Hugging Face's logo

Code2Logic
/
Game-RL-LLaVA-OV-7B

Safetensors
llava_onevision
Model card Files
xet
Community
1
lkdhy commited on
Commit
92603ee
·
verified ·
1 Parent(s): 1514fb5

Upload 20 files

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +7 -0
  3. args.json +429 -0
  4. chat_template.json +3 -0
  5. config.json +198 -0
  6. generation_config.json +6 -0
  7. merges.txt +0 -0
  8. model-00001-of-00004.safetensors +3 -0
  9. model-00002-of-00004.safetensors +3 -0
  10. model-00003-of-00004.safetensors +3 -0
  11. model-00004-of-00004.safetensors +3 -0
  12. model.safetensors.index.json +772 -0
  13. preprocessor_config.json +171 -0
  14. processor_config.json +7 -0
  15. special_tokens_map.json +20 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +65 -0
  18. trainer_state.json +0 -0
  19. training_args.bin +3 -0
  20. video_processor/preprocessor_config.json +25 -0
  21. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<video>": 151647,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644
7
+ }
args.json ADDED
@@ -0,0 +1,429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/root/model/AI-ModelScope/llava-onevision-qwen2-7b-ov-hf",
3
+ "model_type": "llava_onevision_hf",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "template": "llava_onevision_hf",
15
+ "system": "Please carefully observe the image, thoroughly understand the conditions provided in the question, use logical reasoning to arrive at the result, and reflect on and verify the reasoning process to ensure the accuracy of the answer. Finally, provide the correct answer.",
16
+ "max_length": null,
17
+ "truncation_strategy": "left",
18
+ "max_pixels": null,
19
+ "tools_prompt": "react_en",
20
+ "norm_bbox": null,
21
+ "response_prefix": null,
22
+ "padding_side": "right",
23
+ "loss_scale": "last_round",
24
+ "sequence_parallel_size": 1,
25
+ "use_chat_template": true,
26
+ "template_backend": "swift",
27
+ "dataset": [
28
+ "/mnt/data/user/zhao_jun/tangjixin/sample_data/games_new_v20_5k.json"
29
+ ],
30
+ "val_dataset": [],
31
+ "split_dataset_ratio": 0.01,
32
+ "data_seed": 42,
33
+ "dataset_num_proc": 4,
34
+ "streaming": false,
35
+ "enable_cache": false,
36
+ "download_mode": "reuse_dataset_if_exists",
37
+ "columns": {},
38
+ "strict": false,
39
+ "remove_unused_columns": false,
40
+ "model_name": [
41
+ null,
42
+ null
43
+ ],
44
+ "model_author": [
45
+ null,
46
+ null
47
+ ],
48
+ "custom_dataset_info": [],
49
+ "quant_method": null,
50
+ "quant_bits": null,
51
+ "hqq_axis": null,
52
+ "bnb_4bit_compute_dtype": "bfloat16",
53
+ "bnb_4bit_quant_type": "nf4",
54
+ "bnb_4bit_use_double_quant": true,
55
+ "bnb_4bit_quant_storage": null,
56
+ "max_new_tokens": 64,
57
+ "temperature": 1.0,
58
+ "top_k": 50,
59
+ "top_p": 0.85,
60
+ "repetition_penalty": 1.0,
61
+ "num_beams": 1,
62
+ "stream": false,
63
+ "stop_words": [],
64
+ "logprobs": false,
65
+ "top_logprobs": null,
66
+ "ckpt_dir": null,
67
+ "load_dataset_config": null,
68
+ "lora_modules": [],
69
+ "tuner_backend": "peft",
70
+ "train_type": "full",
71
+ "adapters": [],
72
+ "external_plugins": [
73
+ "/mnt/data/user/zhao_jun/tangjixin/ms-swift/examples/train/grpo/plugin/plugin.py"
74
+ ],
75
+ "seed": 42,
76
+ "model_kwargs": {},
77
+ "load_args": false,
78
+ "load_data_args": false,
79
+ "use_hf": false,
80
+ "hub_token": null,
81
+ "custom_register_path": [],
82
+ "ignore_args_error": false,
83
+ "use_swift_lora": false,
84
+ "output_dir": "/mnt/data/user/zhao_jun/tangjixin/output/model/llava_ov-grpo_new_v20_5k/v8-20250330-101445",
85
+ "overwrite_output_dir": false,
86
+ "do_train": false,
87
+ "do_eval": false,
88
+ "do_predict": false,
89
+ "eval_strategy": "steps",
90
+ "prediction_loss_only": false,
91
+ "per_device_train_batch_size": 2,
92
+ "per_device_eval_batch_size": 2,
93
+ "per_gpu_train_batch_size": null,
94
+ "per_gpu_eval_batch_size": null,
95
+ "gradient_accumulation_steps": 2,
96
+ "eval_accumulation_steps": null,
97
+ "eval_delay": 0,
98
+ "torch_empty_cache_steps": null,
99
+ "learning_rate": 2e-07,
100
+ "weight_decay": 0.1,
101
+ "adam_beta1": 0.9,
102
+ "adam_beta2": 0.95,
103
+ "adam_epsilon": 1e-08,
104
+ "max_grad_norm": 1.0,
105
+ "num_train_epochs": 1.0,
106
+ "max_steps": -1,
107
+ "lr_scheduler_type": "constant_with_warmup",
108
+ "lr_scheduler_kwargs": null,
109
+ "warmup_ratio": 0.05,
110
+ "warmup_steps": 0,
111
+ "log_level": "passive",
112
+ "log_level_replica": "warning",
113
+ "log_on_each_node": true,
114
+ "logging_dir": "/mnt/data/user/zhao_jun/tangjixin/output/model/llava_ov-grpo_new_v20_5k/v8-20250330-101445/runs",
115
+ "logging_strategy": "steps",
116
+ "logging_first_step": true,
117
+ "logging_steps": 5,
118
+ "logging_nan_inf_filter": true,
119
+ "save_strategy": "steps",
120
+ "save_steps": 250.0,
121
+ "save_total_limit": -1,
122
+ "save_safetensors": true,
123
+ "save_on_each_node": false,
124
+ "save_only_model": true,
125
+ "restore_callback_states_from_checkpoint": false,
126
+ "no_cuda": false,
127
+ "use_cpu": false,
128
+ "use_mps_device": false,
129
+ "jit_mode_eval": false,
130
+ "use_ipex": false,
131
+ "bf16": true,
132
+ "fp16": false,
133
+ "fp16_opt_level": "O1",
134
+ "half_precision_backend": "auto",
135
+ "bf16_full_eval": false,
136
+ "fp16_full_eval": false,
137
+ "tf32": null,
138
+ "local_rank": 0,
139
+ "ddp_backend": null,
140
+ "tpu_num_cores": null,
141
+ "tpu_metrics_debug": false,
142
+ "debug": null,
143
+ "dataloader_drop_last": false,
144
+ "eval_steps": 250.0,
145
+ "dataloader_num_workers": 4,
146
+ "dataloader_prefetch_factor": null,
147
+ "past_index": -1,
148
+ "run_name": null,
149
+ "disable_tqdm": null,
150
+ "label_names": null,
151
+ "load_best_model_at_end": false,
152
+ "metric_for_best_model": "reward",
153
+ "greater_is_better": true,
154
+ "ignore_data_skip": false,
155
+ "fsdp": "",
156
+ "fsdp_min_num_params": 0,
157
+ "fsdp_config": null,
158
+ "fsdp_transformer_layer_cls_to_wrap": null,
159
+ "accelerator_config": {
160
+ "dispatch_batches": false
161
+ },
162
+ "deepspeed": {
163
+ "fp16": {
164
+ "enabled": "auto",
165
+ "loss_scale": 0,
166
+ "loss_scale_window": 1000,
167
+ "initial_scale_power": 16,
168
+ "hysteresis": 2,
169
+ "min_loss_scale": 1
170
+ },
171
+ "bf16": {
172
+ "enabled": "auto"
173
+ },
174
+ "zero_optimization": {
175
+ "stage": 2,
176
+ "offload_optimizer": {
177
+ "device": "none",
178
+ "pin_memory": true
179
+ },
180
+ "allgather_partitions": true,
181
+ "allgather_bucket_size": 200000000.0,
182
+ "overlap_comm": false,
183
+ "reduce_scatter": true,
184
+ "reduce_bucket_size": 200000000.0,
185
+ "contiguous_gradients": true
186
+ },
187
+ "gradient_accumulation_steps": "auto",
188
+ "gradient_clipping": "auto",
189
+ "steps_per_print": 2000,
190
+ "train_batch_size": "auto",
191
+ "train_micro_batch_size_per_gpu": "auto",
192
+ "wall_clock_breakdown": false
193
+ },
194
+ "label_smoothing_factor": 0.0,
195
+ "optim": "adamw_torch",
196
+ "optim_args": null,
197
+ "adafactor": false,
198
+ "group_by_length": false,
199
+ "length_column_name": "length",
200
+ "report_to": [
201
+ "wandb"
202
+ ],
203
+ "ddp_find_unused_parameters": null,
204
+ "ddp_bucket_cap_mb": null,
205
+ "ddp_broadcast_buffers": null,
206
+ "dataloader_pin_memory": true,
207
+ "dataloader_persistent_workers": false,
208
+ "skip_memory_metrics": true,
209
+ "use_legacy_prediction_loop": false,
210
+ "push_to_hub": false,
211
+ "resume_from_checkpoint": null,
212
+ "hub_model_id": null,
213
+ "hub_strategy": "every_save",
214
+ "hub_private_repo": null,
215
+ "hub_always_push": false,
216
+ "gradient_checkpointing": true,
217
+ "gradient_checkpointing_kwargs": null,
218
+ "include_inputs_for_metrics": false,
219
+ "include_for_metrics": [],
220
+ "eval_do_concat_batches": true,
221
+ "fp16_backend": "auto",
222
+ "evaluation_strategy": "steps",
223
+ "push_to_hub_model_id": null,
224
+ "push_to_hub_organization": null,
225
+ "push_to_hub_token": null,
226
+ "mp_parameters": "",
227
+ "auto_find_batch_size": false,
228
+ "full_determinism": false,
229
+ "torchdynamo": null,
230
+ "ray_scope": "last",
231
+ "ddp_timeout": 1800,
232
+ "torch_compile": false,
233
+ "torch_compile_backend": null,
234
+ "torch_compile_mode": null,
235
+ "dispatch_batches": null,
236
+ "split_batches": null,
237
+ "include_tokens_per_second": false,
238
+ "include_num_input_tokens_seen": false,
239
+ "neftune_noise_alpha": null,
240
+ "optim_target_modules": null,
241
+ "batch_eval_metrics": false,
242
+ "eval_on_start": false,
243
+ "use_liger_kernel": false,
244
+ "eval_use_gather_object": false,
245
+ "average_tokens_across_devices": false,
246
+ "sortish_sampler": false,
247
+ "predict_with_generate": false,
248
+ "generation_max_length": null,
249
+ "generation_num_beams": null,
250
+ "generation_config": null,
251
+ "check_model": true,
252
+ "acc_strategy": "token",
253
+ "train_sampler_random": true,
254
+ "metric_warmup_step": 0,
255
+ "fsdp_num": 1,
256
+ "acc_steps": 1,
257
+ "eval_use_evalscope": false,
258
+ "eval_datasets": [],
259
+ "eval_limit": null,
260
+ "eval_datasets_args": null,
261
+ "eval_generation_config": null,
262
+ "freeze_parameters": [
263
+ "vision_tower",
264
+ "multi_modal_projector"
265
+ ],
266
+ "freeze_parameters_ratio": 0.0,
267
+ "trainable_parameters": [],
268
+ "freeze_llm": false,
269
+ "freeze_vit": true,
270
+ "freeze_aligner": true,
271
+ "target_modules": [
272
+ "all-linear"
273
+ ],
274
+ "target_regex": null,
275
+ "modules_to_save": [],
276
+ "lora_rank": 8,
277
+ "lora_alpha": 32,
278
+ "lora_dropout": 0.05,
279
+ "lora_bias": "none",
280
+ "lora_dtype": null,
281
+ "lorap_lr_ratio": null,
282
+ "use_rslora": false,
283
+ "use_dora": false,
284
+ "lora_ga_batch_size": 2,
285
+ "lora_ga_iters": 2,
286
+ "lora_ga_max_length": 1024,
287
+ "lora_ga_direction": "ArB2r",
288
+ "lora_ga_scale": "stable",
289
+ "lora_ga_stable_gamma": 16,
290
+ "init_weights": true,
291
+ "fourier_n_frequency": 2000,
292
+ "fourier_scaling": 300.0,
293
+ "boft_block_size": 4,
294
+ "boft_block_num": 0,
295
+ "boft_n_butterfly_factor": 1,
296
+ "boft_dropout": 0.0,
297
+ "vera_rank": 256,
298
+ "vera_projection_prng_key": 0,
299
+ "vera_dropout": 0.0,
300
+ "vera_d_initial": 0.1,
301
+ "adapter_act": "gelu",
302
+ "adapter_length": 128,
303
+ "use_galore": false,
304
+ "galore_target_modules": null,
305
+ "galore_rank": 128,
306
+ "galore_update_proj_gap": 50,
307
+ "galore_scale": 1.0,
308
+ "galore_proj_type": "std",
309
+ "galore_optim_per_parameter": false,
310
+ "galore_with_embedding": false,
311
+ "galore_quantization": false,
312
+ "galore_proj_quant": false,
313
+ "galore_proj_bits": 4,
314
+ "galore_proj_group_size": 256,
315
+ "galore_cos_threshold": 0.4,
316
+ "galore_gamma_proj": 2,
317
+ "galore_queue_size": 5,
318
+ "adalora_target_r": 8,
319
+ "adalora_init_r": 12,
320
+ "adalora_tinit": 0,
321
+ "adalora_tfinal": 0,
322
+ "adalora_deltaT": 1,
323
+ "adalora_beta1": 0.85,
324
+ "adalora_beta2": 0.85,
325
+ "adalora_orth_reg_weight": 0.5,
326
+ "llamapro_num_new_blocks": 4,
327
+ "llamapro_num_groups": null,
328
+ "lisa_activated_layers": 0,
329
+ "lisa_step_interval": 20,
330
+ "reft_layer_key": null,
331
+ "reft_layers": null,
332
+ "reft_rank": 4,
333
+ "reft_intervention_type": "LoreftIntervention",
334
+ "reft_args": null,
335
+ "use_liger": false,
336
+ "swanlab_token": null,
337
+ "swanlab_project": null,
338
+ "swanlab_workspace": null,
339
+ "swanlab_exp_name": null,
340
+ "swanlab_mode": "cloud",
341
+ "add_version": true,
342
+ "resume_only_model": false,
343
+ "create_checkpoint_symlink": false,
344
+ "packing": false,
345
+ "lazy_tokenize": true,
346
+ "loss_type": null,
347
+ "optimizer": null,
348
+ "metric": null,
349
+ "zero_hpz_partition_size": null,
350
+ "reward_model": null,
351
+ "reward_adapters": [],
352
+ "reward_model_type": null,
353
+ "reward_model_revision": null,
354
+ "num_ppo_epochs": 4,
355
+ "whiten_rewards": false,
356
+ "kl_coef": 0.05,
357
+ "cliprange": 0.2,
358
+ "vf_coef": 0.1,
359
+ "cliprange_value": 0.2,
360
+ "gamma": 1.0,
361
+ "lam": 0.95,
362
+ "num_mini_batches": 1,
363
+ "local_rollout_forward_batch_size": 64,
364
+ "num_sample_generations": 10,
365
+ "response_length": 512,
366
+ "missing_eos_penalty": null,
367
+ "epsilon": 0.2,
368
+ "epsilon_high": null,
369
+ "num_infer_workers": 2,
370
+ "vllm_max_num_seqs": 256,
371
+ "vllm_enforce_eager": false,
372
+ "vllm_limit_mm_per_prompt": null,
373
+ "vllm_enable_prefix_caching": true,
374
+ "cosine_min_len_value_wrong": -0.5,
375
+ "cosine_max_len_value_wrong": 0.0,
376
+ "cosine_min_len_value_correct": 1.0,
377
+ "cosine_max_len_value_correct": 0.5,
378
+ "cosine_max_len": null,
379
+ "repetition_n_grams": 3,
380
+ "repetition_max_penalty": -1.0,
381
+ "use_lmdeploy": false,
382
+ "lmdeploy_device": "auto",
383
+ "lmdeploy_session_len": null,
384
+ "lmdeploy_cache_max_entry_count": 0.8,
385
+ "async_generate": true,
386
+ "tensor_parallel_size": 1,
387
+ "sleep_level": 0,
388
+ "move_model_batches": null,
389
+ "offload_optimizer": false,
390
+ "offload_model": false,
391
+ "gc_collect_after_offload": false,
392
+ "multi_turn_func": null,
393
+ "mini_batch_size": null,
394
+ "num_generations": 12,
395
+ "max_completion_length": 2048,
396
+ "ds3_gather_for_generation": true,
397
+ "reward_funcs": [
398
+ "external_r1v_acc"
399
+ ],
400
+ "reward_weights": null,
401
+ "log_completions": true,
402
+ "use_vllm": true,
403
+ "vllm_device": [
404
+ "auto"
405
+ ],
406
+ "vllm_gpu_memory_utilization": 0.5,
407
+ "vllm_max_model_len": 8192,
408
+ "num_iterations": 1,
409
+ "rlhf_type": "grpo",
410
+ "ref_model": "/root/model/AI-ModelScope/llava-onevision-qwen2-7b-ov-hf",
411
+ "ref_model_type": "llava_onevision_hf",
412
+ "ref_model_revision": null,
413
+ "beta": 0.04,
414
+ "label_smoothing": 0,
415
+ "rpo_alpha": 1.0,
416
+ "cpo_alpha": 1.0,
417
+ "simpo_gamma": 1,
418
+ "desirable_weight": 1.0,
419
+ "undesirable_weight": 1.0,
420
+ "rank": 0,
421
+ "global_world_size": 6,
422
+ "local_world_size": 6,
423
+ "model_suffix": "llava-onevision-qwen2-7b-ov-hf",
424
+ "model_info": "ModelInfo(model_type='llava_onevision_hf', model_dir='/root/model/AI-ModelScope/llava-onevision-qwen2-7b-ov-hf', torch_dtype=torch.bfloat16, max_model_len=None, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
425
+ "model_meta": "ModelMeta(model_type='llava_onevision_hf', model_groups=[ModelGroup(models=[Model(ms_model_id='llava-hf/llava-onevision-qwen2-0.5b-ov-hf', hf_model_id='llava-hf/llava-onevision-qwen2-0.5b-ov-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='llava-hf/llava-onevision-qwen2-7b-ov-hf', hf_model_id='llava-hf/llava-onevision-qwen2-7b-ov-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='llava-hf/llava-onevision-qwen2-72b-ov-hf', hf_model_id='llava-hf/llava-onevision-qwen2-72b-ov-hf', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='llava_onevision_hf', get_function=<function get_model_tokenizer_llava_onevision at 0x7f7163999360>, model_arch='llava_hf', architectures=['LlavaOnevisionForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=['*.zip', '*.gguf', '*.pth', '*.pt', 'consolidated*', 'onnx/*', '*.safetensors.md', '*.msgpack', '*.onnx', '*.ot', '*.h5', '*.bin', '*.safetensors'], requires=['transformers>=4.45'], tags=[])",
426
+ "model_dir": "/root/model/AI-ModelScope/llava-onevision-qwen2-7b-ov-hf",
427
+ "hub": "<class 'swift.hub.hub.MSHub'>",
428
+ "training_args": "GRPOConfig(output_dir='/mnt/data/user/zhao_jun/tangjixin/output/model/llava_ov-grpo_new_v20_5k/v8-20250330-101445', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-07, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.CONSTANT_WITH_WARMUP: 'constant_with_warmup'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/user/zhao_jun/tangjixin/output/model/llava_ov-grpo_new_v20_5k/v8-20250330-101445/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=250, save_total_limit=-1, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=250, dataloader_num_workers=4, dataloader_prefetch_factor=None, past_index=-1, run_name='/mnt/data/user/zhao_jun/tangjixin/output/model/llava_ov-grpo_new_v20_5k/v8-20250330-101445', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, max_prompt_length=512, num_generations=12, temperature=1.0, max_completion_length=2048, ds3_gather_for_generation=True, use_vllm=True, vllm_device=['auto'], vllm_gpu_memory_utilization=0.5, vllm_dtype='auto', vllm_max_model_len=8192, vllm_enable_prefix_caching=True, vllm_guided_decoding_regex=None, beta=0.04, num_iterations=1, epsilon=0.2, reward_weights=None, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, log_completions=True, check_model=True, acc_strategy='token', train_sampler_random=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None, epsilon_high=None, top_k=50, top_p=0.85, repetition_penalty=1.0, num_infer_workers=2, vllm_max_num_seqs=256, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=2048, repetition_n_grams=3, repetition_max_penalty=-1.0, use_lmdeploy=False, lmdeploy_device='auto', lmdeploy_session_len=None, lmdeploy_cache_max_entry_count=0.8, async_generate=True, tensor_parallel_size=1, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, gc_collect_after_offload=False, multi_turn_func=None, mini_batch_size=None, stop_words=[])"
429
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + ' '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '\n' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '\n' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/model/AI-ModelScope/llava-onevision-qwen2-7b-ov-hf",
3
+ "architectures": [
4
+ "LlavaOnevisionForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 3584,
7
+ "ignore_index": -100,
8
+ "image_grid_pinpoints": [
9
+ [
10
+ 384,
11
+ 384
12
+ ],
13
+ [
14
+ 384,
15
+ 768
16
+ ],
17
+ [
18
+ 384,
19
+ 1152
20
+ ],
21
+ [
22
+ 384,
23
+ 1536
24
+ ],
25
+ [
26
+ 384,
27
+ 1920
28
+ ],
29
+ [
30
+ 384,
31
+ 2304
32
+ ],
33
+ [
34
+ 768,
35
+ 384
36
+ ],
37
+ [
38
+ 768,
39
+ 768
40
+ ],
41
+ [
42
+ 768,
43
+ 1152
44
+ ],
45
+ [
46
+ 768,
47
+ 1536
48
+ ],
49
+ [
50
+ 768,
51
+ 1920
52
+ ],
53
+ [
54
+ 768,
55
+ 2304
56
+ ],
57
+ [
58
+ 1152,
59
+ 384
60
+ ],
61
+ [
62
+ 1152,
63
+ 768
64
+ ],
65
+ [
66
+ 1152,
67
+ 1152
68
+ ],
69
+ [
70
+ 1152,
71
+ 1536
72
+ ],
73
+ [
74
+ 1152,
75
+ 1920
76
+ ],
77
+ [
78
+ 1152,
79
+ 2304
80
+ ],
81
+ [
82
+ 1536,
83
+ 384
84
+ ],
85
+ [
86
+ 1536,
87
+ 768
88
+ ],
89
+ [
90
+ 1536,
91
+ 1152
92
+ ],
93
+ [
94
+ 1536,
95
+ 1536
96
+ ],
97
+ [
98
+ 1536,
99
+ 1920
100
+ ],
101
+ [
102
+ 1536,
103
+ 2304
104
+ ],
105
+ [
106
+ 1920,
107
+ 384
108
+ ],
109
+ [
110
+ 1920,
111
+ 768
112
+ ],
113
+ [
114
+ 1920,
115
+ 1152
116
+ ],
117
+ [
118
+ 1920,
119
+ 1536
120
+ ],
121
+ [
122
+ 1920,
123
+ 1920
124
+ ],
125
+ [
126
+ 1920,
127
+ 2304
128
+ ],
129
+ [
130
+ 2304,
131
+ 384
132
+ ],
133
+ [
134
+ 2304,
135
+ 768
136
+ ],
137
+ [
138
+ 2304,
139
+ 1152
140
+ ],
141
+ [
142
+ 2304,
143
+ 1536
144
+ ],
145
+ [
146
+ 2304,
147
+ 1920
148
+ ],
149
+ [
150
+ 2304,
151
+ 2304
152
+ ]
153
+ ],
154
+ "image_token_index": 151646,
155
+ "keys_to_ignore_at_inference": [
156
+ "past_key_values"
157
+ ],
158
+ "model_type": "llava_onevision",
159
+ "multimodal_projector_bias": true,
160
+ "pad_token_id": 151643,
161
+ "projector_hidden_act": "gelu",
162
+ "text_config": {
163
+ "_name_or_path": "Qwen/Qwen2-7B-Instruct",
164
+ "architectures": [
165
+ "Qwen2ForCausalLM"
166
+ ],
167
+ "bos_token_id": 151643,
168
+ "eos_token_id": 151645,
169
+ "hidden_size": 3584,
170
+ "intermediate_size": 18944,
171
+ "model_type": "qwen2",
172
+ "num_attention_heads": 28,
173
+ "num_hidden_layers": 28,
174
+ "num_key_value_heads": 4,
175
+ "rope_theta": 1000000.0,
176
+ "torch_dtype": "bfloat16",
177
+ "vocab_size": 152128
178
+ },
179
+ "tie_word_embeddings": false,
180
+ "torch_dtype": "bfloat16",
181
+ "transformers_version": "4.48.2",
182
+ "use_image_newline_parameter": true,
183
+ "video_token_index": 151647,
184
+ "vision_aspect_ratio": "anyres_max_9",
185
+ "vision_config": {
186
+ "hidden_size": 1152,
187
+ "image_size": 384,
188
+ "intermediate_size": 4304,
189
+ "model_type": "siglip_vision_model",
190
+ "num_attention_heads": 16,
191
+ "num_hidden_layers": 26,
192
+ "patch_size": 14,
193
+ "torch_dtype": "bfloat16",
194
+ "vision_use_head": false
195
+ },
196
+ "vision_feature_layer": -1,
197
+ "vision_feature_select_strategy": "full"
198
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.48.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc67875ffb98f24176c3eab359aa235f9d77ad07827d927353f721c6aa052789
3
+ size 4911200872
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ced7a6f1dc8f45c27e25315e61ff375c90ab678c369137d5122c4f402d47f9
3
+ size 4991497792
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2c2f91c09f9a3da028cac36f808aa98f20574b5376fdda80597b98e8cf49b5
3
+ size 4932752872
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf818d379b842748484f0c552f1d315302150a37093632684b4ea890cd82a2c0
3
+ size 1226266248
model.safetensors.index.json ADDED
@@ -0,0 +1,772 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16061615168
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model-00001-of-00004.safetensors",
7
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
347
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
348
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
349
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
350
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
351
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
352
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
353
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
354
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
355
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
356
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
357
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
358
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
359
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
360
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
361
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
362
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
363
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
364
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
365
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
366
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
367
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
368
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
369
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
370
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
371
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
372
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
380
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
381
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
382
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
383
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
386
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
387
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
388
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
389
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
394
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
395
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
396
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
397
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
400
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
401
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
402
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
403
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
404
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
405
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
406
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
407
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
408
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
409
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
410
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
411
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
414
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
415
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
416
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
417
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
428
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
429
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
430
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
431
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
432
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
433
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
434
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
435
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
436
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
437
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
438
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
439
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
440
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
441
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
442
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
443
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
444
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
445
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
446
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
447
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
448
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
449
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
454
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
455
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
769
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
770
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
771
+ }
772
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 384,
10
+ 384
11
+ ],
12
+ [
13
+ 384,
14
+ 768
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 384,
22
+ 1536
23
+ ],
24
+ [
25
+ 384,
26
+ 1920
27
+ ],
28
+ [
29
+ 384,
30
+ 2304
31
+ ],
32
+ [
33
+ 768,
34
+ 384
35
+ ],
36
+ [
37
+ 768,
38
+ 768
39
+ ],
40
+ [
41
+ 768,
42
+ 1152
43
+ ],
44
+ [
45
+ 768,
46
+ 1536
47
+ ],
48
+ [
49
+ 768,
50
+ 1920
51
+ ],
52
+ [
53
+ 768,
54
+ 2304
55
+ ],
56
+ [
57
+ 1152,
58
+ 384
59
+ ],
60
+ [
61
+ 1152,
62
+ 768
63
+ ],
64
+ [
65
+ 1152,
66
+ 1152
67
+ ],
68
+ [
69
+ 1152,
70
+ 1536
71
+ ],
72
+ [
73
+ 1152,
74
+ 1920
75
+ ],
76
+ [
77
+ 1152,
78
+ 2304
79
+ ],
80
+ [
81
+ 1536,
82
+ 384
83
+ ],
84
+ [
85
+ 1536,
86
+ 768
87
+ ],
88
+ [
89
+ 1536,
90
+ 1152
91
+ ],
92
+ [
93
+ 1536,
94
+ 1536
95
+ ],
96
+ [
97
+ 1536,
98
+ 1920
99
+ ],
100
+ [
101
+ 1536,
102
+ 2304
103
+ ],
104
+ [
105
+ 1920,
106
+ 384
107
+ ],
108
+ [
109
+ 1920,
110
+ 768
111
+ ],
112
+ [
113
+ 1920,
114
+ 1152
115
+ ],
116
+ [
117
+ 1920,
118
+ 1536
119
+ ],
120
+ [
121
+ 1920,
122
+ 1920
123
+ ],
124
+ [
125
+ 1920,
126
+ 2304
127
+ ],
128
+ [
129
+ 2304,
130
+ 384
131
+ ],
132
+ [
133
+ 2304,
134
+ 768
135
+ ],
136
+ [
137
+ 2304,
138
+ 1152
139
+ ],
140
+ [
141
+ 2304,
142
+ 1536
143
+ ],
144
+ [
145
+ 2304,
146
+ 1920
147
+ ],
148
+ [
149
+ 2304,
150
+ 2304
151
+ ]
152
+ ],
153
+ "image_mean": [
154
+ 0.5,
155
+ 0.5,
156
+ 0.5
157
+ ],
158
+ "image_processor_type": "LlavaOnevisionImageProcessor",
159
+ "image_std": [
160
+ 0.5,
161
+ 0.5,
162
+ 0.5
163
+ ],
164
+ "processor_class": "LlavaOnevisionProcessor",
165
+ "resample": 3,
166
+ "rescale_factor": 0.00392156862745098,
167
+ "size": {
168
+ "height": 384,
169
+ "width": 384
170
+ }
171
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "num_image_tokens": 729,
4
+ "processor_class": "LlavaOnevisionProcessor",
5
+ "video_token": "<video>",
6
+ "vision_feature_select_strategy": "full"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09f1889210ae8f16539761f6a6d645641eb8e583d22c6f36c92d253e247887f
3
+ size 11418634
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<video>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "<|im_start|>",
47
+ "<|im_end|>"
48
+ ],
49
+ "bos_token": null,
50
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
51
+ "clean_up_tokenization_spaces": false,
52
+ "eos_token": "<|im_end|>",
53
+ "errors": "replace",
54
+ "extra_special_tokens": {},
55
+ "max_length": null,
56
+ "model_max_length": 131072,
57
+ "pad_to_multiple_of": null,
58
+ "pad_token": "<|endoftext|>",
59
+ "pad_token_type_id": 0,
60
+ "padding_side": "right",
61
+ "processor_class": "LlavaOnevisionProcessor",
62
+ "split_special_tokens": false,
63
+ "tokenizer_class": "Qwen2Tokenizer",
64
+ "unk_token": null
65
+ }
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:fbbf597bc0c1bd7e36a7d1f8f77ce149538a0ada6ab10055394805a4a74ed728
3
+ size 9272
video_processor/preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LlavaOnevisionVideoProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "LlavaOnevisionProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 384,
23
+ "width": 384
24
+ }
25
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff