad2square": false,
394
+ "pad_token_id": 2,
395
+ "ps_version": "v2",
396
+ "select_layer": -1,
397
+ "template": "internlm2-chat",
398
+ "torch_dtype": "bfloat16",
399
+ "transformers_version": null,
400
+ "use_backbone_lora": 0,
401
+ "use_llm_lora": 0,
402
+ "use_thumbnail": false,
403
+ "vision_config": {
404
+ "_attn_implementation_autoset": true,
405
+ "_name_or_path": "",
406
+ "add_cross_attention": false,
407
+ "architectures": [
408
+ "InternVisionModel"
409
+ ],
410
+ "attention_dropout": 0.0,
411
+ "bad_words_ids": null,
412
+ "begin_suppress_tokens": null,
413
+ "bos_token_id": null,
414
+ "chunk_size_feed_forward": 0,
415
+ "cross_attention_hidden_size": null,
416
+ "decoder_start_token_id": null,
417
+ "diversity_penalty": 0.0,
418
+ "do_sample": false,
419
+ "drop_path_rate": 0.1,
420
+ "dropout": 0.0,
421
+ "early_stopping": false,
422
+ "encoder_no_repeat_ngram_size": 0,
423
+ "eos_token_id": null,
424
+ "exponential_decay_length_penalty": null,
425
+ "finetuning_task": null,
426
+ "forced_bos_token_id": null,
427
+ "forced_eos_token_id": null,
428
+ "hidden_act": "gelu",
429
+ "hidden_size": 1024,
430
+ "id2label": {
431
+ "0": "LABEL_0",
432
+ "1": "LABEL_1"
433
+ },
434
+ "image_size": 448,
435
+ "initializer_factor": 1.0,
436
+ "initializer_range": 0.02,
437
+ "intermediate_size": 4096,
438
+ "is_decoder": false,
439
+ "is_encoder_decoder": false,
440
+ "label2id": {
441
+ "LABEL_0": 0,
442
+ "LABEL_1": 1
443
+ },
444
+ "layer_norm_eps": 1e-06,
445
+ "length_penalty": 1.0,
446
+ "max_length": 20,
447
+ "min_length": 0,
448
+ "model_type": "intern_vit_6b",
449
+ "no_repeat_ngram_size": 0,
450
+ "norm_type": "layer_norm",
451
+ "num_attention_heads": 16,
452
+ "num_beam_groups": 1,
453
+ "num_beams": 1,
454
+ "num_channels": 3,
455
+ "num_hidden_layers": 24,
456
+ "num_return_sequences": 1,
457
+ "output_attentions": false,
458
+ "output_hidden_states": false,
459
+ "output_scores": false,
460
+ "pad_token_id": null,
461
+ "patch_size": 14,
462
+ "prefix": null,
463
+ "problem_type": null,
464
+ "pruned_heads": {},
465
+ "qk_normalization": false,
466
+ "qkv_bias": true,
467
+ "remove_invalid_values": false,
468
+ "repetition_penalty": 1.0,
469
+ "return_dict": true,
470
+ "return_dict_in_generate": false,
471
+ "sep_token_id": null,
472
+ "suppress_tokens": null,
473
+ "task_specific_params": null,
474
+ "temperature": 1.0,
475
+ "tf_legacy_loss": false,
476
+ "tie_encoder_decoder": false,
477
+ "tie_word_embeddings": true,
478
+ "tokenizer_class": null,
479
+ "top_k": 50,
480
+ "top_p": 1.0,
481
+ "torch_dtype": "bfloat16",
482
+ "torchscript": false,
483
+ "transformers_version": "4.46.3",
484
+ "typical_p": 1.0,
485
+ "use_bfloat16": true,
486
+ "use_flash_attn": true
487
+ }
488
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step7500
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a3667bab4db03eb6fe6e4dd0b15091d47b97872c6ac818d8ca7a562bbd2b16
3
+ size 4992571160
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1fcac91a7f188cd19a9d5281cf511536350dcfee6221e7af5b6b4d97e7c15e4
3
+ size 650642770
model.safetensors.index.json ADDED
@@ -0,0 +1,1091 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5643083810
4
+ },
5
+ "weight_map": {
6
+ "action_adaptor.0.bias": "model-00002-of-00002.safetensors",
7
+ "action_adaptor.0.weight": "model-00002-of-00002.safetensors",
8
+ "action_adaptor.2.bias": "model-00002-of-00002.safetensors",
9
+ "action_adaptor.2.weight": "model-00002-of-00002.safetensors",
10
+ "action_adaptor.4.bias": "model-00002-of-00002.safetensors",
11
+ "action_adaptor.4.weight": "model-00002-of-00002.safetensors",
12
+ "action_model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
13
+ "action_model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
14
+ "action_model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
15
+ "action_model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
16
+ "action_model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
17
+ "action_model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
18
+ "action_model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
19
+ "action_model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
20
+ "action_model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
21
+ "action_model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
22
+ "action_model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
23
+ "action_model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
24
+ "action_model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
25
+ "action_model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
26
+ "action_model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
27
+ "action_model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
28
+ "action_model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
29
+ "action_model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
30
+ "action_model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
31
+ "action_model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
32
+ "action_model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
33
+ "action_model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
34
+ "action_model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
35
+ "action_model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
36
+ "action_model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
37
+ "action_model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
38
+ "action_model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
39
+ "action_model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
40
+ "action_model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
41
+ "action_model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
42
+ "action_model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
43
+ "action_model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
44
+ "action_model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
45
+ "action_model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
46
+ "action_model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
47
+ "action_model.layers.13.attention.wo.weight": "model-00001-of-00002.safetensors",
48
+ "action_model.layers.13.attention.wqkv.weight": "model-00001-of-00002.safetensors",
49
+ "action_model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
50
+ "action_model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
51
+ "action_model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
52
+ "action_model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
53
+ "action_model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
54
+ "action_model.layers.14.attention.wo.weight": "model-00001-of-00002.safetensors",
55
+ "action_model.layers.14.attention.wqkv.weight": "model-00001-of-00002.safetensors",
56
+ "action_model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
57
+ "action_model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
58
+ "action_model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
59
+ "action_model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
60
+ "action_model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
61
+ "action_model.layers.15.attention.wo.weight": "model-00001-of-00002.safetensors",
62
+ "action_model.layers.15.attention.wqkv.weight": "model-00001-of-00002.safetensors",
63
+ "action_model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
64
+ "action_model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
65
+ "action_model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
66
+ "action_model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
67
+ "action_model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
68
+ "action_model.layers.16.attention.wo.weight": "model-00001-of-00002.safetensors",
69
+ "action_model.layers.16.attention.wqkv.weight": "model-00001-of-00002.safetensors",
70
+ "action_model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
71
+ "action_model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
72
+ "action_model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
73
+ "action_model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
74
+ "action_model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
75
+ "action_model.layers.17.attention.wo.weight": "model-00001-of-00002.safetensors",
76
+ "action_model.layers.17.attention.wqkv.weight": "model-00001-of-00002.safetensors",
77
+ "action_model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
78
+ "action_model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
79
+ "action_model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
80
+ "action_model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
81
+ "action_model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
82
+ "action_model.layers.18.attention.wo.weight": "model-00001-of-00002.safetensors",
83
+ "action_model.layers.18.attention.wqkv.weight": "model-00001-of-00002.safetensors",
84
+ "action_model.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
85
+ "action_model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
86
+ "action_model.layers.18.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
87
+ "action_model.layers.18.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
88
+ "action_model.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
89
+ "action_model.layers.19.attention.wo.weight": "model-00002-of-00002.safetensors",
90
+ "action_model.layers.19.attention.wqkv.weight": "model-00002-of-00002.safetensors",
91
+ "action_model.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
92
+ "action_model.layers.19.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
93
+ "action_model.layers.19.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
94
+ "action_model.layers.19.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
95
+ "action_model.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
96
+ "action_model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
97
+ "action_model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
98
+ "action_model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
99
+ "action_model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
100
+ "action_model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
101
+ "action_model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
102
+ "action_model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
103
+ "action_model.layers.20.attention.wo.weight": "model-00002-of-00002.safetensors",
104
+ "action_model.layers.20.attention.wqkv.weight": "model-00002-of-00002.safetensors",
105
+ "action_model.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
106
+ "action_model.layers.20.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
107
+ "action_model.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
108
+ "action_model.layers.20.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
109
+ "action_model.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
110
+ "action_model.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
111
+ "action_model.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
112
+ "action_model.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
113
+ "action_model.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
114
+ "action_model.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
115
+ "action_model.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
116
+ "action_model.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
117
+ "action_model.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
118
+ "action_model.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
119
+ "action_model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
120
+ "action_model.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
121
+ "action_model.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
122
+ "action_model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
123
+ "action_model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
124
+ "action_model.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
125
+ "action_model.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
126
+ "action_model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
127
+ "action_model.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
128
+ "action_model.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
129
+ "action_model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
130
+ "action_model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
131
+ "action_model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
132
+ "action_model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
133
+ "action_model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
134
+ "action_model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
135
+ "action_model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
136
+ "action_model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
137
+ "action_model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
138
+ "action_model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
139
+ "action_model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
140
+ "action_model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
141
+ "action_model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
142
+ "action_model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
143
+ "action_model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
144
+ "action_model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
145
+ "action_model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
146
+ "action_model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
147
+ "action_model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
148
+ "action_model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
149
+ "action_model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
150
+ "action_model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
151
+ "action_model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
152
+ "action_model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
153
+ "action_model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
154
+ "action_model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
155
+ "action_model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
156
+ "action_model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
157
+ "action_model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
158
+ "action_model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
159
+ "action_model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
160
+ "action_model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
161
+ "action_model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
162
+ "action_model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
163
+ "action_model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
164
+ "action_model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
165
+ "action_model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
166
+ "action_model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
167
+ "action_model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
168
+ "action_model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
169
+ "action_model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
170
+ "action_model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
171
+ "action_model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
172
+ "action_model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
173
+ "action_model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
174
+ "action_model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
175
+ "action_model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
176
+ "action_model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
177
+ "action_model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
178
+ "action_model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
179
+ "action_model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
180
+ "action_model.norm.weight": "model-00002-of-00002.safetensors",
181
+ "final_layer.ffn_final.fc1.bias": "model-00002-of-00002.safetensors",
182
+ "final_layer.ffn_final.fc1.weight": "model-00002-of-00002.safetensors",
183
+ "final_layer.ffn_final.fc2.bias": "model-00002-of-00002.safetensors",
184
+ "final_layer.ffn_final.fc2.weight": "model-00002-of-00002.safetensors",
185
+ "final_layer.norm_final.weight": "model-00002-of-00002.safetensors",
186
+ "freq_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
187
+ "freq_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
188
+ "freq_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
189
+ "freq_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
190
+ "k_proj_layers.0.bias": "model-00002-of-00002.safetensors",
191
+ "k_proj_layers.0.weight": "model-00002-of-00002.safetensors",
192
+ "k_proj_layers.1.bias": "model-00002-of-00002.safetensors",
193
+ "k_proj_layers.1.weight": "model-00002-of-00002.safetensors",
194
+ "k_proj_layers.10.bias": "model-00002-of-00002.safetensors",
195
+ "k_proj_layers.10.weight": "model-00002-of-00002.safetensors",
196
+ "k_proj_layers.11.bias": "model-00002-of-00002.safetensors",
197
+ "k_proj_layers.11.weight": "model-00002-of-00002.safetensors",
198
+ "k_proj_layers.12.bias": "model-00002-of-00002.safetensors",
199
+ "k_proj_layers.12.weight": "model-00002-of-00002.safetensors",
200
+ "k_proj_layers.13.bias": "model-00002-of-00002.safetensors",
201
+ "k_proj_layers.13.weight": "model-00002-of-00002.safetensors",
202
+ "k_proj_layers.14.bias": "model-00002-of-00002.safetensors",
203
+ "k_proj_layers.14.weight": "model-00002-of-00002.safetensors",
204
+ "k_proj_layers.15.bias": "model-00002-of-00002.safetensors",
205
+ "k_proj_layers.15.weight": "model-00002-of-00002.safetensors",
206
+ "k_proj_layers.16.bias": "model-00002-of-00002.safetensors",
207
+ "k_proj_layers.16.weight": "model-00002-of-00002.safetensors",
208
+ "k_proj_layers.17.bias": "model-00002-of-00002.safetensors",
209
+ "k_proj_layers.17.weight": "model-00002-of-00002.safetensors",
210
+ "k_proj_layers.18.bias": "model-00002-of-00002.safetensors",
211
+ "k_proj_layers.18.weight": "model-00002-of-00002.safetensors",
212
+ "k_proj_layers.19.bias": "model-00002-of-00002.safetensors",
213
+ "k_proj_layers.19.weight": "model-00002-of-00002.safetensors",
214
+ "k_proj_layers.2.bias": "model-00002-of-00002.safetensors",
215
+ "k_proj_layers.2.weight": "model-00002-of-00002.safetensors",
216
+ "k_proj_layers.20.bias": "model-00002-of-00002.safetensors",
217
+ "k_proj_layers.20.weight": "model-00002-of-00002.safetensors",
218
+ "k_proj_layers.21.bias": "model-00002-of-00002.safetensors",
219
+ "k_proj_layers.21.weight": "model-00002-of-00002.safetensors",
220
+ "k_proj_layers.22.bias": "model-00002-of-00002.safetensors",
221
+ "k_proj_layers.22.weight": "model-00002-of-00002.safetensors",
222
+ "k_proj_layers.23.bias": "model-00002-of-00002.safetensors",
223
+ "k_proj_layers.23.weight": "model-00002-of-00002.safetensors",
224
+ "k_proj_layers.3.bias": "model-00002-of-00002.safetensors",
225
+ "k_proj_layers.3.weight": "model-00002-of-00002.safetensors",
226
+ "k_proj_layers.4.bias": "model-00002-of-00002.safetensors",
227
+ "k_proj_layers.4.weight": "model-00002-of-00002.safetensors",
228
+ "k_proj_layers.5.bias": "model-00002-of-00002.safetensors",
229
+ "k_proj_layers.5.weight": "model-00002-of-00002.safetensors",
230
+ "k_proj_layers.6.bias": "model-00002-of-00002.safetensors",
231
+ "k_proj_layers.6.weight": "model-00002-of-00002.safetensors",
232
+ "k_proj_layers.7.bias": "model-00002-of-00002.safetensors",
233
+ "k_proj_layers.7.weight": "model-00002-of-00002.safetensors",
234
+ "k_proj_layers.8.bias": "model-00002-of-00002.safetensors",
235
+ "k_proj_layers.8.weight": "model-00002-of-00002.safetensors",
236
+ "k_proj_layers.9.bias": "model-00002-of-00002.safetensors",
237
+ "k_proj_layers.9.weight": "model-00002-of-00002.safetensors",
238
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
239
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
240
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
241
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
242
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
243
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
244
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
245
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
246
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
247
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
248
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
249
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
250
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
251
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
252
+ "language_model.model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
253
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
254
+ "language_model.model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
255
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
256
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
257
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
258
+ "language_model.model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
259
+ "language_model.model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
260
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
261
+ "language_model.model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
262
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
263
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
264
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
265
+ "language_model.model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
266
+ "language_model.model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
267
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
268
+ "language_model.model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
269
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
270
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
271
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
272
+ "language_model.model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
273
+ "language_model.model.layers.13.attention.wo.weight": "model-00001-of-00002.safetensors",
274
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00001-of-00002.safetensors",
275
+ "language_model.model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
276
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
277
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
278
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
279
+ "language_model.model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
280
+ "language_model.model.layers.14.attention.wo.weight": "model-00001-of-00002.safetensors",
281
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00001-of-00002.safetensors",
282
+ "language_model.model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
283
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
284
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
285
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
286
+ "language_model.model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
287
+ "language_model.model.layers.15.attention.wo.weight": "model-00001-of-00002.safetensors",
288
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00001-of-00002.safetensors",
289
+ "language_model.model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
290
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
291
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
292
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
293
+ "language_model.model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
294
+ "language_model.model.layers.16.attention.wo.weight": "model-00001-of-00002.safetensors",
295
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00001-of-00002.safetensors",
296
+ "language_model.model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
297
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
298
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
299
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
300
+ "language_model.model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
301
+ "language_model.model.layers.17.attention.wo.weight": "model-00001-of-00002.safetensors",
302
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00001-of-00002.safetensors",
303
+ "language_model.model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
304
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
305
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
306
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
307
+ "language_model.model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
308
+ "language_model.model.layers.18.attention.wo.weight": "model-00001-of-00002.safetensors",
309
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00001-of-00002.safetensors",
310
+ "language_model.model.layers.18.attention_norm.weight": "model-00001-of-00002.safetensors",
311
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
312
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
313
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
314
+ "language_model.model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
315
+ "language_model.model.layers.19.attention.wo.weight": "model-00001-of-00002.safetensors",
316
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00001-of-00002.safetensors",
317
+ "language_model.model.layers.19.attention_norm.weight": "model-00001-of-00002.safetensors",
318
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
319
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
320
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
321
+ "language_model.model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
322
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
323
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
324
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
325
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
326
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
327
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
328
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
329
+ "language_model.model.layers.20.attention.wo.weight": "model-00001-of-00002.safetensors",
330
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00001-of-00002.safetensors",
331
+ "language_model.model.layers.20.attention_norm.weight": "model-00001-of-00002.safetensors",
332
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
333
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
334
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
335
+ "language_model.model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
336
+ "language_model.model.layers.21.attention.wo.weight": "model-00001-of-00002.safetensors",
337
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00001-of-00002.safetensors",
338
+ "language_model.model.layers.21.attention_norm.weight": "model-00001-of-00002.safetensors",
339
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
340
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
341
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
342
+ "language_model.model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
343
+ "language_model.model.layers.22.attention.wo.weight": "model-00001-of-00002.safetensors",
344
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00001-of-00002.safetensors",
345
+ "language_model.model.layers.22.attention_norm.weight": "model-00001-of-00002.safetensors",
346
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
347
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
348
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
349
+ "language_model.model.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
350
+ "language_model.model.layers.23.attention.wo.weight": "model-00001-of-00002.safetensors",
351
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00001-of-00002.safetensors",
352
+ "language_model.model.layers.23.attention_norm.weight": "model-00001-of-00002.safetensors",
353
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
354
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
355
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
356
+ "language_model.model.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
357
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
358
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
359
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
360
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
361
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
362
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
363
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
364
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
365
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
366
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
367
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
368
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
369
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
370
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
371
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
372
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
373
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
374
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
375
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
376
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
377
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
378
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
379
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
380
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
381
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
382
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
383
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
384
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
385
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
386
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
387
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
388
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
389
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
390
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
391
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
392
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
393
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
394
+ "language_model.model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
395
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
396
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
397
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
398
+ "language_model.model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
399
+ "language_model.model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
400
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
401
+ "language_model.model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
402
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
403
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
404
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
405
+ "language_model.model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
406
+ "language_model.model.norm.weight": "model-00001-of-00002.safetensors",
407
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00002.safetensors",
408
+ "language_model.output.weight": "model-00001-of-00002.safetensors",
409
+ "latent_planner.latent_action_expert.layers.0.attention.wo.weight": "model-00002-of-00002.safetensors",
410
+ "latent_planner.latent_action_expert.layers.0.attention.wqkv.weight": "model-00002-of-00002.safetensors",
411
+ "latent_planner.latent_action_expert.layers.0.attention_norm.weight": "model-00002-of-00002.safetensors",
412
+ "latent_planner.latent_action_expert.layers.0.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
413
+ "latent_planner.latent_action_expert.layers.0.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
414
+ "latent_planner.latent_action_expert.layers.0.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
415
+ "latent_planner.latent_action_expert.layers.0.ffn_norm.weight": "model-00002-of-00002.safetensors",
416
+ "latent_planner.latent_action_expert.layers.1.attention.wo.weight": "model-00002-of-00002.safetensors",
417
+ "latent_planner.latent_action_expert.layers.1.attention.wqkv.weight": "model-00002-of-00002.safetensors",
418
+ "latent_planner.latent_action_expert.layers.1.attention_norm.weight": "model-00002-of-00002.safetensors",
419
+ "latent_planner.latent_action_expert.layers.1.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
420
+ "latent_planner.latent_action_expert.layers.1.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
421
+ "latent_planner.latent_action_expert.layers.1.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
422
+ "latent_planner.latent_action_expert.layers.1.ffn_norm.weight": "model-00002-of-00002.safetensors",
423
+ "latent_planner.latent_action_expert.layers.10.attention.wo.weight": "model-00002-of-00002.safetensors",
424
+ "latent_planner.latent_action_expert.layers.10.attention.wqkv.weight": "model-00002-of-00002.safetensors",
425
+ "latent_planner.latent_action_expert.layers.10.attention_norm.weight": "model-00002-of-00002.safetensors",
426
+ "latent_planner.latent_action_expert.layers.10.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
427
+ "latent_planner.latent_action_expert.layers.10.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
428
+ "latent_planner.latent_action_expert.layers.10.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
429
+ "latent_planner.latent_action_expert.layers.10.ffn_norm.weight": "model-00002-of-00002.safetensors",
430
+ "latent_planner.latent_action_expert.layers.11.attention.wo.weight": "model-00002-of-00002.safetensors",
431
+ "latent_planner.latent_action_expert.layers.11.attention.wqkv.weight": "model-00002-of-00002.safetensors",
432
+ "latent_planner.latent_action_expert.layers.11.attention_norm.weight": "model-00002-of-00002.safetensors",
433
+ "latent_planner.latent_action_expert.layers.11.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
434
+ "latent_planner.latent_action_expert.layers.11.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
435
+ "latent_planner.latent_action_expert.layers.11.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
436
+ "latent_planner.latent_action_expert.layers.11.ffn_norm.weight": "model-00002-of-00002.safetensors",
437
+ "latent_planner.latent_action_expert.layers.12.attention.wo.weight": "model-00002-of-00002.safetensors",
438
+ "latent_planner.latent_action_expert.layers.12.attention.wqkv.weight": "model-00002-of-00002.safetensors",
439
+ "latent_planner.latent_action_expert.layers.12.attention_norm.weight": "model-00002-of-00002.safetensors",
440
+ "latent_planner.latent_action_expert.layers.12.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
441
+ "latent_planner.latent_action_expert.layers.12.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
442
+ "latent_planner.latent_action_expert.layers.12.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
443
+ "latent_planner.latent_action_expert.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
444
+ "latent_planner.latent_action_expert.layers.13.attention.wo.weight": "model-00002-of-00002.safetensors",
445
+ "latent_planner.latent_action_expert.layers.13.attention.wqkv.weight": "model-00002-of-00002.safetensors",
446
+ "latent_planner.latent_action_expert.layers.13.attention_norm.weight": "model-00002-of-00002.safetensors",
447
+ "latent_planner.latent_action_expert.layers.13.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
448
+ "latent_planner.latent_action_expert.layers.13.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
449
+ "latent_planner.latent_action_expert.layers.13.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
450
+ "latent_planner.latent_action_expert.layers.13.ffn_norm.weight": "model-00002-of-00002.safetensors",
451
+ "latent_planner.latent_action_expert.layers.14.attention.wo.weight": "model-00002-of-00002.safetensors",
452
+ "latent_planner.latent_action_expert.layers.14.attention.wqkv.weight": "model-00002-of-00002.safetensors",
453
+ "latent_planner.latent_action_expert.layers.14.attention_norm.weight": "model-00002-of-00002.safetensors",
454
+ "latent_planner.latent_action_expert.layers.14.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
455
+ "latent_planner.latent_action_expert.layers.14.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
456
+ "latent_planner.latent_action_expert.layers.14.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
457
+ "latent_planner.latent_action_expert.layers.14.ffn_norm.weight": "model-00002-of-00002.safetensors",
458
+ "latent_planner.latent_action_expert.layers.15.attention.wo.weight": "model-00002-of-00002.safetensors",
459
+ "latent_planner.latent_action_expert.layers.15.attention.wqkv.weight": "model-00002-of-00002.safetensors",
460
+ "latent_planner.latent_action_expert.layers.15.attention_norm.weight": "model-00002-of-00002.safetensors",
461
+ "latent_planner.latent_action_expert.layers.15.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
462
+ "latent_planner.latent_action_expert.layers.15.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
463
+ "latent_planner.latent_action_expert.layers.15.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
464
+ "latent_planner.latent_action_expert.layers.15.ffn_norm.weight": "model-00002-of-00002.safetensors",
465
+ "latent_planner.latent_action_expert.layers.16.attention.wo.weight": "model-00002-of-00002.safetensors",
466
+ "latent_planner.latent_action_expert.layers.16.attention.wqkv.weight": "model-00002-of-00002.safetensors",
467
+ "latent_planner.latent_action_expert.layers.16.attention_norm.weight": "model-00002-of-00002.safetensors",
468
+ "latent_planner.latent_action_expert.layers.16.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
469
+ "latent_planner.latent_action_expert.layers.16.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
470
+ "latent_planner.latent_action_expert.layers.16.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
471
+ "latent_planner.latent_action_expert.layers.16.ffn_norm.weight": "model-00002-of-00002.safetensors",
472
+ "latent_planner.latent_action_expert.layers.17.attention.wo.weight": "model-00002-of-00002.safetensors",
473
+ "latent_planner.latent_action_expert.layers.17.attention.wqkv.weight": "model-00002-of-00002.safetensors",
474
+ "latent_planner.latent_action_expert.layers.17.attention_norm.weight": "model-00002-of-00002.safetensors",
475
+ "latent_planner.latent_action_expert.layers.17.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
476
+ "latent_planner.latent_action_expert.layers.17.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
477
+ "latent_planner.latent_action_expert.layers.17.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
478
+ "latent_planner.latent_action_expert.layers.17.ffn_norm.weight": "model-00002-of-00002.safetensors",
479
+ "latent_planner.latent_action_expert.layers.18.attention.wo.weight": "model-00002-of-00002.safetensors",
480
+ "latent_planner.latent_action_expert.layers.18.attention.wqkv.weight": "model-00002-of-00002.safetensors",
481
+ "latent_planner.latent_action_expert.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
482
+ "latent_planner.latent_action_expert.layers.18.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
483
+ "latent_planner.latent_action_expert.layers.18.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
484
+ "latent_planner.latent_action_expert.layers.18.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
485
+ "latent_planner.latent_action_expert.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
486
+ "latent_planner.latent_action_expert.layers.19.attention.wo.weight": "model-00002-of-00002.safetensors",
487
+ "latent_planner.latent_action_expert.layers.19.attention.wqkv.weight": "model-00002-of-00002.safetensors",
488
+ "latent_planner.latent_action_expert.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
489
+ "latent_planner.latent_action_expert.layers.19.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
490
+ "latent_planner.latent_action_expert.layers.19.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
491
+ "latent_planner.latent_action_expert.layers.19.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
492
+ "latent_planner.latent_action_expert.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
493
+ "latent_planner.latent_action_expert.layers.2.attention.wo.weight": "model-00002-of-00002.safetensors",
494
+ "latent_planner.latent_action_expert.layers.2.attention.wqkv.weight": "model-00002-of-00002.safetensors",
495
+ "latent_planner.latent_action_expert.layers.2.attention_norm.weight": "model-00002-of-00002.safetensors",
496
+ "latent_planner.latent_action_expert.layers.2.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
497
+ "latent_planner.latent_action_expert.layers.2.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
498
+ "latent_planner.latent_action_expert.layers.2.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
499
+ "latent_planner.latent_action_expert.layers.2.ffn_norm.weight": "model-00002-of-00002.safetensors",
500
+ "latent_planner.latent_action_expert.layers.20.attention.wo.weight": "model-00002-of-00002.safetensors",
501
+ "latent_planner.latent_action_expert.layers.20.attention.wqkv.weight": "model-00002-of-00002.safetensors",
502
+ "latent_planner.latent_action_expert.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
503
+ "latent_planner.latent_action_expert.layers.20.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
504
+ "latent_planner.latent_action_expert.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
505
+ "latent_planner.latent_action_expert.layers.20.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
506
+ "latent_planner.latent_action_expert.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
507
+ "latent_planner.latent_action_expert.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
508
+ "latent_planner.latent_action_expert.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
509
+ "latent_planner.latent_action_expert.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
510
+ "latent_planner.latent_action_expert.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
511
+ "latent_planner.latent_action_expert.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
512
+ "latent_planner.latent_action_expert.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
513
+ "latent_planner.latent_action_expert.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
514
+ "latent_planner.latent_action_expert.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
515
+ "latent_planner.latent_action_expert.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
516
+ "latent_planner.latent_action_expert.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
517
+ "latent_planner.latent_action_expert.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
518
+ "latent_planner.latent_action_expert.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
519
+ "latent_planner.latent_action_expert.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
520
+ "latent_planner.latent_action_expert.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
521
+ "latent_planner.latent_action_expert.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
522
+ "latent_planner.latent_action_expert.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
523
+ "latent_planner.latent_action_expert.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
524
+ "latent_planner.latent_action_expert.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
525
+ "latent_planner.latent_action_expert.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
526
+ "latent_planner.latent_action_expert.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
527
+ "latent_planner.latent_action_expert.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
528
+ "latent_planner.latent_action_expert.layers.3.attention.wo.weight": "model-00002-of-00002.safetensors",
529
+ "latent_planner.latent_action_expert.layers.3.attention.wqkv.weight": "model-00002-of-00002.safetensors",
530
+ "latent_planner.latent_action_expert.layers.3.attention_norm.weight": "model-00002-of-00002.safetensors",
531
+ "latent_planner.latent_action_expert.layers.3.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
532
+ "latent_planner.latent_action_expert.layers.3.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
533
+ "latent_planner.latent_action_expert.layers.3.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
534
+ "latent_planner.latent_action_expert.layers.3.ffn_norm.weight": "model-00002-of-00002.safetensors",
535
+ "latent_planner.latent_action_expert.layers.4.attention.wo.weight": "model-00002-of-00002.safetensors",
536
+ "latent_planner.latent_action_expert.layers.4.attention.wqkv.weight": "model-00002-of-00002.safetensors",
537
+ "latent_planner.latent_action_expert.layers.4.attention_norm.weight": "model-00002-of-00002.safetensors",
538
+ "latent_planner.latent_action_expert.layers.4.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
539
+ "latent_planner.latent_action_expert.layers.4.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
540
+ "latent_planner.latent_action_expert.layers.4.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
541
+ "latent_planner.latent_action_expert.layers.4.ffn_norm.weight": "model-00002-of-00002.safetensors",
542
+ "latent_planner.latent_action_expert.layers.5.attention.wo.weight": "model-00002-of-00002.safetensors",
543
+ "latent_planner.latent_action_expert.layers.5.attention.wqkv.weight": "model-00002-of-00002.safetensors",
544
+ "latent_planner.latent_action_expert.layers.5.attention_norm.weight": "model-00002-of-00002.safetensors",
545
+ "latent_planner.latent_action_expert.layers.5.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
546
+ "latent_planner.latent_action_expert.layers.5.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
547
+ "latent_planner.latent_action_expert.layers.5.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
548
+ "latent_planner.latent_action_expert.layers.5.ffn_norm.weight": "model-00002-of-00002.safetensors",
549
+ "latent_planner.latent_action_expert.layers.6.attention.wo.weight": "model-00002-of-00002.safetensors",
550
+ "latent_planner.latent_action_expert.layers.6.attention.wqkv.weight": "model-00002-of-00002.safetensors",
551
+ "latent_planner.latent_action_expert.layers.6.attention_norm.weight": "model-00002-of-00002.safetensors",
552
+ "latent_planner.latent_action_expert.layers.6.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
553
+ "latent_planner.latent_action_expert.layers.6.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
554
+ "latent_planner.latent_action_expert.layers.6.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
555
+ "latent_planner.latent_action_expert.layers.6.ffn_norm.weight": "model-00002-of-00002.safetensors",
556
+ "latent_planner.latent_action_expert.layers.7.attention.wo.weight": "model-00002-of-00002.safetensors",
557
+ "latent_planner.latent_action_expert.layers.7.attention.wqkv.weight": "model-00002-of-00002.safetensors",
558
+ "latent_planner.latent_action_expert.layers.7.attention_norm.weight": "model-00002-of-00002.safetensors",
559
+ "latent_planner.latent_action_expert.layers.7.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
560
+ "latent_planner.latent_action_expert.layers.7.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
561
+ "latent_planner.latent_action_expert.layers.7.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
562
+ "latent_planner.latent_action_expert.layers.7.ffn_norm.weight": "model-00002-of-00002.safetensors",
563
+ "latent_planner.latent_action_expert.layers.8.attention.wo.weight": "model-00002-of-00002.safetensors",
564
+ "latent_planner.latent_action_expert.layers.8.attention.wqkv.weight": "model-00002-of-00002.safetensors",
565
+ "latent_planner.latent_action_expert.layers.8.attention_norm.weight": "model-00002-of-00002.safetensors",
566
+ "latent_planner.latent_action_expert.layers.8.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
567
+ "latent_planner.latent_action_expert.layers.8.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
568
+ "latent_planner.latent_action_expert.layers.8.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
569
+ "latent_planner.latent_action_expert.layers.8.ffn_norm.weight": "model-00002-of-00002.safetensors",
570
+ "latent_planner.latent_action_expert.layers.9.attention.wo.weight": "model-00002-of-00002.safetensors",
571
+ "latent_planner.latent_action_expert.layers.9.attention.wqkv.weight": "model-00002-of-00002.safetensors",
572
+ "latent_planner.latent_action_expert.layers.9.attention_norm.weight": "model-00002-of-00002.safetensors",
573
+ "latent_planner.latent_action_expert.layers.9.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
574
+ "latent_planner.latent_action_expert.layers.9.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
575
+ "latent_planner.latent_action_expert.layers.9.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
576
+ "latent_planner.latent_action_expert.layers.9.ffn_norm.weight": "model-00002-of-00002.safetensors",
577
+ "latent_planner.latent_action_expert.norm.weight": "model-00002-of-00002.safetensors",
578
+ "latent_planner.latent_final_layer.ffn_final.fc1.bias": "model-00002-of-00002.safetensors",
579
+ "latent_planner.latent_final_layer.ffn_final.fc1.weight": "model-00002-of-00002.safetensors",
580
+ "latent_planner.latent_final_layer.ffn_final.fc2.bias": "model-00002-of-00002.safetensors",
581
+ "latent_planner.latent_final_layer.ffn_final.fc2.weight": "model-00002-of-00002.safetensors",
582
+ "latent_planner.latent_final_layer.norm_final.weight": "model-00002-of-00002.safetensors",
583
+ "latent_planner.latent_k_proj_layers.0.bias": "model-00002-of-00002.safetensors",
584
+ "latent_planner.latent_k_proj_layers.0.weight": "model-00002-of-00002.safetensors",
585
+ "latent_planner.latent_k_proj_layers.1.bias": "model-00002-of-00002.safetensors",
586
+ "latent_planner.latent_k_proj_layers.1.weight": "model-00002-of-00002.safetensors",
587
+ "latent_planner.latent_k_proj_layers.10.bias": "model-00002-of-00002.safetensors",
588
+ "latent_planner.latent_k_proj_layers.10.weight": "model-00002-of-00002.safetensors",
589
+ "latent_planner.latent_k_proj_layers.11.bias": "model-00002-of-00002.safetensors",
590
+ "latent_planner.latent_k_proj_layers.11.weight": "model-00002-of-00002.safetensors",
591
+ "latent_planner.latent_k_proj_layers.12.bias": "model-00002-of-00002.safetensors",
592
+ "latent_planner.latent_k_proj_layers.12.weight": "model-00002-of-00002.safetensors",
593
+ "latent_planner.latent_k_proj_layers.13.bias": "model-00002-of-00002.safetensors",
594
+ "latent_planner.latent_k_proj_layers.13.weight": "model-00002-of-00002.safetensors",
595
+ "latent_planner.latent_k_proj_layers.14.bias": "model-00002-of-00002.safetensors",
596
+ "latent_planner.latent_k_proj_layers.14.weight": "model-00002-of-00002.safetensors",
597
+ "latent_planner.latent_k_proj_layers.15.bias": "model-00002-of-00002.safetensors",
598
+ "latent_planner.latent_k_proj_layers.15.weight": "model-00002-of-00002.safetensors",
599
+ "latent_planner.latent_k_proj_layers.16.bias": "model-00002-of-00002.safetensors",
600
+ "latent_planner.latent_k_proj_layers.16.weight": "model-00002-of-00002.safetensors",
601
+ "latent_planner.latent_k_proj_layers.17.bias": "model-00002-of-00002.safetensors",
602
+ "latent_planner.latent_k_proj_layers.17.weight": "model-00002-of-00002.safetensors",
603
+ "latent_planner.latent_k_proj_layers.18.bias": "model-00002-of-00002.safetensors",
604
+ "latent_planner.latent_k_proj_layers.18.weight": "model-00002-of-00002.safetensors",
605
+ "latent_planner.latent_k_proj_layers.19.bias": "model-00002-of-00002.safetensors",
606
+ "latent_planner.latent_k_proj_layers.19.weight": "model-00002-of-00002.safetensors",
607
+ "latent_planner.latent_k_proj_layers.2.bias": "model-00002-of-00002.safetensors",
608
+ "latent_planner.latent_k_proj_layers.2.weight": "model-00002-of-00002.safetensors",
609
+ "latent_planner.latent_k_proj_layers.20.bias": "model-00002-of-00002.safetensors",
610
+ "latent_planner.latent_k_proj_layers.20.weight": "model-00002-of-00002.safetensors",
611
+ "latent_planner.latent_k_proj_layers.21.bias": "model-00002-of-00002.safetensors",
612
+ "latent_planner.latent_k_proj_layers.21.weight": "model-00002-of-00002.safetensors",
613
+ "latent_planner.latent_k_proj_layers.22.bias": "model-00002-of-00002.safetensors",
614
+ "latent_planner.latent_k_proj_layers.22.weight": "model-00002-of-00002.safetensors",
615
+ "latent_planner.latent_k_proj_layers.23.bias": "model-00002-of-00002.safetensors",
616
+ "latent_planner.latent_k_proj_layers.23.weight": "model-00002-of-00002.safetensors",
617
+ "latent_planner.latent_k_proj_layers.3.bias": "model-00002-of-00002.safetensors",
618
+ "latent_planner.latent_k_proj_layers.3.weight": "model-00002-of-00002.safetensors",
619
+ "latent_planner.latent_k_proj_layers.4.bias": "model-00002-of-00002.safetensors",
620
+ "latent_planner.latent_k_proj_layers.4.weight": "model-00002-of-00002.safetensors",
621
+ "latent_planner.latent_k_proj_layers.5.bias": "model-00002-of-00002.safetensors",
622
+ "latent_planner.latent_k_proj_layers.5.weight": "model-00002-of-00002.safetensors",
623
+ "latent_planner.latent_k_proj_layers.6.bias": "model-00002-of-00002.safetensors",
624
+ "latent_planner.latent_k_proj_layers.6.weight": "model-00002-of-00002.safetensors",
625
+ "latent_planner.latent_k_proj_layers.7.bias": "model-00002-of-00002.safetensors",
626
+ "latent_planner.latent_k_proj_layers.7.weight": "model-00002-of-00002.safetensors",
627
+ "latent_planner.latent_k_proj_layers.8.bias": "model-00002-of-00002.safetensors",
628
+ "latent_planner.latent_k_proj_layers.8.weight": "model-00002-of-00002.safetensors",
629
+ "latent_planner.latent_k_proj_layers.9.bias": "model-00002-of-00002.safetensors",
630
+ "latent_planner.latent_k_proj_layers.9.weight": "model-00002-of-00002.safetensors",
631
+ "latent_planner.latent_state_action_adaptor.0.bias": "model-00002-of-00002.safetensors",
632
+ "latent_planner.latent_state_action_adaptor.0.weight": "model-00002-of-00002.safetensors",
633
+ "latent_planner.latent_state_action_adaptor.2.bias": "model-00002-of-00002.safetensors",
634
+ "latent_planner.latent_state_action_adaptor.2.weight": "model-00002-of-00002.safetensors",
635
+ "latent_planner.latent_state_action_adaptor.4.bias": "model-00002-of-00002.safetensors",
636
+ "latent_planner.latent_state_action_adaptor.4.weight": "model-00002-of-00002.safetensors",
637
+ "latent_planner.latent_v_proj_layers.0.bias": "model-00002-of-00002.safetensors",
638
+ "latent_planner.latent_v_proj_layers.0.weight": "model-00002-of-00002.safetensors",
639
+ "latent_planner.latent_v_proj_layers.1.bias": "model-00002-of-00002.safetensors",
640
+ "latent_planner.latent_v_proj_layers.1.weight": "model-00002-of-00002.safetensors",
641
+ "latent_planner.latent_v_proj_layers.10.bias": "model-00002-of-00002.safetensors",
642
+ "latent_planner.latent_v_proj_layers.10.weight": "model-00002-of-00002.safetensors",
643
+ "latent_planner.latent_v_proj_layers.11.bias": "model-00002-of-00002.safetensors",
644
+ "latent_planner.latent_v_proj_layers.11.weight": "model-00002-of-00002.safetensors",
645
+ "latent_planner.latent_v_proj_layers.12.bias": "model-00002-of-00002.safetensors",
646
+ "latent_planner.latent_v_proj_layers.12.weight": "model-00002-of-00002.safetensors",
647
+ "latent_planner.latent_v_proj_layers.13.bias": "model-00002-of-00002.safetensors",
648
+ "latent_planner.latent_v_proj_layers.13.weight": "model-00002-of-00002.safetensors",
649
+ "latent_planner.latent_v_proj_layers.14.bias": "model-00002-of-00002.safetensors",
650
+ "latent_planner.latent_v_proj_layers.14.weight": "model-00002-of-00002.safetensors",
651
+ "latent_planner.latent_v_proj_layers.15.bias": "model-00002-of-00002.safetensors",
652
+ "latent_planner.latent_v_proj_layers.15.weight": "model-00002-of-00002.safetensors",
653
+ "latent_planner.latent_v_proj_layers.16.bias": "model-00002-of-00002.safetensors",
654
+ "latent_planner.latent_v_proj_layers.16.weight": "model-00002-of-00002.safetensors",
655
+ "latent_planner.latent_v_proj_layers.17.bias": "model-00002-of-00002.safetensors",
656
+ "latent_planner.latent_v_proj_layers.17.weight": "model-00002-of-00002.safetensors",
657
+ "latent_planner.latent_v_proj_layers.18.bias": "model-00002-of-00002.safetensors",
658
+ "latent_planner.latent_v_proj_layers.18.weight": "model-00002-of-00002.safetensors",
659
+ "latent_planner.latent_v_proj_layers.19.bias": "model-00002-of-00002.safetensors",
660
+ "latent_planner.latent_v_proj_layers.19.weight": "model-00002-of-00002.safetensors",
661
+ "latent_planner.latent_v_proj_layers.2.bias": "model-00002-of-00002.safetensors",
662
+ "latent_planner.latent_v_proj_layers.2.weight": "model-00002-of-00002.safetensors",
663
+ "latent_planner.latent_v_proj_layers.20.bias": "model-00002-of-00002.safetensors",
664
+ "latent_planner.latent_v_proj_layers.20.weight": "model-00002-of-00002.safetensors",
665
+ "latent_planner.latent_v_proj_layers.21.bias": "model-00002-of-00002.safetensors",
666
+ "latent_planner.latent_v_proj_layers.21.weight": "model-00002-of-00002.safetensors",
667
+ "latent_planner.latent_v_proj_layers.22.bias": "model-00002-of-00002.safetensors",
668
+ "latent_planner.latent_v_proj_layers.22.weight": "model-00002-of-00002.safetensors",
669
+ "latent_planner.latent_v_proj_layers.23.bias": "model-00002-of-00002.safetensors",
670
+ "latent_planner.latent_v_proj_layers.23.weight": "model-00002-of-00002.safetensors",
671
+ "latent_planner.latent_v_proj_layers.3.bias": "model-00002-of-00002.safetensors",
672
+ "latent_planner.latent_v_proj_layers.3.weight": "model-00002-of-00002.safetensors",
673
+ "latent_planner.latent_v_proj_layers.4.bias": "model-00002-of-00002.safetensors",
674
+ "latent_planner.latent_v_proj_layers.4.weight": "model-00002-of-00002.safetensors",
675
+ "latent_planner.latent_v_proj_layers.5.bias": "model-00002-of-00002.safetensors",
676
+ "latent_planner.latent_v_proj_layers.5.weight": "model-00002-of-00002.safetensors",
677
+ "latent_planner.latent_v_proj_layers.6.bias": "model-00002-of-00002.safetensors",
678
+ "latent_planner.latent_v_proj_layers.6.weight": "model-00002-of-00002.safetensors",
679
+ "latent_planner.latent_v_proj_layers.7.bias": "model-00002-of-00002.safetensors",
680
+ "latent_planner.latent_v_proj_layers.7.weight": "model-00002-of-00002.safetensors",
681
+ "latent_planner.latent_v_proj_layers.8.bias": "model-00002-of-00002.safetensors",
682
+ "latent_planner.latent_v_proj_layers.8.weight": "model-00002-of-00002.safetensors",
683
+ "latent_planner.latent_v_proj_layers.9.bias": "model-00002-of-00002.safetensors",
684
+ "latent_planner.latent_v_proj_layers.9.weight": "model-00002-of-00002.safetensors",
685
+ "latent_planner.score.weight": "model-00002-of-00002.safetensors",
686
+ "mlp1.0.bias": "model-00001-of-00002.safetensors",
687
+ "mlp1.0.weight": "model-00001-of-00002.safetensors",
688
+ "mlp1.1.bias": "model-00001-of-00002.safetensors",
689
+ "mlp1.1.weight": "model-00001-of-00002.safetensors",
690
+ "mlp1.3.bias": "model-00001-of-00002.safetensors",
691
+ "mlp1.3.weight": "model-00001-of-00002.safetensors",
692
+ "state_adaptor.0.bias": "model-00002-of-00002.safetensors",
693
+ "state_adaptor.0.weight": "model-00002-of-00002.safetensors",
694
+ "state_adaptor.2.bias": "model-00002-of-00002.safetensors",
695
+ "state_adaptor.2.weight": "model-00002-of-00002.safetensors",
696
+ "state_adaptor.4.bias": "model-00002-of-00002.safetensors",
697
+ "state_adaptor.4.weight": "model-00002-of-00002.safetensors",
698
+ "time_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
699
+ "time_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
700
+ "time_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
701
+ "time_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
702
+ "v_proj_layers.0.bias": "model-00002-of-00002.safetensors",
703
+ "v_proj_layers.0.weight": "model-00002-of-00002.safetensors",
704
+ "v_proj_layers.1.bias": "model-00002-of-00002.safetensors",
705
+ "v_proj_layers.1.weight": "model-00002-of-00002.safetensors",
706
+ "v_proj_layers.10.bias": "model-00002-of-00002.safetensors",
707
+ "v_proj_layers.10.weight": "model-00002-of-00002.safetensors",
708
+ "v_proj_layers.11.bias": "model-00002-of-00002.safetensors",
709
+ "v_proj_layers.11.weight": "model-00002-of-00002.safetensors",
710
+ "v_proj_layers.12.bias": "model-00002-of-00002.safetensors",
711
+ "v_proj_layers.12.weight": "model-00002-of-00002.safetensors",
712
+ "v_proj_layers.13.bias": "model-00002-of-00002.safetensors",
713
+ "v_proj_layers.13.weight": "model-00002-of-00002.safetensors",
714
+ "v_proj_layers.14.bias": "model-00002-of-00002.safetensors",
715
+ "v_proj_layers.14.weight": "model-00002-of-00002.safetensors",
716
+ "v_proj_layers.15.bias": "model-00002-of-00002.safetensors",
717
+ "v_proj_layers.15.weight": "model-00002-of-00002.safetensors",
718
+ "v_proj_layers.16.bias": "model-00002-of-00002.safetensors",
719
+ "v_proj_layers.16.weight": "model-00002-of-00002.safetensors",
720
+ "v_proj_layers.17.bias": "model-00002-of-00002.safetensors",
721
+ "v_proj_layers.17.weight": "model-00002-of-00002.safetensors",
722
+ "v_proj_layers.18.bias": "model-00002-of-00002.safetensors",
723
+ "v_proj_layers.18.weight": "model-00002-of-00002.safetensors",
724
+ "v_proj_layers.19.bias": "model-00002-of-00002.safetensors",
725
+ "v_proj_layers.19.weight": "model-00002-of-00002.safetensors",
726
+ "v_proj_layers.2.bias": "model-00002-of-00002.safetensors",
727
+ "v_proj_layers.2.weight": "model-00002-of-00002.safetensors",
728
+ "v_proj_layers.20.bias": "model-00002-of-00002.safetensors",
729
+ "v_proj_layers.20.weight": "model-00002-of-00002.safetensors",
730
+ "v_proj_layers.21.bias": "model-00002-of-00002.safetensors",
731
+ "v_proj_layers.21.weight": "model-00002-of-00002.safetensors",
732
+ "v_proj_layers.22.bias": "model-00002-of-00002.safetensors",
733
+ "v_proj_layers.22.weight": "model-00002-of-00002.safetensors",
734
+ "v_proj_layers.23.bias": "model-00002-of-00002.safetensors",
735
+ "v_proj_layers.23.weight": "model-00002-of-00002.safetensors",
736
+ "v_proj_layers.3.bias": "model-00002-of-00002.safetensors",
737
+ "v_proj_layers.3.weight": "model-00002-of-00002.safetensors",
738
+ "v_proj_layers.4.bias": "model-00002-of-00002.safetensors",
739
+ "v_proj_layers.4.weight": "model-00002-of-00002.safetensors",
740
+ "v_proj_layers.5.bias": "model-00002-of-00002.safetensors",
741
+ "v_proj_layers.5.weight": "model-00002-of-00002.safetensors",
742
+ "v_proj_layers.6.bias": "model-00002-of-00002.safetensors",
743
+ "v_proj_layers.6.weight": "model-00002-of-00002.safetensors",
744
+ "v_proj_layers.7.bias": "model-00002-of-00002.safetensors",
745
+ "v_proj_layers.7.weight": "model-00002-of-00002.safetensors",
746
+ "v_proj_layers.8.bias": "model-00002-of-00002.safetensors",
747
+ "v_proj_layers.8.weight": "model-00002-of-00002.safetensors",
748
+ "v_proj_layers.9.bias": "model-00002-of-00002.safetensors",
749
+ "v_proj_layers.9.weight": "model-00002-of-00002.safetensors",
750
+ "vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
751
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
752
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
753
+ "vision_model.embeddings.position_embedding": "model-00001-of-00002.safetensors",
754
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00002.safetensors",
755
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00002.safetensors",
756
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
757
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
758
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00002.safetensors",
759
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00002.safetensors",
760
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
761
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
762
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
763
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
764
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00002.safetensors",
765
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00002.safetensors",
766
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00002.safetensors",
767
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00002.safetensors",
768
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00002.safetensors",
769
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00002.safetensors",
770
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
771
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
772
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00002.safetensors",
773
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00002.safetensors",
774
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
775
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
776
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
777
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
778
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00002.safetensors",
779
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00002.safetensors",
780
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00002.safetensors",
781
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00002.safetensors",
782
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00002.safetensors",
783
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00002.safetensors",
784
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
785
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
786
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00002.safetensors",
787
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00002.safetensors",
788
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
789
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
790
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
791
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
792
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00002.safetensors",
793
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00002.safetensors",
794
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00002.safetensors",
795
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00002.safetensors",
796
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00002.safetensors",
797
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00002.safetensors",
798
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
799
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
800
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00002.safetensors",
801
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00002.safetensors",
802
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
803
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
804
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
805
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
806
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00002.safetensors",
807
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00002.safetensors",
808
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00002.safetensors",
809
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00002.safetensors",
810
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00002.safetensors",
811
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00002.safetensors",
812
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
813
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
814
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00002.safetensors",
815
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00002.safetensors",
816
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
817
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
818
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
819
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
820
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00002.safetensors",
821
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00002.safetensors",
822
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00002.safetensors",
823
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00002.safetensors",
824
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00002.safetensors",
825
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00002.safetensors",
826
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
827
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
828
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00002.safetensors",
829
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00002.safetensors",
830
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
831
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
832
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
833
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
834
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00002.safetensors",
835
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00002.safetensors",
836
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00002.safetensors",
837
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00002.safetensors",
838
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00002.safetensors",
839
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00002.safetensors",
840
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
841
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
842
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00002.safetensors",
843
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00002.safetensors",
844
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
845
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
846
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
847
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
848
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00002.safetensors",
849
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00002.safetensors",
850
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00002.safetensors",
851
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00002.safetensors",
852
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00002.safetensors",
853
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00002.safetensors",
854
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
855
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
856
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00002.safetensors",
857
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00002.safetensors",
858
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
859
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
860
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
861
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
862
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00002.safetensors",
863
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00002.safetensors",
864
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00002.safetensors",
865
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00002.safetensors",
866
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00002.safetensors",
867
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00002.safetensors",
868
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
869
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
870
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00002.safetensors",
871
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00002.safetensors",
872
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
873
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
874
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
875
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
876
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00002.safetensors",
877
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00002.safetensors",
878
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00002.safetensors",
879
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00002.safetensors",
880
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00002.safetensors",
881
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00002.safetensors",
882
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
883
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
884
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00002.safetensors",
885
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00002.safetensors",
886
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
887
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
888
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
889
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
890
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00002.safetensors",
891
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00002.safetensors",
892
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00002.safetensors",
893
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00002.safetensors",
894
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00002.safetensors",
895
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00002.safetensors",
896
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
897
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
898
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00002.safetensors",
899
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00002.safetensors",
900
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
901
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
902
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
903
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
904
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00002.safetensors",
905
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00002.safetensors",
906
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00002.safetensors",
907
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00002.safetensors",
908
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00002.safetensors",
909
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00002.safetensors",
910
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
911
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
912
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00002.safetensors",
913
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00002.safetensors",
914
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
915
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
916
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
917
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
918
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00002.safetensors",
919
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00002.safetensors",
920
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00002.safetensors",
921
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00002.safetensors",
922
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00002.safetensors",
923
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00002.safetensors",
924
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
925
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
926
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00002.safetensors",
927
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00002.safetensors",
928
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
929
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
930
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
931
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
932
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00002.safetensors",
933
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00002.safetensors",
934
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00002.safetensors",
935
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00002.safetensors",
936
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00002.safetensors",
937
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00002.safetensors",
938
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
939
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
940
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00002.safetensors",
941
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00002.safetensors",
942
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
943
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
944
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
945
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
946
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00002.safetensors",
947
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00002.safetensors",
948
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00002.safetensors",
949
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00002.safetensors",
950
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00002.safetensors",
951
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00002.safetensors",
952
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
953
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
954
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00002.safetensors",
955
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00002.safetensors",
956
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
957
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
958
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
959
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
960
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00002.safetensors",
961
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00002.safetensors",
962
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00002.safetensors",
963
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00002.safetensors",
964
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00002.safetensors",
965
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00002.safetensors",
966
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
967
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
968
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00002.safetensors",
969
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00002.safetensors",
970
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
971
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
972
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
973
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
974
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00002.safetensors",
975
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00002.safetensors",
976
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00002.safetensors",
977
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00002.safetensors",
978
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00002.safetensors",
979
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00002.safetensors",
980
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
981
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
982
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00002.safetensors",
983
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00002.safetensors",
984
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
985
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
986
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
987
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
988
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00002.safetensors",
989
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00002.safetensors",
990
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00002.safetensors",
991
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00002.safetensors",
992
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00002.safetensors",
993
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00002.safetensors",
994
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
995
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
996
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00002.safetensors",
997
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00002.safetensors",
998
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
999
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1000
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1001
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1002
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00002.safetensors",
1003
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00002.safetensors",
1004
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00002.safetensors",
1005
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00002.safetensors",
1006
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00002.safetensors",
1007
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00002.safetensors",
1008
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
1009
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
1010
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00002.safetensors",
1011
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00002.safetensors",
1012
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
1013
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1014
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1015
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1016
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00002.safetensors",
1017
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00002.safetensors",
1018
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00002.safetensors",
1019
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00002.safetensors",
1020
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00002.safetensors",
1021
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00002.safetensors",
1022
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
1023
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
1024
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00002.safetensors",
1025
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00002.safetensors",
1026
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
1027
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1028
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1029
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1030
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00002.safetensors",
1031
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00002.safetensors",
1032
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00002.safetensors",
1033
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00002.safetensors",
1034
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00002.safetensors",
1035
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00002.safetensors",
1036
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
1037
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
1038
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00002.safetensors",
1039
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00002.safetensors",
1040
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
1041
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1042
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1043
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1044
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00002.safetensors",
1045
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00002.safetensors",
1046
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00002.safetensors",
1047
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00002.safetensors",
1048
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00002.safetensors",
1049
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00002.safetensors",
1050
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
1051
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
1052
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00002.safetensors",
1053
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00002.safetensors",
1054
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
1055
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1056
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1057
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1058
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00002.safetensors",
1059
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00002.safetensors",
1060
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00002.safetensors",
1061
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00002.safetensors",
1062
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00002.safetensors",
1063
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00002.safetensors",
1064
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
1065
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
1066
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00002.safetensors",
1067
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00002.safetensors",
1068
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
1069
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1070
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1071
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1072
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00002.safetensors",
1073
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00002.safetensors",
1074
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00002.safetensors",
1075
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00002.safetensors",
1076
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00002.safetensors",
1077
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00002.safetensors",
1078
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
1079
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
1080
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00002.safetensors",
1081
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00002.safetensors",
1082
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
1083
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
1084
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
1085
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
1086
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00002.safetensors",
1087
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00002.safetensors",
1088
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00002.safetensors",
1089
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00002.safetensors"
1090
+ }
1091
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b1a38687e202ec2e13f432bc869fa320be0907c971920f45d09d4e719794ea
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5aaf128881dff789bc9d40089a7e5d0f75cfbe9d6121114f50ec52bdf87eac
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2c01f6f9d2680aeb825d0f175fab40dfeb5979c803024e53314ecf688b27d2
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b124e4a2654984665b7f15199347f34adcba203df728f31093a11f8d6a904552
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b6dee5545119323ee17493cd13e4928e734900dc093889f3b3601226c4f898
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1dedd15804b4cb957a1085f38aa317d8e8ce442a2d94bd0c50482e1b066254
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6081b1c373a77fb362905778135e2a94841537095be47c7c6da5253ed1d1cf62
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527bebd7d0074a5721cb0b0b3506a79401ea51239e6d8530b0d91b585b2f7b04
3
+ size 15984
special_tokens_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>"
18
+ ],
19
+ "bos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "unk_token": {
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ }
47
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<|im_start|>",
150
+ "<|im_end|>",
151
+ "<|action_start|>",
152
+ "<|action_end|>",
153
+ "<|interpreter|>",
154
+ "<|plugin|>",
155
+ "<img>",
156
+ "</img>",
157
+ "<IMG_CONTEXT>",
158
+ "<quad>",
159
+ "</quad>",
160
+ "<ref>",
161
+ "</ref>",
162
+ "<box>",
163
+ "</box>"
164
+ ],
165
+ "auto_map": {
166
+ "AutoTokenizer": [
167
+ "tokenization_internlm2.InternLM2Tokenizer",
168
+ null
169
+ ]
170
+ },
171
+ "bos_token": "<s>",
172
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "</s>",
175
+ "model_max_length": 4096,
176
+ "pad_token": "</s>",
177
+ "tokenizer_class": "InternLM2Tokenizer",
178
+ "unk_token": "<unk>"
179
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab0bf09c29846c0ea51de1d7183e7cac15a29a5d08da6afa8487c6209437b4e
3
+ size 7160
zero_to_fp32.py ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import json
25
+ from tqdm import tqdm
26
+ from collections import OrderedDict
27
+ from dataclasses import dataclass
28
+
29
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
30
+ # DeepSpeed data structures it has to be available in the current python environment.
31
+ from deepspeed.utils import logger
32
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
33
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
34
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
35
+
36
+
37
+ @dataclass
38
+ class zero_model_state:
39
+ buffers: dict()
40
+ param_shapes: dict()
41
+ shared_params: list
42
+ ds_version: int
43
+ frozen_param_shapes: dict()
44
+ frozen_param_fragments: dict()
45
+
46
+
47
+ debug = 0
48
+
49
+ # load to cpu
50
+ device = torch.device('cpu')
51
+
52
+
53
+ def atoi(text):
54
+ return int(text) if text.isdigit() else text
55
+
56
+
57
+ def natural_keys(text):
58
+ '''
59
+ alist.sort(key=natural_keys) sorts in human order
60
+ http://nedbatchelder.com/blog/200712/human_sorting.html
61
+ (See Toothy's implementation in the comments)
62
+ '''
63
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
64
+
65
+
66
+ def get_model_state_file(checkpoint_dir, zero_stage):
67
+ if not os.path.isdir(checkpoint_dir):
68
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
69
+
70
+ # there should be only one file
71
+ if zero_stage <= 2:
72
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
73
+ elif zero_stage == 3:
74
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
75
+
76
+ if not os.path.exists(file):
77
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
78
+
79
+ return file
80
+
81
+
82
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
83
+ # XXX: need to test that this simple glob rule works for multi-node setup too
84
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
85
+
86
+ if len(ckpt_files) == 0:
87
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
88
+
89
+ return ckpt_files
90
+
91
+
92
+ def get_optim_files(checkpoint_dir):
93
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
94
+
95
+
96
+ def get_model_state_files(checkpoint_dir):
97
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
98
+
99
+
100
+ def parse_model_states(files):
101
+ zero_model_states = []
102
+ for file in files:
103
+ state_dict = torch.load(file, map_location=device)
104
+
105
+ if BUFFER_NAMES not in state_dict:
106
+ raise ValueError(f"{file} is not a model state checkpoint")
107
+ buffer_names = state_dict[BUFFER_NAMES]
108
+ if debug:
109
+ print("Found buffers:", buffer_names)
110
+
111
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
112
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
113
+ param_shapes = state_dict[PARAM_SHAPES]
114
+
115
+ # collect parameters that are included in param_shapes
116
+ param_names = []
117
+ for s in param_shapes:
118
+ for name in s.keys():
119
+ param_names.append(name)
120
+
121
+ # update with frozen parameters
122
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
123
+ if frozen_param_shapes is not None:
124
+ if debug:
125
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
126
+ param_names += list(frozen_param_shapes.keys())
127
+
128
+ # handle shared params
129
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
130
+
131
+ ds_version = state_dict.get(DS_VERSION, None)
132
+
133
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
134
+
135
+ z_model_state = zero_model_state(buffers=buffers,
136
+ param_shapes=param_shapes,
137
+ shared_params=shared_params,
138
+ ds_version=ds_version,
139
+ frozen_param_shapes=frozen_param_shapes,
140
+ frozen_param_fragments=frozen_param_fragments)
141
+ zero_model_states.append(z_model_state)
142
+
143
+ return zero_model_states
144
+
145
+
146
+ def parse_optim_states(files, ds_checkpoint_dir):
147
+ total_files = len(files)
148
+ state_dicts = []
149
+ for f in files:
150
+ state_dict = torch.load(f, map_location=device)
151
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
152
+ # and also handle the case where it was already removed by another helper script
153
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
154
+ state_dicts.append(state_dict)
155
+
156
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
157
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
158
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
159
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
160
+
161
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
162
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
163
+ # use the max of the partition_count to get the dp world_size.
164
+
165
+ if type(world_size) is list:
166
+ world_size = max(world_size)
167
+
168
+ if world_size != total_files:
169
+ raise ValueError(
170
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
171
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
172
+ )
173
+
174
+ # the groups are named differently in each stage
175
+ if zero_stage <= 2:
176
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
177
+ elif zero_stage == 3:
178
+ fp32_groups_key = FP32_FLAT_GROUPS
179
+ else:
180
+ raise ValueError(f"unknown zero stage {zero_stage}")
181
+
182
+ if zero_stage <= 2:
183
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
184
+ elif zero_stage == 3:
185
+ # if there is more than one param group, there will be multiple flattened tensors - one
186
+ # flattened tensor per group - for simplicity merge them into a single tensor
187
+ #
188
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
189
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
190
+
191
+ fp32_flat_groups = [
192
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
193
+ ]
194
+
195
+ return zero_stage, world_size, fp32_flat_groups
196
+
197
+
198
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
199
+ """
200
+ Returns fp32 state_dict reconstructed from ds checkpoint
201
+
202
+ Args:
203
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
204
+
205
+ """
206
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
207
+
208
+ optim_files = get_optim_files(ds_checkpoint_dir)
209
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
210
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
211
+
212
+ model_files = get_model_state_files(ds_checkpoint_dir)
213
+
214
+ zero_model_states = parse_model_states(model_files)
215
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
216
+
217
+ if zero_stage <= 2:
218
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
219
+ exclude_frozen_parameters)
220
+ elif zero_stage == 3:
221
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
222
+ exclude_frozen_parameters)
223
+
224
+
225
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
226
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
227
+ return
228
+
229
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
230
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
231
+
232
+ if debug:
233
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
234
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
235
+
236
+ wanted_params = len(frozen_param_shapes)
237
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
238
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
239
+ print(f'Frozen params: Have {avail_numel} numels to process.')
240
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
241
+
242
+ total_params = 0
243
+ total_numel = 0
244
+ for name, shape in frozen_param_shapes.items():
245
+ total_params += 1
246
+ unpartitioned_numel = shape.numel()
247
+ total_numel += unpartitioned_numel
248
+
249
+ state_dict[name] = frozen_param_fragments[name]
250
+
251
+ if debug:
252
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
253
+
254
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
255
+
256
+
257
+ def _has_callable(obj, fn):
258
+ attr = getattr(obj, fn, None)
259
+ return callable(attr)
260
+
261
+
262
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
263
+ param_shapes = zero_model_states[0].param_shapes
264
+
265
+ # Reconstruction protocol:
266
+ #
267
+ # XXX: document this
268
+
269
+ if debug:
270
+ for i in range(world_size):
271
+ for j in range(len(fp32_flat_groups[0])):
272
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
273
+
274
+ # XXX: memory usage doubles here (zero2)
275
+ num_param_groups = len(fp32_flat_groups[0])
276
+ merged_single_partition_of_fp32_groups = []
277
+ for i in range(num_param_groups):
278
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
279
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
280
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
281
+ avail_numel = sum(
282
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
283
+
284
+ if debug:
285
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
286
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
287
+ # not asserting if there is a mismatch due to possible padding
288
+ print(f"Have {avail_numel} numels to process.")
289
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
290
+
291
+ # params
292
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
293
+ # out-of-core computing solution
294
+ total_numel = 0
295
+ total_params = 0
296
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
297
+ offset = 0
298
+ avail_numel = full_single_fp32_vector.numel()
299
+ for name, shape in shapes.items():
300
+
301
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
302
+ total_numel += unpartitioned_numel
303
+ total_params += 1
304
+
305
+ if debug:
306
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
307
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
308
+ offset += unpartitioned_numel
309
+
310
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
311
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
312
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
313
+ # live optimizer object, so we are checking that the numbers are within the right range
314
+ align_to = 2 * world_size
315
+
316
+ def zero2_align(x):
317
+ return align_to * math.ceil(x / align_to)
318
+
319
+ if debug:
320
+ print(f"original offset={offset}, avail_numel={avail_numel}")
321
+
322
+ offset = zero2_align(offset)
323
+ avail_numel = zero2_align(avail_numel)
324
+
325
+ if debug:
326
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
327
+
328
+ # Sanity check
329
+ if offset != avail_numel:
330
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
331
+
332
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
333
+
334
+
335
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
336
+ exclude_frozen_parameters):
337
+ state_dict = OrderedDict()
338
+
339
+ # buffers
340
+ buffers = zero_model_states[0].buffers
341
+ state_dict.update(buffers)
342
+ if debug:
343
+ print(f"added {len(buffers)} buffers")
344
+
345
+ if not exclude_frozen_parameters:
346
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
347
+
348
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
349
+
350
+ # recover shared parameters
351
+ for pair in zero_model_states[0].shared_params:
352
+ if pair[1] in state_dict:
353
+ state_dict[pair[0]] = state_dict[pair[1]]
354
+
355
+ return state_dict
356
+
357
+
358
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
359
+ remainder = unpartitioned_numel % world_size
360
+ padding_numel = (world_size - remainder) if remainder else 0
361
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
362
+ return partitioned_numel, padding_numel
363
+
364
+
365
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
366
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
367
+ return
368
+
369
+ if debug:
370
+ for i in range(world_size):
371
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
372
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
373
+
374
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
375
+ wanted_params = len(frozen_param_shapes)
376
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
377
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
378
+ print(f'Frozen params: Have {avail_numel} numels to process.')
379
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
380
+
381
+ total_params = 0
382
+ total_numel = 0
383
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
384
+ total_params += 1
385
+ unpartitioned_numel = shape.numel()
386
+ total_numel += unpartitioned_numel
387
+
388
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
389
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
390
+
391
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
392
+
393
+ if debug:
394
+ print(
395
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
396
+ )
397
+
398
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
399
+
400
+
401
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
402
+ param_shapes = zero_model_states[0].param_shapes
403
+ avail_numel = fp32_flat_groups[0].numel() * world_size
404
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
405
+ # param, re-consolidating each param, while dealing with padding if any
406
+
407
+ # merge list of dicts, preserving order
408
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
409
+
410
+ if debug:
411
+ for i in range(world_size):
412
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
413
+
414
+ wanted_params = len(param_shapes)
415
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
416
+ # not asserting if there is a mismatch due to possible padding
417
+ avail_numel = fp32_flat_groups[0].numel() * world_size
418
+ print(f"Trainable params: Have {avail_numel} numels to process.")
419
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
420
+
421
+ # params
422
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
423
+ # out-of-core computing solution
424
+ offset = 0
425
+ total_numel = 0
426
+ total_params = 0
427
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
428
+ unpartitioned_numel = shape.numel()
429
+ total_numel += unpartitioned_numel
430
+ total_params += 1
431
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
432
+
433
+ if debug:
434
+ print(
435
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
436
+ )
437
+
438
+ # XXX: memory usage doubles here
439
+ state_dict[name] = torch.cat(
440
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
441
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
442
+ offset += partitioned_numel
443
+
444
+ offset *= world_size
445
+
446
+ # Sanity check
447
+ if offset != avail_numel:
448
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
449
+
450
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
451
+
452
+
453
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
454
+ exclude_frozen_parameters):
455
+ state_dict = OrderedDict()
456
+
457
+ # buffers
458
+ buffers = zero_model_states[0].buffers
459
+ state_dict.update(buffers)
460
+ if debug:
461
+ print(f"added {len(buffers)} buffers")
462
+
463
+ if not exclude_frozen_parameters:
464
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
465
+
466
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
467
+
468
+ # recover shared parameters
469
+ for pair in zero_model_states[0].shared_params:
470
+ if pair[1] in state_dict:
471
+ state_dict[pair[0]] = state_dict[pair[1]]
472
+
473
+ return state_dict
474
+
475
+
476
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
477
+ """
478
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
479
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
480
+ via a model hub.
481
+
482
+ Args:
483
+ - ``checkpoint_dir``: path to the desired checkpoint folder
484
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
485
+ - ``exclude_frozen_parameters``: exclude frozen parameters
486
+
487
+ Returns:
488
+ - pytorch ``state_dict``
489
+
490
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
491
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
492
+ the checkpoint.
493
+
494
+ A typical usage might be ::
495
+
496
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
497
+ # do the training and checkpoint saving
498
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
499
+ model = model.cpu() # move to cpu
500
+ model.load_state_dict(state_dict)
501
+ # submit to model hub or save the model to share with others
502
+
503
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
504
+ application. i.e. you will need to re-initialize the deepspeed engine, since
505
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
506
+
507
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
508
+
509
+ """
510
+ if tag is None:
511
+ latest_path = os.path.join(checkpoint_dir, 'latest')
512
+ if os.path.isfile(latest_path):
513
+ with open(latest_path, 'r') as fd:
514
+ tag = fd.read().strip()
515
+ else:
516
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
517
+
518
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
519
+
520
+ if not os.path.isdir(ds_checkpoint_dir):
521
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
522
+
523
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
524
+
525
+
526
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
527
+ output_dir,
528
+ max_shard_size="5GB",
529
+ safe_serialization=False,
530
+ tag=None,
531
+ exclude_frozen_parameters=False):
532
+ """
533
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
534
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
535
+
536
+ Args:
537
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
538
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
539
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
540
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
541
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
542
+ - ``exclude_frozen_parameters``: exclude frozen parameters
543
+ """
544
+ # Dependency pre-check
545
+ if safe_serialization:
546
+ try:
547
+ from safetensors.torch import save_file
548
+ except ImportError:
549
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
550
+ raise
551
+ if max_shard_size is not None:
552
+ try:
553
+ from huggingface_hub import split_torch_state_dict_into_shards
554
+ except ImportError:
555
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
556
+ raise
557
+
558
+ # Convert zero checkpoint to state_dict
559
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
560
+
561
+ # Shard the model if it is too big.
562
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
563
+ if max_shard_size is not None:
564
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
565
+ state_dict_split = split_torch_state_dict_into_shards(state_dict,
566
+ filename_pattern=filename_pattern,
567
+ max_shard_size=max_shard_size)
568
+ else:
569
+ from collections import namedtuple
570
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
571
+ state_dict_split = StateDictSplit(is_sharded=False,
572
+ filename_to_tensors={weights_name: list(state_dict.keys())})
573
+
574
+ # Save the model
575
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
576
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
577
+ shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
578
+ output_path = os.path.join(output_dir, shard_file)
579
+ if safe_serialization:
580
+ save_file(shard, output_path, metadata={"format": "pt"})
581
+ else:
582
+ torch.save(shard, output_path)
583
+
584
+ # Save index if sharded
585
+ if state_dict_split.is_sharded:
586
+ index = {
587
+ "metadata": state_dict_split.metadata,
588
+ "weight_map": state_dict_split.tensor_to_filename,
589
+ }
590
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
591
+ save_index_file = os.path.join(output_dir, save_index_file)
592
+ with open(save_index_file, "w", encoding="utf-8") as f:
593
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
594
+ f.write(content)
595
+
596
+
597
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
598
+ """
599
+ 1. Put the provided model to cpu
600
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
601
+ 3. Load it into the provided model
602
+
603
+ Args:
604
+ - ``model``: the model object to update
605
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
606
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
607
+
608
+ Returns:
609
+ - ``model`: modified model
610
+
611
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
612
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
613
+ conveniently placed for you in the checkpoint folder.
614
+
615
+ A typical usage might be ::
616
+
617
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
618
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
619
+ # submit to model hub or save the model to share with others
620
+
621
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
622
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
623
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
624
+
625
+ """
626
+ logger.info(f"Extracting fp32 weights")
627
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
628
+
629
+ logger.info(f"Overwriting model with fp32 weights")
630
+ model = model.cpu()
631
+ model.load_state_dict(state_dict, strict=False)
632
+
633
+ return model
634
+
635
+
636
+ if __name__ == "__main__":
637
+ parser = argparse.ArgumentParser()
638
+ parser.add_argument("checkpoint_dir",
639
+ type=str,
640
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
641
+ parser.add_argument("output_dir",
642
+ type=str,
643
+ help="directory to the pytorch fp32 state_dict output files"
644
+ "(e.g. path/checkpoint-12-output/)")
645
+ parser.add_argument(
646
+ "--max_shard_size",
647
+ type=str,
648
+ default="5GB",
649
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
650
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
651
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
652
+ "without CPU OOM issues.")
653
+ parser.add_argument(
654
+ "--safe_serialization",
655
+ default=False,
656
+ action='store_true',
657
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
658
+ parser.add_argument("-t",
659
+ "--tag",
660
+ type=str,
661
+ default=None,
662
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
663
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
664
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
665
+ args = parser.parse_args()
666
+
667
+ debug = args.debug
668
+
669
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
670
+ args.output_dir,
671
+ max_shard_size=args.max_shard_size,
672
+ safe_serialization=args.safe_serialization,
673
+ tag=args.tag,
674
+ exclude_frozen_parameters=args.exclude_frozen_parameters)