U4R
/

Safetensors
chimera
custom_code
File size: 15,866 Bytes
56b87c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
{
  "_commit_hash": null,
  "_name_or_path": "/mnt/workspace/Chimera/checkpoints/solva-reasoner-2B",
  "architectures": [
    "ChimeraChatModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_chimera.ChimeraChatConfig",
    "AutoModel": "modeling_chimera.ChimeraChatModel",
    "AutoModelForCausalLM": "modeling_chimera.ChimeraChatModel"
  },
  "downsample_ratio": 0.5,
  "dynamic_image_size": true,
  "expert_encoder_config": {
    "_attn_implementation_internal": null,
    "_commit_hash": null,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "config_list": [
      {
        "config": {
          "_name_or_path": "/cpfs01/shared/ADLab/datasets/science_dataset/solva_modules/table_kosmos",
          "add_cross_attention": false,
          "architectures": [
            "Kosmos2_5VisionModel"
          ],
          "attention_dropout": 0.0,
          "bad_words_ids": null,
          "begin_suppress_tokens": null,
          "bos_token_id": null,
          "chunk_size_feed_forward": 0,
          "cross_attention_hidden_size": null,
          "d_ff": 3968,
          "d_kv": 64,
          "decoder_start_token_id": null,
          "dense_act_fn": "gelu_new",
          "diversity_penalty": 0.0,
          "do_sample": false,
          "dropout_rate": 0.0,
          "early_stopping": false,
          "encoder_no_repeat_ngram_size": 0,
          "eos_token_id": null,
          "exponential_decay_length_penalty": null,
          "finetuning_task": null,
          "forced_bos_token_id": null,
          "forced_eos_token_id": null,
          "hidden_size": 1536,
          "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
          },
          "initializer_factor": 1.0,
          "initializer_range": 1e-10,
          "is_decoder": false,
          "is_encoder_decoder": false,
          "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
          },
          "layer_norm_eps": 1e-06,
          "length_penalty": 1.0,
          "max_length": 4096,
          "min_length": 0,
          "model_type": "kosmos_2_5_vision_model",
          "no_repeat_ngram_size": 0,
          "num_attention_heads": 24,
          "num_beam_groups": 1,
          "num_beams": 1,
          "num_hidden_layers": 18,
          "num_return_sequences": 1,
          "output_attentions": false,
          "output_hidden_states": false,
          "output_scores": false,
          "pad_token_id": null,
          "patch_embed_hidden_size": 768,
          "prefix": null,
          "problem_type": null,
          "pruned_heads": {},
          "remove_invalid_values": false,
          "repetition_penalty": 1.0,
          "return_dict": true,
          "return_dict_in_generate": false,
          "sep_token_id": null,
          "seq_len": 4096,
          "suppress_tokens": null,
          "task_specific_params": null,
          "temperature": 1.0,
          "tf_legacy_loss": false,
          "tie_encoder_decoder": false,
          "tie_word_embeddings": true,
          "tokenizer_class": null,
          "top_k": 50,
          "top_p": 1.0,
          "torch_dtype": "float32",
          "torchscript": false,
          "transformers_version": "4.44.2",
          "typical_p": 1.0,
          "use_bfloat16": false
        },
        "domain": "table",
        "index": 0,
        "select_layer": -1
      },
      {
        "config": {
          "_name_or_path": "/cpfs01/shared/ADLab/datasets/science_dataset/solva_modules/math_clip",
          "add_cross_attention": false,
          "architectures": null,
          "attention_dropout": 0.0,
          "bad_words_ids": null,
          "begin_suppress_tokens": null,
          "bos_token_id": null,
          "chunk_size_feed_forward": 0,
          "cross_attention_hidden_size": null,
          "decoder_start_token_id": null,
          "diversity_penalty": 0.0,
          "do_sample": false,
          "dropout": 0.0,
          "early_stopping": false,
          "encoder_no_repeat_ngram_size": 0,
          "eos_token_id": null,
          "exponential_decay_length_penalty": null,
          "finetuning_task": null,
          "forced_bos_token_id": null,
          "forced_eos_token_id": null,
          "hidden_act": "quick_gelu",
          "hidden_size": 1024,
          "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
          },
          "image_size": 336,
          "initializer_factor": 1.0,
          "initializer_range": 0.02,
          "intermediate_size": 4096,
          "is_decoder": false,
          "is_encoder_decoder": false,
          "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
          },
          "layer_norm_eps": 1e-05,
          "length_penalty": 1.0,
          "max_length": 20,
          "min_length": 0,
          "model_type": "clip_vision_model",
          "no_repeat_ngram_size": 0,
          "num_attention_heads": 16,
          "num_beam_groups": 1,
          "num_beams": 1,
          "num_channels": 3,
          "num_hidden_layers": 24,
          "num_return_sequences": 1,
          "output_attentions": false,
          "output_hidden_states": false,
          "output_scores": false,
          "pad_token_id": null,
          "patch_size": 14,
          "prefix": null,
          "problem_type": null,
          "projection_dim": 768,
          "pruned_heads": {},
          "remove_invalid_values": false,
          "repetition_penalty": 1.0,
          "return_dict": true,
          "return_dict_in_generate": false,
          "sep_token_id": null,
          "suppress_tokens": null,
          "task_specific_params": null,
          "temperature": 1.0,
          "tf_legacy_loss": false,
          "tie_encoder_decoder": false,
          "tie_word_embeddings": true,
          "tokenizer_class": null,
          "top_k": 50,
          "top_p": 1.0,
          "torch_dtype": null,
          "torchscript": false,
          "transformers_version": "4.44.2",
          "typical_p": 1.0,
          "use_bfloat16": false
        },
        "domain": "math",
        "index": 1,
        "select_layer": -2
      },
      {
        "config": {
          "_name_or_path": "/cpfs01/shared/ADLab/datasets/science_dataset/solva_modules/chart_p2s",
          "add_cross_attention": false,
          "architectures": [
            "Pix2StructVisionModel"
          ],
          "attention_dropout": 0.0,
          "bad_words_ids": null,
          "begin_suppress_tokens": null,
          "bos_token_id": null,
          "chunk_size_feed_forward": 0,
          "cross_attention_hidden_size": null,
          "d_ff": 3968,
          "d_kv": 64,
          "decoder_start_token_id": null,
          "dense_act_fn": "gelu_new",
          "diversity_penalty": 0.0,
          "do_sample": false,
          "dropout_rate": 0.0,
          "early_stopping": false,
          "encoder_no_repeat_ngram_size": 0,
          "eos_token_id": null,
          "exponential_decay_length_penalty": null,
          "finetuning_task": null,
          "forced_bos_token_id": null,
          "forced_eos_token_id": null,
          "hidden_size": 1536,
          "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
          },
          "initializer_factor": 1.0,
          "initializer_range": 0.02,
          "is_decoder": false,
          "is_encoder_decoder": false,
          "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
          },
          "layer_norm_bias": false,
          "layer_norm_eps": 1e-06,
          "length_penalty": 1.0,
          "max_length": 20,
          "min_length": 0,
          "model_type": "pix2struct_vision_model",
          "no_repeat_ngram_size": 0,
          "num_attention_heads": 24,
          "num_beam_groups": 1,
          "num_beams": 1,
          "num_channels": 3,
          "num_hidden_layers": 18,
          "num_return_sequences": 1,
          "output_attentions": false,
          "output_hidden_states": false,
          "output_scores": false,
          "pad_token_id": null,
          "patch_embed_hidden_size": 768,
          "patch_size": 16,
          "prefix": null,
          "problem_type": null,
          "projection_dim": 768,
          "pruned_heads": {},
          "relative_attention_max_distance": 128,
          "relative_attention_num_buckets": 32,
          "remove_invalid_values": false,
          "repetition_penalty": 1.0,
          "return_dict": true,
          "return_dict_in_generate": false,
          "sep_token_id": null,
          "seq_len": 4096,
          "suppress_tokens": null,
          "task_specific_params": null,
          "temperature": 1.0,
          "tf_legacy_loss": false,
          "tie_encoder_decoder": false,
          "tie_word_embeddings": true,
          "tokenizer_class": null,
          "top_k": 50,
          "top_p": 1.0,
          "torch_dtype": "float32",
          "torchscript": false,
          "transformers_version": "4.44.2",
          "typical_p": 1.0,
          "use_bfloat16": false
        },
        "domain": "chart",
        "index": 2,
        "select_layer": -1
      }
    ],
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "llm_hidden_size": 2048,
    "max_length": 20,
    "min_length": 0,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_encoder": 3,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "separate_load": false,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": null,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "force_image_size": 448,
  "llm_config": {
    "_name_or_path": "internlm/internlm2-chat-1_8b",
    "add_cross_attention": false,
    "architectures": [
      "InternLM2ForCausalLM"
    ],
    "attn_implementation": "flash_attention_2",
    "auto_map": {
      "AutoConfig": "configuration_internlm2.InternLM2Config",
      "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
      "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
    },
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bias": false,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 32768,
    "min_length": 0,
    "model_type": "internlm2",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 24,
    "num_key_value_heads": 8,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 2,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 2.0,
      "type": "dynamic"
    },
    "rope_theta": 1000000,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "transformers_version": "4.44.2",
    "typical_p": 1.0,
    "use_bfloat16": true,
    "use_cache": false,
    "vocab_size": 92558
  },
  "max_dynamic_patch": 6,
  "min_dynamic_patch": 1,
  "model_type": "chimera",
  "pad2square": false,
  "ps_version": "v2",
  "select_layer": -1,
  "template": "solva-chat",
  "torch_dtype": "bfloat16",
  "transformers_version": null,
  "use_backbone_lora": 0,
  "use_llm_lora": 0,
  "use_thumbnail": true,
  "vision_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "InternVisionModel"
    ],
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_path_rate": 0.1,
    "dropout": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 448,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "intern_vit_6b",
    "no_repeat_ngram_size": 0,
    "norm_type": "layer_norm",
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 14,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "qk_normalization": false,
    "qkv_bias": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "transformers_version": "4.44.2",
    "typical_p": 1.0,
    "use_bfloat16": true,
    "use_flash_attn": true
  }
}