Hugging Face's logo

p1k0
/
mmmt_model

Safetensors
Model card Files
xet
Community
p1k0 commited on
Commit
b2784b0
·
verified ·
1 Parent(s): 4fa3c9c

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/README.md +67 -0
  3. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/args.json +505 -0
  4. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/added_tokens.json +24 -0
  5. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/args.json +505 -0
  6. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/chat_template.jinja +7 -0
  7. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/config.json +138 -0
  8. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/generation_config.json +12 -0
  9. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/latest +1 -0
  10. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/merges.txt +0 -0
  11. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/model.safetensors.index.json +737 -0
  12. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/preprocessor_config.json +19 -0
  13. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/special_tokens_map.json +31 -0
  14. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/tokenizer_config.json +208 -0
  15. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/trainer_state.json +0 -0
  16. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/video_preprocessor_config.json +43 -0
  17. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/vocab.json +0 -0
  18. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/zero_to_fp32.py +760 -0
  19. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/completions.jsonl +3 -0
  20. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/logging.jsonl +0 -0
  21. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/README.md +67 -0
  22. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/args.json +505 -0
  23. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/added_tokens.json +24 -0
  24. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/args.json +505 -0
  25. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/chat_template.jinja +7 -0
  26. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/config.json +138 -0
  27. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/generation_config.json +12 -0
  28. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/latest +1 -0
  29. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/merges.txt +0 -0
  30. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/model.safetensors.index.json +737 -0
  31. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/preprocessor_config.json +19 -0
  32. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/special_tokens_map.json +31 -0
  33. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/tokenizer_config.json +208 -0
  34. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/trainer_state.json +0 -0
  35. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/completions.jsonl +0 -0
  36. grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/logging.jsonl +0 -0
  37. grpo/qwen2.5vl-7b-τ-checkpoint-1250/added_tokens.json +24 -0
  38. grpo/qwen2.5vl-7b-τ-checkpoint-1250/args.json +507 -0
  39. grpo/qwen2.5vl-7b-τ-checkpoint-1250/chat_template.jinja +7 -0
  40. grpo/qwen2.5vl-7b-τ-checkpoint-1250/config.json +138 -0
  41. grpo/qwen2.5vl-7b-τ-checkpoint-1250/generation_config.json +12 -0
  42. grpo/qwen2.5vl-7b-τ-checkpoint-1250/latest +1 -0
  43. grpo/qwen2.5vl-7b-τ-checkpoint-1250/merges.txt +0 -0
  44. grpo/qwen2.5vl-7b-τ-checkpoint-1250/model.safetensors.index.json +737 -0
  45. grpo/qwen2.5vl-7b-τ-checkpoint-1250/preprocessor_config.json +19 -0
  46. grpo/qwen2.5vl-7b-τ-checkpoint-1250/special_tokens_map.json +31 -0
  47. grpo/qwen2.5vl-7b-τ-checkpoint-1250/tokenizer_config.json +208 -0
  48. grpo/qwen2.5vl-7b-τ-checkpoint-1250/trainer_state.json +0 -0
  49. grpo/qwen2.5vl-7b-τ-checkpoint-1250/video_preprocessor_config.json +43 -0
  50. grpo/qwen2.5vl-7b-τ-checkpoint-1250/vocab.json +0 -0
.gitattributes CHANGED
@@ -43,3 +43,4 @@ qwen2.5vl-7b-thinking_v2_full_cls_grpo/v0-20250912-102404/checkpoint-1250/tokeni
43
  qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/completions.jsonl filter=lfs diff=lfs merge=lfs -text
44
  qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
  baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
43
  qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/completions.jsonl filter=lfs diff=lfs merge=lfs -text
44
  qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
  baseline/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/completions.jsonl filter=lfs diff=lfs merge=lfs -text
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: v13-20250907-200700
4
+ tags:
5
+ - generated_from_trainer
6
+ - grpo
7
+ - trl
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for v13-20250907-200700
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
22
+ generator = pipeline("text-generation", model="None", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+
30
+
31
+
32
+ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
33
+
34
+ ### Framework versions
35
+
36
+ - TRL: 0.20.0
37
+ - Transformers: 4.55.4
38
+ - Pytorch: 2.7.1
39
+ - Datasets: 3.6.0
40
+ - Tokenizers: 0.21.4
41
+
42
+ ## Citations
43
+
44
+ Cite GRPO as:
45
+
46
+ ```bibtex
47
+ @article{zhihong2024deepseekmath,
48
+ title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
49
+ author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
50
+ year = 2024,
51
+ eprint = {arXiv:2402.03300},
52
+ }
53
+
54
+ ```
55
+
56
+ Cite TRL as:
57
+
58
+ ```bibtex
59
+ @misc{vonwerra2022trl,
60
+ title = {{TRL: Transformer Reinforcement Learning}},
61
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
62
+ year = 2020,
63
+ journal = {GitHub repository},
64
+ publisher = {GitHub},
65
+ howpublished = {\url{https://github.com/huggingface/trl}}
66
+ }
67
+ ```
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/args.json ADDED
@@ -0,0 +1,505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.01,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 100.0,
39
+ "save_total_limit": 10,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 200.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": false,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "swanlab"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": false,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "enable_channel_loss": false,
186
+ "check_model": true,
187
+ "acc_strategy": "token",
188
+ "train_dataloader_shuffle": true,
189
+ "max_epochs": null,
190
+ "aligner_lr": null,
191
+ "vit_lr": null,
192
+ "use_logits_to_keep": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": "grpo",
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
206
+ "model_type": "qwen2_5_vl",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5_vl",
221
+ "system": null,
222
+ "max_length": 128000,
223
+ "truncation_strategy": "left",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "last_round",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/train_base.jsonl"
236
+ ],
237
+ "val_dataset": [
238
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/test_base_02.jsonl"
239
+ ],
240
+ "split_dataset_ratio": 0.0,
241
+ "dataset_num_proc": 1,
242
+ "load_from_cache_file": true,
243
+ "dataset_shuffle": true,
244
+ "val_dataset_shuffle": false,
245
+ "streaming": false,
246
+ "interleave_prob": null,
247
+ "stopping_strategy": "first_exhausted",
248
+ "shuffle_buffer_size": 1000,
249
+ "download_mode": "reuse_dataset_if_exists",
250
+ "columns": {},
251
+ "strict": false,
252
+ "model_name": null,
253
+ "model_author": null,
254
+ "custom_dataset_info": [],
255
+ "quant_method": null,
256
+ "quant_bits": null,
257
+ "hqq_axis": null,
258
+ "bnb_4bit_compute_dtype": "bfloat16",
259
+ "bnb_4bit_quant_type": "nf4",
260
+ "bnb_4bit_use_double_quant": true,
261
+ "bnb_4bit_quant_storage": null,
262
+ "max_new_tokens": 1024,
263
+ "temperature": 1.0,
264
+ "top_k": 50,
265
+ "top_p": 0.9,
266
+ "repetition_penalty": 1.0,
267
+ "num_beams": 1,
268
+ "stream": false,
269
+ "stop_words": [],
270
+ "logprobs": false,
271
+ "top_logprobs": null,
272
+ "ckpt_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
273
+ "lora_modules": [],
274
+ "train_type": "full",
275
+ "adapters": [],
276
+ "external_plugins": [
277
+ "examples/train/grpo/plugin/plugin.py"
278
+ ],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": true,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [
291
+ "model.visual",
292
+ "model.visual.merger"
293
+ ],
294
+ "freeze_parameters_regex": null,
295
+ "freeze_parameters_ratio": 0.0,
296
+ "trainable_parameters": [],
297
+ "trainable_parameters_regex": null,
298
+ "freeze_llm": false,
299
+ "freeze_vit": true,
300
+ "freeze_aligner": true,
301
+ "target_modules": [
302
+ "all-linear"
303
+ ],
304
+ "target_regex": null,
305
+ "target_parameters": null,
306
+ "modules_to_save": [],
307
+ "lora_rank": 8,
308
+ "lora_alpha": 32,
309
+ "lora_dropout": 0.05,
310
+ "lora_bias": "none",
311
+ "lora_dtype": null,
312
+ "lorap_lr_ratio": null,
313
+ "use_rslora": false,
314
+ "use_dora": false,
315
+ "lora_ga_batch_size": 2,
316
+ "lora_ga_iters": 2,
317
+ "lora_ga_max_length": 1024,
318
+ "lora_ga_direction": "ArB2r",
319
+ "lora_ga_scale": "stable",
320
+ "lora_ga_stable_gamma": 16,
321
+ "init_weights": true,
322
+ "fourier_n_frequency": 2000,
323
+ "fourier_scaling": 300.0,
324
+ "boft_block_size": 4,
325
+ "boft_block_num": 0,
326
+ "boft_n_butterfly_factor": 1,
327
+ "boft_dropout": 0.0,
328
+ "vera_rank": 256,
329
+ "vera_projection_prng_key": 0,
330
+ "vera_dropout": 0.0,
331
+ "vera_d_initial": 0.1,
332
+ "adapter_act": "gelu",
333
+ "adapter_length": 128,
334
+ "use_galore": false,
335
+ "galore_target_modules": null,
336
+ "galore_rank": 128,
337
+ "galore_update_proj_gap": 50,
338
+ "galore_scale": 1.0,
339
+ "galore_proj_type": "std",
340
+ "galore_optim_per_parameter": false,
341
+ "galore_with_embedding": false,
342
+ "galore_quantization": false,
343
+ "galore_proj_quant": false,
344
+ "galore_proj_bits": 4,
345
+ "galore_proj_group_size": 256,
346
+ "galore_cos_threshold": 0.4,
347
+ "galore_gamma_proj": 2,
348
+ "galore_queue_size": 5,
349
+ "adalora_target_r": 8,
350
+ "adalora_init_r": 12,
351
+ "adalora_tinit": 0,
352
+ "adalora_tfinal": 0,
353
+ "adalora_deltaT": 1,
354
+ "adalora_beta1": 0.85,
355
+ "adalora_beta2": 0.85,
356
+ "adalora_orth_reg_weight": 0.5,
357
+ "llamapro_num_new_blocks": 4,
358
+ "llamapro_num_groups": null,
359
+ "lisa_activated_layers": 0,
360
+ "lisa_step_interval": 20,
361
+ "reft_layer_key": null,
362
+ "reft_layers": null,
363
+ "reft_rank": 4,
364
+ "reft_intervention_type": "LoreftIntervention",
365
+ "reft_args": null,
366
+ "swanlab_token": null,
367
+ "swanlab_project": null,
368
+ "swanlab_workspace": null,
369
+ "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700",
370
+ "swanlab_lark_webhook_url": null,
371
+ "swanlab_lark_secret": null,
372
+ "swanlab_mode": "cloud",
373
+ "add_version": true,
374
+ "create_checkpoint_symlink": false,
375
+ "zero_hpz_partition_size": null,
376
+ "deepspeed_autotp_size": null,
377
+ "early_stop_interval": null,
378
+ "sft_alpha": 0,
379
+ "reward_model": null,
380
+ "reward_adapters": [],
381
+ "reward_model_type": null,
382
+ "reward_model_revision": null,
383
+ "num_ppo_epochs": 4,
384
+ "whiten_rewards": false,
385
+ "kl_coef": 0.05,
386
+ "cliprange": 0.2,
387
+ "vf_coef": 0.1,
388
+ "cliprange_value": 0.2,
389
+ "gamma": 1.0,
390
+ "lam": 0.95,
391
+ "num_mini_batches": 1,
392
+ "local_rollout_forward_batch_size": 64,
393
+ "num_sample_generations": 10,
394
+ "response_length": 1024,
395
+ "missing_eos_penalty": null,
396
+ "vllm_gpu_memory_utilization": 0.9,
397
+ "vllm_tensor_parallel_size": 1,
398
+ "vllm_pipeline_parallel_size": 1,
399
+ "vllm_enable_expert_parallel": false,
400
+ "vllm_max_num_seqs": 256,
401
+ "vllm_max_model_len": null,
402
+ "vllm_disable_custom_all_reduce": true,
403
+ "vllm_enforce_eager": false,
404
+ "vllm_limit_mm_per_prompt": {},
405
+ "vllm_max_lora_rank": 16,
406
+ "vllm_enable_prefix_caching": true,
407
+ "vllm_use_async_engine": false,
408
+ "vllm_quantization": null,
409
+ "vllm_reasoning_parser": null,
410
+ "vllm_disable_cascade_attn": false,
411
+ "vllm_data_parallel_size": 1,
412
+ "gpu_memory_utilization": null,
413
+ "tensor_parallel_size": null,
414
+ "limit_mm_per_prompt": null,
415
+ "data_parallel_size": null,
416
+ "use_async_engine": null,
417
+ "epsilon": 0.2,
418
+ "epsilon_high": null,
419
+ "delta": null,
420
+ "vllm_mode": "server",
421
+ "vllm_server_base_url": null,
422
+ "vllm_server_host": [
423
+ "127.0.0.1"
424
+ ],
425
+ "vllm_server_port": [
426
+ 8000
427
+ ],
428
+ "vllm_server_timeout": 240.0,
429
+ "cosine_min_len_value_wrong": -0.5,
430
+ "cosine_max_len_value_wrong": 0.0,
431
+ "cosine_min_len_value_correct": 1.0,
432
+ "cosine_max_len_value_correct": 0.5,
433
+ "cosine_max_len": null,
434
+ "repetition_n_grams": 3,
435
+ "repetition_max_penalty": -1.0,
436
+ "reward_model_plugin": null,
437
+ "sync_ref_model": false,
438
+ "ref_model_sync_steps": 512,
439
+ "ref_model_mixup_alpha": 0.6,
440
+ "async_generate": false,
441
+ "sleep_level": 0,
442
+ "move_model_batches": null,
443
+ "offload_optimizer": true,
444
+ "offload_model": true,
445
+ "gc_collect_after_offload": false,
446
+ "multi_turn_func": null,
447
+ "multi_turn_scheduler": null,
448
+ "max_turns": null,
449
+ "completion_length_limit_scope": "per_round",
450
+ "vllm_server_pass_dataset": false,
451
+ "dynamic_sample": false,
452
+ "max_resample_times": 3,
453
+ "overlong_filter": false,
454
+ "soft_max_length": null,
455
+ "soft_cache_length": null,
456
+ "scale_rewards": true,
457
+ "log_entropy": false,
458
+ "top_entropy_quantile": 1.0,
459
+ "importance_sampling_level": "token",
460
+ "wandb_log_unique_prompts": null,
461
+ "generation_batch_size": null,
462
+ "steps_per_generation": null,
463
+ "num_generations": 6,
464
+ "reward_funcs": [
465
+ "comet_worker"
466
+ ],
467
+ "reward_weights": null,
468
+ "log_completions": true,
469
+ "use_vllm": true,
470
+ "num_iterations": 1,
471
+ "teacher_model": null,
472
+ "teacher_adapters": [],
473
+ "teacher_model_type": null,
474
+ "teacher_model_revision": null,
475
+ "rlhf_type": "grpo",
476
+ "ref_model": null,
477
+ "ref_adapters": [],
478
+ "ref_model_type": null,
479
+ "ref_model_revision": null,
480
+ "beta": 0.0,
481
+ "label_smoothing": 0,
482
+ "max_completion_length": 1024,
483
+ "rpo_alpha": null,
484
+ "ld_alpha": null,
485
+ "discopop_tau": 0.05,
486
+ "loss_weights": null,
487
+ "cpo_alpha": 1.0,
488
+ "simpo_gamma": 1,
489
+ "desirable_weight": 1.0,
490
+ "undesirable_weight": 1.0,
491
+ "center_rewards_coefficient": null,
492
+ "lmbda": 0.5,
493
+ "seq_kd": false,
494
+ "vllm_client": "<swift.trainers.rlhf_trainer.vllm_client.VLLMClient object at 0x7fe979c8b5e0>",
495
+ "rank": 0,
496
+ "global_world_size": 3,
497
+ "local_world_size": 3,
498
+ "model_suffix": "checkpoint-280",
499
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
500
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fe97a9fdbd0>, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
501
+ "model_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
502
+ "hub": "<class 'swift.hub.hub.MSHub'>",
503
+ "evaluation_strategy": "steps",
504
+ "training_args": "GRPOConfig(output_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700', 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=4, per_device_eval_batch_size=4, 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=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=10, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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=True, eval_steps=200, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': 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=['swanlab'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=False, 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, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=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, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=6, max_completion_length=1024, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=24, steps_per_generation=2, temperature=1.0, top_p=0.9, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_server_base_url=None, vllm_mode='server', vllm_guided_decoding_regex=None, vllm_server_host=['127.0.0.1'], vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.9, vllm_tensor_parallel_size=1, beta=0.0, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, importance_sampling_level='token', reward_weights=None, scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=256, vllm_max_model_len=None, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, 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=1024, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, async_generate=False, sleep_level=0, move_model_batches=None, offload_optimizer=True, offload_model=True, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, dataset_shuffle=True, stop_words=[])"
505
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/args.json ADDED
@@ -0,0 +1,505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.01,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 100.0,
39
+ "save_total_limit": 10,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 200.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": false,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "swanlab"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": false,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "enable_channel_loss": false,
186
+ "check_model": true,
187
+ "acc_strategy": "token",
188
+ "train_dataloader_shuffle": true,
189
+ "max_epochs": null,
190
+ "aligner_lr": null,
191
+ "vit_lr": null,
192
+ "use_logits_to_keep": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": "grpo",
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
206
+ "model_type": "qwen2_5_vl",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5_vl",
221
+ "system": null,
222
+ "max_length": 128000,
223
+ "truncation_strategy": "left",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "last_round",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/train_base.jsonl"
236
+ ],
237
+ "val_dataset": [
238
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/test_base_02.jsonl"
239
+ ],
240
+ "split_dataset_ratio": 0.0,
241
+ "dataset_num_proc": 1,
242
+ "load_from_cache_file": true,
243
+ "dataset_shuffle": true,
244
+ "val_dataset_shuffle": false,
245
+ "streaming": false,
246
+ "interleave_prob": null,
247
+ "stopping_strategy": "first_exhausted",
248
+ "shuffle_buffer_size": 1000,
249
+ "download_mode": "reuse_dataset_if_exists",
250
+ "columns": {},
251
+ "strict": false,
252
+ "model_name": null,
253
+ "model_author": null,
254
+ "custom_dataset_info": [],
255
+ "quant_method": null,
256
+ "quant_bits": null,
257
+ "hqq_axis": null,
258
+ "bnb_4bit_compute_dtype": "bfloat16",
259
+ "bnb_4bit_quant_type": "nf4",
260
+ "bnb_4bit_use_double_quant": true,
261
+ "bnb_4bit_quant_storage": null,
262
+ "max_new_tokens": 1024,
263
+ "temperature": 1.0,
264
+ "top_k": 50,
265
+ "top_p": 0.9,
266
+ "repetition_penalty": 1.0,
267
+ "num_beams": 1,
268
+ "stream": false,
269
+ "stop_words": [],
270
+ "logprobs": false,
271
+ "top_logprobs": null,
272
+ "ckpt_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
273
+ "lora_modules": [],
274
+ "train_type": "full",
275
+ "adapters": [],
276
+ "external_plugins": [
277
+ "examples/train/grpo/plugin/plugin.py"
278
+ ],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": true,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [
291
+ "model.visual",
292
+ "model.visual.merger"
293
+ ],
294
+ "freeze_parameters_regex": null,
295
+ "freeze_parameters_ratio": 0.0,
296
+ "trainable_parameters": [],
297
+ "trainable_parameters_regex": null,
298
+ "freeze_llm": false,
299
+ "freeze_vit": true,
300
+ "freeze_aligner": true,
301
+ "target_modules": [
302
+ "all-linear"
303
+ ],
304
+ "target_regex": null,
305
+ "target_parameters": null,
306
+ "modules_to_save": [],
307
+ "lora_rank": 8,
308
+ "lora_alpha": 32,
309
+ "lora_dropout": 0.05,
310
+ "lora_bias": "none",
311
+ "lora_dtype": null,
312
+ "lorap_lr_ratio": null,
313
+ "use_rslora": false,
314
+ "use_dora": false,
315
+ "lora_ga_batch_size": 2,
316
+ "lora_ga_iters": 2,
317
+ "lora_ga_max_length": 1024,
318
+ "lora_ga_direction": "ArB2r",
319
+ "lora_ga_scale": "stable",
320
+ "lora_ga_stable_gamma": 16,
321
+ "init_weights": true,
322
+ "fourier_n_frequency": 2000,
323
+ "fourier_scaling": 300.0,
324
+ "boft_block_size": 4,
325
+ "boft_block_num": 0,
326
+ "boft_n_butterfly_factor": 1,
327
+ "boft_dropout": 0.0,
328
+ "vera_rank": 256,
329
+ "vera_projection_prng_key": 0,
330
+ "vera_dropout": 0.0,
331
+ "vera_d_initial": 0.1,
332
+ "adapter_act": "gelu",
333
+ "adapter_length": 128,
334
+ "use_galore": false,
335
+ "galore_target_modules": null,
336
+ "galore_rank": 128,
337
+ "galore_update_proj_gap": 50,
338
+ "galore_scale": 1.0,
339
+ "galore_proj_type": "std",
340
+ "galore_optim_per_parameter": false,
341
+ "galore_with_embedding": false,
342
+ "galore_quantization": false,
343
+ "galore_proj_quant": false,
344
+ "galore_proj_bits": 4,
345
+ "galore_proj_group_size": 256,
346
+ "galore_cos_threshold": 0.4,
347
+ "galore_gamma_proj": 2,
348
+ "galore_queue_size": 5,
349
+ "adalora_target_r": 8,
350
+ "adalora_init_r": 12,
351
+ "adalora_tinit": 0,
352
+ "adalora_tfinal": 0,
353
+ "adalora_deltaT": 1,
354
+ "adalora_beta1": 0.85,
355
+ "adalora_beta2": 0.85,
356
+ "adalora_orth_reg_weight": 0.5,
357
+ "llamapro_num_new_blocks": 4,
358
+ "llamapro_num_groups": null,
359
+ "lisa_activated_layers": 0,
360
+ "lisa_step_interval": 20,
361
+ "reft_layer_key": null,
362
+ "reft_layers": null,
363
+ "reft_rank": 4,
364
+ "reft_intervention_type": "LoreftIntervention",
365
+ "reft_args": null,
366
+ "swanlab_token": null,
367
+ "swanlab_project": null,
368
+ "swanlab_workspace": null,
369
+ "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700",
370
+ "swanlab_lark_webhook_url": null,
371
+ "swanlab_lark_secret": null,
372
+ "swanlab_mode": "cloud",
373
+ "add_version": true,
374
+ "create_checkpoint_symlink": false,
375
+ "zero_hpz_partition_size": null,
376
+ "deepspeed_autotp_size": null,
377
+ "early_stop_interval": null,
378
+ "sft_alpha": 0,
379
+ "reward_model": null,
380
+ "reward_adapters": [],
381
+ "reward_model_type": null,
382
+ "reward_model_revision": null,
383
+ "num_ppo_epochs": 4,
384
+ "whiten_rewards": false,
385
+ "kl_coef": 0.05,
386
+ "cliprange": 0.2,
387
+ "vf_coef": 0.1,
388
+ "cliprange_value": 0.2,
389
+ "gamma": 1.0,
390
+ "lam": 0.95,
391
+ "num_mini_batches": 1,
392
+ "local_rollout_forward_batch_size": 64,
393
+ "num_sample_generations": 10,
394
+ "response_length": 1024,
395
+ "missing_eos_penalty": null,
396
+ "vllm_gpu_memory_utilization": 0.9,
397
+ "vllm_tensor_parallel_size": 1,
398
+ "vllm_pipeline_parallel_size": 1,
399
+ "vllm_enable_expert_parallel": false,
400
+ "vllm_max_num_seqs": 256,
401
+ "vllm_max_model_len": null,
402
+ "vllm_disable_custom_all_reduce": true,
403
+ "vllm_enforce_eager": false,
404
+ "vllm_limit_mm_per_prompt": {},
405
+ "vllm_max_lora_rank": 16,
406
+ "vllm_enable_prefix_caching": true,
407
+ "vllm_use_async_engine": false,
408
+ "vllm_quantization": null,
409
+ "vllm_reasoning_parser": null,
410
+ "vllm_disable_cascade_attn": false,
411
+ "vllm_data_parallel_size": 1,
412
+ "gpu_memory_utilization": null,
413
+ "tensor_parallel_size": null,
414
+ "limit_mm_per_prompt": null,
415
+ "data_parallel_size": null,
416
+ "use_async_engine": null,
417
+ "epsilon": 0.2,
418
+ "epsilon_high": null,
419
+ "delta": null,
420
+ "vllm_mode": "server",
421
+ "vllm_server_base_url": null,
422
+ "vllm_server_host": [
423
+ "127.0.0.1"
424
+ ],
425
+ "vllm_server_port": [
426
+ 8000
427
+ ],
428
+ "vllm_server_timeout": 240.0,
429
+ "cosine_min_len_value_wrong": -0.5,
430
+ "cosine_max_len_value_wrong": 0.0,
431
+ "cosine_min_len_value_correct": 1.0,
432
+ "cosine_max_len_value_correct": 0.5,
433
+ "cosine_max_len": null,
434
+ "repetition_n_grams": 3,
435
+ "repetition_max_penalty": -1.0,
436
+ "reward_model_plugin": null,
437
+ "sync_ref_model": false,
438
+ "ref_model_sync_steps": 512,
439
+ "ref_model_mixup_alpha": 0.6,
440
+ "async_generate": false,
441
+ "sleep_level": 0,
442
+ "move_model_batches": null,
443
+ "offload_optimizer": true,
444
+ "offload_model": true,
445
+ "gc_collect_after_offload": false,
446
+ "multi_turn_func": null,
447
+ "multi_turn_scheduler": null,
448
+ "max_turns": null,
449
+ "completion_length_limit_scope": "per_round",
450
+ "vllm_server_pass_dataset": false,
451
+ "dynamic_sample": false,
452
+ "max_resample_times": 3,
453
+ "overlong_filter": false,
454
+ "soft_max_length": null,
455
+ "soft_cache_length": null,
456
+ "scale_rewards": true,
457
+ "log_entropy": false,
458
+ "top_entropy_quantile": 1.0,
459
+ "importance_sampling_level": "token",
460
+ "wandb_log_unique_prompts": null,
461
+ "generation_batch_size": null,
462
+ "steps_per_generation": null,
463
+ "num_generations": 6,
464
+ "reward_funcs": [
465
+ "comet_worker"
466
+ ],
467
+ "reward_weights": null,
468
+ "log_completions": true,
469
+ "use_vllm": true,
470
+ "num_iterations": 1,
471
+ "teacher_model": null,
472
+ "teacher_adapters": [],
473
+ "teacher_model_type": null,
474
+ "teacher_model_revision": null,
475
+ "rlhf_type": "grpo",
476
+ "ref_model": null,
477
+ "ref_adapters": [],
478
+ "ref_model_type": null,
479
+ "ref_model_revision": null,
480
+ "beta": 0.0,
481
+ "label_smoothing": 0,
482
+ "max_completion_length": 1024,
483
+ "rpo_alpha": null,
484
+ "ld_alpha": null,
485
+ "discopop_tau": 0.05,
486
+ "loss_weights": null,
487
+ "cpo_alpha": 1.0,
488
+ "simpo_gamma": 1,
489
+ "desirable_weight": 1.0,
490
+ "undesirable_weight": 1.0,
491
+ "center_rewards_coefficient": null,
492
+ "lmbda": 0.5,
493
+ "seq_kd": false,
494
+ "vllm_client": "<swift.trainers.rlhf_trainer.vllm_client.VLLMClient object at 0x7fe979c8b5e0>",
495
+ "rank": 0,
496
+ "global_world_size": 3,
497
+ "local_world_size": 3,
498
+ "model_suffix": "checkpoint-280",
499
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
500
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fe97a9fdbd0>, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
501
+ "model_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
502
+ "hub": "<class 'swift.hub.hub.MSHub'>",
503
+ "evaluation_strategy": "steps",
504
+ "training_args": "GRPOConfig(output_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700', 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=4, per_device_eval_batch_size=4, 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=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=10, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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=True, eval_steps=200, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': 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=['swanlab'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=False, 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, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=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, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=6, max_completion_length=1024, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=24, steps_per_generation=2, temperature=1.0, top_p=0.9, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_server_base_url=None, vllm_mode='server', vllm_guided_decoding_regex=None, vllm_server_host=['127.0.0.1'], vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.9, vllm_tensor_parallel_size=1, beta=0.0, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, importance_sampling_level='token', reward_weights=None, scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=256, vllm_max_model_len=None, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, 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=1024, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, async_generate=False, sleep_level=0, move_model_batches=None, offload_optimizer=True, offload_model=True, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, dataset_shuffle=True, stop_words=[])"
505
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "text_config": {
33
+ "architectures": [
34
+ "Qwen2_5_VLForConditionalGeneration"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 3584,
41
+ "image_token_id": null,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention"
73
+ ],
74
+ "max_position_embeddings": 128000,
75
+ "max_window_layers": 28,
76
+ "model_type": "qwen2_5_vl_text",
77
+ "num_attention_heads": 28,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 4,
80
+ "pad_token_id": 151643,
81
+ "rms_norm_eps": 1e-06,
82
+ "rope_scaling": {
83
+ "mrope_section": [
84
+ 16,
85
+ 24,
86
+ 24
87
+ ],
88
+ "rope_type": "default",
89
+ "type": "default"
90
+ },
91
+ "rope_theta": 1000000.0,
92
+ "sliding_window": null,
93
+ "torch_dtype": "bfloat16",
94
+ "use_cache": false,
95
+ "use_sliding_window": false,
96
+ "video_token_id": null,
97
+ "vision_end_token_id": 151653,
98
+ "vision_start_token_id": 151652,
99
+ "vision_token_id": 151654,
100
+ "vocab_size": 152064
101
+ },
102
+ "tie_word_embeddings": false,
103
+ "torch_dtype": "bfloat16",
104
+ "transformers_version": "4.55.4",
105
+ "use_cache": false,
106
+ "use_sliding_window": false,
107
+ "video_token_id": 151656,
108
+ "vision_config": {
109
+ "depth": 32,
110
+ "fullatt_block_indexes": [
111
+ 7,
112
+ 15,
113
+ 23,
114
+ 31
115
+ ],
116
+ "hidden_act": "silu",
117
+ "hidden_size": 1280,
118
+ "in_channels": 3,
119
+ "in_chans": 3,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3420,
122
+ "model_type": "qwen2_5_vl",
123
+ "num_heads": 16,
124
+ "out_hidden_size": 3584,
125
+ "pad_token_id": 151643,
126
+ "patch_size": 14,
127
+ "spatial_merge_size": 2,
128
+ "spatial_patch_size": 14,
129
+ "temporal_patch_size": 2,
130
+ "tokens_per_second": 2,
131
+ "torch_dtype": "bfloat16",
132
+ "window_size": 112
133
+ },
134
+ "vision_end_token_id": 151653,
135
+ "vision_start_token_id": 151652,
136
+ "vision_token_id": 151654,
137
+ "vocab_size": 152064
138
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.55.4"
12
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step750
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 848896,
4
+ "total_size": 16584333312
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "size": {
36
+ "longest_edge": 12845056,
37
+ "shortest_edge": 3136
38
+ },
39
+ "size_divisor": null,
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/checkpoint-750/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info("Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info("Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/completions.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0777f685f14da74a5b7e7215514a2a9ef812ca1be39990968863d9c56a1065c
3
+ size 35206007
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo/v13-20250907-200700/logging.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: v2-20250910-213626
4
+ tags:
5
+ - generated_from_trainer
6
+ - grpo
7
+ - trl
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for v2-20250910-213626
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
22
+ generator = pipeline("text-generation", model="None", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+
30
+
31
+
32
+ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
33
+
34
+ ### Framework versions
35
+
36
+ - TRL: 0.20.0
37
+ - Transformers: 4.55.4
38
+ - Pytorch: 2.7.1
39
+ - Datasets: 3.6.0
40
+ - Tokenizers: 0.21.4
41
+
42
+ ## Citations
43
+
44
+ Cite GRPO as:
45
+
46
+ ```bibtex
47
+ @article{zhihong2024deepseekmath,
48
+ title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
49
+ author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
50
+ year = 2024,
51
+ eprint = {arXiv:2402.03300},
52
+ }
53
+
54
+ ```
55
+
56
+ Cite TRL as:
57
+
58
+ ```bibtex
59
+ @misc{vonwerra2022trl,
60
+ title = {{TRL: Transformer Reinforcement Learning}},
61
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
62
+ year = 2020,
63
+ journal = {GitHub repository},
64
+ publisher = {GitHub},
65
+ howpublished = {\url{https://github.com/huggingface/trl}}
66
+ }
67
+ ```
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/args.json ADDED
@@ -0,0 +1,505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 10.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.01,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 50.0,
39
+ "save_total_limit": 10,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 100.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": false,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "swanlab"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": false,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "enable_channel_loss": false,
186
+ "check_model": true,
187
+ "acc_strategy": "token",
188
+ "train_dataloader_shuffle": true,
189
+ "max_epochs": null,
190
+ "aligner_lr": null,
191
+ "vit_lr": null,
192
+ "use_logits_to_keep": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": "grpo",
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200",
206
+ "model_type": "qwen2_5_vl",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5_vl",
221
+ "system": null,
222
+ "max_length": 128000,
223
+ "truncation_strategy": "left",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "last_round",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/train_base_sp.jsonl"
236
+ ],
237
+ "val_dataset": [
238
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/test_base_02.jsonl"
239
+ ],
240
+ "split_dataset_ratio": 0.0,
241
+ "dataset_num_proc": 1,
242
+ "load_from_cache_file": true,
243
+ "dataset_shuffle": true,
244
+ "val_dataset_shuffle": false,
245
+ "streaming": false,
246
+ "interleave_prob": null,
247
+ "stopping_strategy": "first_exhausted",
248
+ "shuffle_buffer_size": 1000,
249
+ "download_mode": "reuse_dataset_if_exists",
250
+ "columns": {},
251
+ "strict": false,
252
+ "model_name": null,
253
+ "model_author": null,
254
+ "custom_dataset_info": [],
255
+ "quant_method": null,
256
+ "quant_bits": null,
257
+ "hqq_axis": null,
258
+ "bnb_4bit_compute_dtype": "bfloat16",
259
+ "bnb_4bit_quant_type": "nf4",
260
+ "bnb_4bit_use_double_quant": true,
261
+ "bnb_4bit_quant_storage": null,
262
+ "max_new_tokens": 1024,
263
+ "temperature": 1.0,
264
+ "top_k": 50,
265
+ "top_p": 0.9,
266
+ "repetition_penalty": 1.0,
267
+ "num_beams": 1,
268
+ "stream": false,
269
+ "stop_words": [],
270
+ "logprobs": false,
271
+ "top_logprobs": null,
272
+ "ckpt_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200",
273
+ "lora_modules": [],
274
+ "train_type": "full",
275
+ "adapters": [],
276
+ "external_plugins": [
277
+ "examples/train/grpo/plugin/plugin.py"
278
+ ],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": true,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [
291
+ "model.visual",
292
+ "model.visual.merger"
293
+ ],
294
+ "freeze_parameters_regex": null,
295
+ "freeze_parameters_ratio": 0.0,
296
+ "trainable_parameters": [],
297
+ "trainable_parameters_regex": null,
298
+ "freeze_llm": false,
299
+ "freeze_vit": true,
300
+ "freeze_aligner": true,
301
+ "target_modules": [
302
+ "all-linear"
303
+ ],
304
+ "target_regex": null,
305
+ "target_parameters": null,
306
+ "modules_to_save": [],
307
+ "lora_rank": 8,
308
+ "lora_alpha": 32,
309
+ "lora_dropout": 0.05,
310
+ "lora_bias": "none",
311
+ "lora_dtype": null,
312
+ "lorap_lr_ratio": null,
313
+ "use_rslora": false,
314
+ "use_dora": false,
315
+ "lora_ga_batch_size": 2,
316
+ "lora_ga_iters": 2,
317
+ "lora_ga_max_length": 1024,
318
+ "lora_ga_direction": "ArB2r",
319
+ "lora_ga_scale": "stable",
320
+ "lora_ga_stable_gamma": 16,
321
+ "init_weights": true,
322
+ "fourier_n_frequency": 2000,
323
+ "fourier_scaling": 300.0,
324
+ "boft_block_size": 4,
325
+ "boft_block_num": 0,
326
+ "boft_n_butterfly_factor": 1,
327
+ "boft_dropout": 0.0,
328
+ "vera_rank": 256,
329
+ "vera_projection_prng_key": 0,
330
+ "vera_dropout": 0.0,
331
+ "vera_d_initial": 0.1,
332
+ "adapter_act": "gelu",
333
+ "adapter_length": 128,
334
+ "use_galore": false,
335
+ "galore_target_modules": null,
336
+ "galore_rank": 128,
337
+ "galore_update_proj_gap": 50,
338
+ "galore_scale": 1.0,
339
+ "galore_proj_type": "std",
340
+ "galore_optim_per_parameter": false,
341
+ "galore_with_embedding": false,
342
+ "galore_quantization": false,
343
+ "galore_proj_quant": false,
344
+ "galore_proj_bits": 4,
345
+ "galore_proj_group_size": 256,
346
+ "galore_cos_threshold": 0.4,
347
+ "galore_gamma_proj": 2,
348
+ "galore_queue_size": 5,
349
+ "adalora_target_r": 8,
350
+ "adalora_init_r": 12,
351
+ "adalora_tinit": 0,
352
+ "adalora_tfinal": 0,
353
+ "adalora_deltaT": 1,
354
+ "adalora_beta1": 0.85,
355
+ "adalora_beta2": 0.85,
356
+ "adalora_orth_reg_weight": 0.5,
357
+ "llamapro_num_new_blocks": 4,
358
+ "llamapro_num_groups": null,
359
+ "lisa_activated_layers": 0,
360
+ "lisa_step_interval": 20,
361
+ "reft_layer_key": null,
362
+ "reft_layers": null,
363
+ "reft_rank": 4,
364
+ "reft_intervention_type": "LoreftIntervention",
365
+ "reft_args": null,
366
+ "swanlab_token": null,
367
+ "swanlab_project": null,
368
+ "swanlab_workspace": null,
369
+ "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626",
370
+ "swanlab_lark_webhook_url": null,
371
+ "swanlab_lark_secret": null,
372
+ "swanlab_mode": "cloud",
373
+ "add_version": true,
374
+ "create_checkpoint_symlink": false,
375
+ "zero_hpz_partition_size": null,
376
+ "deepspeed_autotp_size": null,
377
+ "early_stop_interval": null,
378
+ "sft_alpha": 0,
379
+ "reward_model": null,
380
+ "reward_adapters": [],
381
+ "reward_model_type": null,
382
+ "reward_model_revision": null,
383
+ "num_ppo_epochs": 4,
384
+ "whiten_rewards": false,
385
+ "kl_coef": 0.05,
386
+ "cliprange": 0.2,
387
+ "vf_coef": 0.1,
388
+ "cliprange_value": 0.2,
389
+ "gamma": 1.0,
390
+ "lam": 0.95,
391
+ "num_mini_batches": 1,
392
+ "local_rollout_forward_batch_size": 64,
393
+ "num_sample_generations": 10,
394
+ "response_length": 1024,
395
+ "missing_eos_penalty": null,
396
+ "vllm_gpu_memory_utilization": 0.9,
397
+ "vllm_tensor_parallel_size": 1,
398
+ "vllm_pipeline_parallel_size": 1,
399
+ "vllm_enable_expert_parallel": false,
400
+ "vllm_max_num_seqs": 256,
401
+ "vllm_max_model_len": null,
402
+ "vllm_disable_custom_all_reduce": true,
403
+ "vllm_enforce_eager": false,
404
+ "vllm_limit_mm_per_prompt": {},
405
+ "vllm_max_lora_rank": 16,
406
+ "vllm_enable_prefix_caching": true,
407
+ "vllm_use_async_engine": false,
408
+ "vllm_quantization": null,
409
+ "vllm_reasoning_parser": null,
410
+ "vllm_disable_cascade_attn": false,
411
+ "vllm_data_parallel_size": 1,
412
+ "gpu_memory_utilization": null,
413
+ "tensor_parallel_size": null,
414
+ "limit_mm_per_prompt": null,
415
+ "data_parallel_size": null,
416
+ "use_async_engine": null,
417
+ "epsilon": 0.2,
418
+ "epsilon_high": null,
419
+ "delta": null,
420
+ "vllm_mode": "server",
421
+ "vllm_server_base_url": null,
422
+ "vllm_server_host": [
423
+ "127.0.0.1"
424
+ ],
425
+ "vllm_server_port": [
426
+ 8000
427
+ ],
428
+ "vllm_server_timeout": 240.0,
429
+ "cosine_min_len_value_wrong": -0.5,
430
+ "cosine_max_len_value_wrong": 0.0,
431
+ "cosine_min_len_value_correct": 1.0,
432
+ "cosine_max_len_value_correct": 0.5,
433
+ "cosine_max_len": null,
434
+ "repetition_n_grams": 3,
435
+ "repetition_max_penalty": -1.0,
436
+ "reward_model_plugin": null,
437
+ "sync_ref_model": false,
438
+ "ref_model_sync_steps": 512,
439
+ "ref_model_mixup_alpha": 0.6,
440
+ "async_generate": false,
441
+ "sleep_level": 0,
442
+ "move_model_batches": null,
443
+ "offload_optimizer": true,
444
+ "offload_model": true,
445
+ "gc_collect_after_offload": false,
446
+ "multi_turn_func": null,
447
+ "multi_turn_scheduler": null,
448
+ "max_turns": null,
449
+ "completion_length_limit_scope": "per_round",
450
+ "vllm_server_pass_dataset": false,
451
+ "dynamic_sample": false,
452
+ "max_resample_times": 3,
453
+ "overlong_filter": false,
454
+ "soft_max_length": null,
455
+ "soft_cache_length": null,
456
+ "scale_rewards": true,
457
+ "log_entropy": false,
458
+ "top_entropy_quantile": 1.0,
459
+ "importance_sampling_level": "token",
460
+ "wandb_log_unique_prompts": null,
461
+ "generation_batch_size": null,
462
+ "steps_per_generation": null,
463
+ "num_generations": 6,
464
+ "reward_funcs": [
465
+ "comet_worker"
466
+ ],
467
+ "reward_weights": null,
468
+ "log_completions": true,
469
+ "use_vllm": true,
470
+ "num_iterations": 1,
471
+ "teacher_model": null,
472
+ "teacher_adapters": [],
473
+ "teacher_model_type": null,
474
+ "teacher_model_revision": null,
475
+ "rlhf_type": "grpo",
476
+ "ref_model": null,
477
+ "ref_adapters": [],
478
+ "ref_model_type": null,
479
+ "ref_model_revision": null,
480
+ "beta": 0.0,
481
+ "label_smoothing": 0,
482
+ "max_completion_length": 1024,
483
+ "rpo_alpha": null,
484
+ "ld_alpha": null,
485
+ "discopop_tau": 0.05,
486
+ "loss_weights": null,
487
+ "cpo_alpha": 1.0,
488
+ "simpo_gamma": 1,
489
+ "desirable_weight": 1.0,
490
+ "undesirable_weight": 1.0,
491
+ "center_rewards_coefficient": null,
492
+ "lmbda": 0.5,
493
+ "seq_kd": false,
494
+ "vllm_client": "<swift.trainers.rlhf_trainer.vllm_client.VLLMClient object at 0x7fd4bf477760>",
495
+ "rank": 0,
496
+ "global_world_size": 3,
497
+ "local_world_size": 3,
498
+ "model_suffix": "checkpoint-1200",
499
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
500
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fd4c01edbd0>, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
501
+ "model_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200",
502
+ "hub": "<class 'swift.hub.hub.MSHub'>",
503
+ "evaluation_strategy": "steps",
504
+ "training_args": "GRPOConfig(output_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626', 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=4, per_device_eval_batch_size=4, 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=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=10.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=10, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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=True, eval_steps=100, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': 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=['swanlab'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=False, 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, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=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, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=6, max_completion_length=1024, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=24, steps_per_generation=2, temperature=1.0, top_p=0.9, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_server_base_url=None, vllm_mode='server', vllm_guided_decoding_regex=None, vllm_server_host=['127.0.0.1'], vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.9, vllm_tensor_parallel_size=1, beta=0.0, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, importance_sampling_level='token', reward_weights=None, scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=256, vllm_max_model_len=None, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, 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=1024, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, async_generate=False, sleep_level=0, move_model_batches=None, offload_optimizer=True, offload_model=True, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, dataset_shuffle=True, stop_words=[])"
505
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/args.json ADDED
@@ -0,0 +1,505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 10.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.01,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 50.0,
39
+ "save_total_limit": 10,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 100.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": false,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "swanlab"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": false,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "enable_channel_loss": false,
186
+ "check_model": true,
187
+ "acc_strategy": "token",
188
+ "train_dataloader_shuffle": true,
189
+ "max_epochs": null,
190
+ "aligner_lr": null,
191
+ "vit_lr": null,
192
+ "use_logits_to_keep": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": "grpo",
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200",
206
+ "model_type": "qwen2_5_vl",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5_vl",
221
+ "system": null,
222
+ "max_length": 128000,
223
+ "truncation_strategy": "left",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "last_round",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/train_base_sp.jsonl"
236
+ ],
237
+ "val_dataset": [
238
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift/test_base_02.jsonl"
239
+ ],
240
+ "split_dataset_ratio": 0.0,
241
+ "dataset_num_proc": 1,
242
+ "load_from_cache_file": true,
243
+ "dataset_shuffle": true,
244
+ "val_dataset_shuffle": false,
245
+ "streaming": false,
246
+ "interleave_prob": null,
247
+ "stopping_strategy": "first_exhausted",
248
+ "shuffle_buffer_size": 1000,
249
+ "download_mode": "reuse_dataset_if_exists",
250
+ "columns": {},
251
+ "strict": false,
252
+ "model_name": null,
253
+ "model_author": null,
254
+ "custom_dataset_info": [],
255
+ "quant_method": null,
256
+ "quant_bits": null,
257
+ "hqq_axis": null,
258
+ "bnb_4bit_compute_dtype": "bfloat16",
259
+ "bnb_4bit_quant_type": "nf4",
260
+ "bnb_4bit_use_double_quant": true,
261
+ "bnb_4bit_quant_storage": null,
262
+ "max_new_tokens": 1024,
263
+ "temperature": 1.0,
264
+ "top_k": 50,
265
+ "top_p": 0.9,
266
+ "repetition_penalty": 1.0,
267
+ "num_beams": 1,
268
+ "stream": false,
269
+ "stop_words": [],
270
+ "logprobs": false,
271
+ "top_logprobs": null,
272
+ "ckpt_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200",
273
+ "lora_modules": [],
274
+ "train_type": "full",
275
+ "adapters": [],
276
+ "external_plugins": [
277
+ "examples/train/grpo/plugin/plugin.py"
278
+ ],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": true,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [
291
+ "model.visual",
292
+ "model.visual.merger"
293
+ ],
294
+ "freeze_parameters_regex": null,
295
+ "freeze_parameters_ratio": 0.0,
296
+ "trainable_parameters": [],
297
+ "trainable_parameters_regex": null,
298
+ "freeze_llm": false,
299
+ "freeze_vit": true,
300
+ "freeze_aligner": true,
301
+ "target_modules": [
302
+ "all-linear"
303
+ ],
304
+ "target_regex": null,
305
+ "target_parameters": null,
306
+ "modules_to_save": [],
307
+ "lora_rank": 8,
308
+ "lora_alpha": 32,
309
+ "lora_dropout": 0.05,
310
+ "lora_bias": "none",
311
+ "lora_dtype": null,
312
+ "lorap_lr_ratio": null,
313
+ "use_rslora": false,
314
+ "use_dora": false,
315
+ "lora_ga_batch_size": 2,
316
+ "lora_ga_iters": 2,
317
+ "lora_ga_max_length": 1024,
318
+ "lora_ga_direction": "ArB2r",
319
+ "lora_ga_scale": "stable",
320
+ "lora_ga_stable_gamma": 16,
321
+ "init_weights": true,
322
+ "fourier_n_frequency": 2000,
323
+ "fourier_scaling": 300.0,
324
+ "boft_block_size": 4,
325
+ "boft_block_num": 0,
326
+ "boft_n_butterfly_factor": 1,
327
+ "boft_dropout": 0.0,
328
+ "vera_rank": 256,
329
+ "vera_projection_prng_key": 0,
330
+ "vera_dropout": 0.0,
331
+ "vera_d_initial": 0.1,
332
+ "adapter_act": "gelu",
333
+ "adapter_length": 128,
334
+ "use_galore": false,
335
+ "galore_target_modules": null,
336
+ "galore_rank": 128,
337
+ "galore_update_proj_gap": 50,
338
+ "galore_scale": 1.0,
339
+ "galore_proj_type": "std",
340
+ "galore_optim_per_parameter": false,
341
+ "galore_with_embedding": false,
342
+ "galore_quantization": false,
343
+ "galore_proj_quant": false,
344
+ "galore_proj_bits": 4,
345
+ "galore_proj_group_size": 256,
346
+ "galore_cos_threshold": 0.4,
347
+ "galore_gamma_proj": 2,
348
+ "galore_queue_size": 5,
349
+ "adalora_target_r": 8,
350
+ "adalora_init_r": 12,
351
+ "adalora_tinit": 0,
352
+ "adalora_tfinal": 0,
353
+ "adalora_deltaT": 1,
354
+ "adalora_beta1": 0.85,
355
+ "adalora_beta2": 0.85,
356
+ "adalora_orth_reg_weight": 0.5,
357
+ "llamapro_num_new_blocks": 4,
358
+ "llamapro_num_groups": null,
359
+ "lisa_activated_layers": 0,
360
+ "lisa_step_interval": 20,
361
+ "reft_layer_key": null,
362
+ "reft_layers": null,
363
+ "reft_rank": 4,
364
+ "reft_intervention_type": "LoreftIntervention",
365
+ "reft_args": null,
366
+ "swanlab_token": null,
367
+ "swanlab_project": null,
368
+ "swanlab_workspace": null,
369
+ "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626",
370
+ "swanlab_lark_webhook_url": null,
371
+ "swanlab_lark_secret": null,
372
+ "swanlab_mode": "cloud",
373
+ "add_version": true,
374
+ "create_checkpoint_symlink": false,
375
+ "zero_hpz_partition_size": null,
376
+ "deepspeed_autotp_size": null,
377
+ "early_stop_interval": null,
378
+ "sft_alpha": 0,
379
+ "reward_model": null,
380
+ "reward_adapters": [],
381
+ "reward_model_type": null,
382
+ "reward_model_revision": null,
383
+ "num_ppo_epochs": 4,
384
+ "whiten_rewards": false,
385
+ "kl_coef": 0.05,
386
+ "cliprange": 0.2,
387
+ "vf_coef": 0.1,
388
+ "cliprange_value": 0.2,
389
+ "gamma": 1.0,
390
+ "lam": 0.95,
391
+ "num_mini_batches": 1,
392
+ "local_rollout_forward_batch_size": 64,
393
+ "num_sample_generations": 10,
394
+ "response_length": 1024,
395
+ "missing_eos_penalty": null,
396
+ "vllm_gpu_memory_utilization": 0.9,
397
+ "vllm_tensor_parallel_size": 1,
398
+ "vllm_pipeline_parallel_size": 1,
399
+ "vllm_enable_expert_parallel": false,
400
+ "vllm_max_num_seqs": 256,
401
+ "vllm_max_model_len": null,
402
+ "vllm_disable_custom_all_reduce": true,
403
+ "vllm_enforce_eager": false,
404
+ "vllm_limit_mm_per_prompt": {},
405
+ "vllm_max_lora_rank": 16,
406
+ "vllm_enable_prefix_caching": true,
407
+ "vllm_use_async_engine": false,
408
+ "vllm_quantization": null,
409
+ "vllm_reasoning_parser": null,
410
+ "vllm_disable_cascade_attn": false,
411
+ "vllm_data_parallel_size": 1,
412
+ "gpu_memory_utilization": null,
413
+ "tensor_parallel_size": null,
414
+ "limit_mm_per_prompt": null,
415
+ "data_parallel_size": null,
416
+ "use_async_engine": null,
417
+ "epsilon": 0.2,
418
+ "epsilon_high": null,
419
+ "delta": null,
420
+ "vllm_mode": "server",
421
+ "vllm_server_base_url": null,
422
+ "vllm_server_host": [
423
+ "127.0.0.1"
424
+ ],
425
+ "vllm_server_port": [
426
+ 8000
427
+ ],
428
+ "vllm_server_timeout": 240.0,
429
+ "cosine_min_len_value_wrong": -0.5,
430
+ "cosine_max_len_value_wrong": 0.0,
431
+ "cosine_min_len_value_correct": 1.0,
432
+ "cosine_max_len_value_correct": 0.5,
433
+ "cosine_max_len": null,
434
+ "repetition_n_grams": 3,
435
+ "repetition_max_penalty": -1.0,
436
+ "reward_model_plugin": null,
437
+ "sync_ref_model": false,
438
+ "ref_model_sync_steps": 512,
439
+ "ref_model_mixup_alpha": 0.6,
440
+ "async_generate": false,
441
+ "sleep_level": 0,
442
+ "move_model_batches": null,
443
+ "offload_optimizer": true,
444
+ "offload_model": true,
445
+ "gc_collect_after_offload": false,
446
+ "multi_turn_func": null,
447
+ "multi_turn_scheduler": null,
448
+ "max_turns": null,
449
+ "completion_length_limit_scope": "per_round",
450
+ "vllm_server_pass_dataset": false,
451
+ "dynamic_sample": false,
452
+ "max_resample_times": 3,
453
+ "overlong_filter": false,
454
+ "soft_max_length": null,
455
+ "soft_cache_length": null,
456
+ "scale_rewards": true,
457
+ "log_entropy": false,
458
+ "top_entropy_quantile": 1.0,
459
+ "importance_sampling_level": "token",
460
+ "wandb_log_unique_prompts": null,
461
+ "generation_batch_size": null,
462
+ "steps_per_generation": null,
463
+ "num_generations": 6,
464
+ "reward_funcs": [
465
+ "comet_worker"
466
+ ],
467
+ "reward_weights": null,
468
+ "log_completions": true,
469
+ "use_vllm": true,
470
+ "num_iterations": 1,
471
+ "teacher_model": null,
472
+ "teacher_adapters": [],
473
+ "teacher_model_type": null,
474
+ "teacher_model_revision": null,
475
+ "rlhf_type": "grpo",
476
+ "ref_model": null,
477
+ "ref_adapters": [],
478
+ "ref_model_type": null,
479
+ "ref_model_revision": null,
480
+ "beta": 0.0,
481
+ "label_smoothing": 0,
482
+ "max_completion_length": 1024,
483
+ "rpo_alpha": null,
484
+ "ld_alpha": null,
485
+ "discopop_tau": 0.05,
486
+ "loss_weights": null,
487
+ "cpo_alpha": 1.0,
488
+ "simpo_gamma": 1,
489
+ "desirable_weight": 1.0,
490
+ "undesirable_weight": 1.0,
491
+ "center_rewards_coefficient": null,
492
+ "lmbda": 0.5,
493
+ "seq_kd": false,
494
+ "vllm_client": "<swift.trainers.rlhf_trainer.vllm_client.VLLMClient object at 0x7fd4bf477760>",
495
+ "rank": 0,
496
+ "global_world_size": 3,
497
+ "local_world_size": 3,
498
+ "model_suffix": "checkpoint-1200",
499
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
500
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fd4c01edbd0>, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
501
+ "model_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue/v1-20250909-142720/checkpoint-1200",
502
+ "hub": "<class 'swift.hub.hub.MSHub'>",
503
+ "evaluation_strategy": "steps",
504
+ "training_args": "GRPOConfig(output_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626', 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=4, per_device_eval_batch_size=4, 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=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=10.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=10, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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=True, eval_steps=100, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': 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=['swanlab'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=False, 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, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=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, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=6, max_completion_length=1024, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=24, steps_per_generation=2, temperature=1.0, top_p=0.9, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_server_base_url=None, vllm_mode='server', vllm_guided_decoding_regex=None, vllm_server_host=['127.0.0.1'], vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.9, vllm_tensor_parallel_size=1, beta=0.0, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, importance_sampling_level='token', reward_weights=None, scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=256, vllm_max_model_len=None, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, 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=1024, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, async_generate=False, sleep_level=0, move_model_batches=None, offload_optimizer=True, offload_model=True, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, dataset_shuffle=True, stop_words=[])"
505
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "text_config": {
33
+ "architectures": [
34
+ "Qwen2_5_VLForConditionalGeneration"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 3584,
41
+ "image_token_id": null,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention"
73
+ ],
74
+ "max_position_embeddings": 128000,
75
+ "max_window_layers": 28,
76
+ "model_type": "qwen2_5_vl_text",
77
+ "num_attention_heads": 28,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 4,
80
+ "pad_token_id": 151643,
81
+ "rms_norm_eps": 1e-06,
82
+ "rope_scaling": {
83
+ "mrope_section": [
84
+ 16,
85
+ 24,
86
+ 24
87
+ ],
88
+ "rope_type": "default",
89
+ "type": "default"
90
+ },
91
+ "rope_theta": 1000000.0,
92
+ "sliding_window": null,
93
+ "torch_dtype": "bfloat16",
94
+ "use_cache": false,
95
+ "use_sliding_window": false,
96
+ "video_token_id": null,
97
+ "vision_end_token_id": 151653,
98
+ "vision_start_token_id": 151652,
99
+ "vision_token_id": 151654,
100
+ "vocab_size": 152064
101
+ },
102
+ "tie_word_embeddings": false,
103
+ "torch_dtype": "bfloat16",
104
+ "transformers_version": "4.55.4",
105
+ "use_cache": false,
106
+ "use_sliding_window": false,
107
+ "video_token_id": 151656,
108
+ "vision_config": {
109
+ "depth": 32,
110
+ "fullatt_block_indexes": [
111
+ 7,
112
+ 15,
113
+ 23,
114
+ 31
115
+ ],
116
+ "hidden_act": "silu",
117
+ "hidden_size": 1280,
118
+ "in_channels": 3,
119
+ "in_chans": 3,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3420,
122
+ "model_type": "qwen2_5_vl",
123
+ "num_heads": 16,
124
+ "out_hidden_size": 3584,
125
+ "pad_token_id": 151643,
126
+ "patch_size": 14,
127
+ "spatial_merge_size": 2,
128
+ "spatial_patch_size": 14,
129
+ "temporal_patch_size": 2,
130
+ "tokens_per_second": 2,
131
+ "torch_dtype": "bfloat16",
132
+ "window_size": 112
133
+ },
134
+ "vision_end_token_id": 151653,
135
+ "vision_start_token_id": 151652,
136
+ "vision_token_id": 151654,
137
+ "vocab_size": 152064
138
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.55.4"
12
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step250
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 848896,
4
+ "total_size": 16584333312
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/checkpoint-250/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/completions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-thinking_v2_full_comet_grpo_continue_sp/v2-20250910-213626/logging.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-τ-checkpoint-1250/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/args.json ADDED
@@ -0,0 +1,507 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 5.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.01,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 250.0,
39
+ "save_total_limit": 10,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 500.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": false,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "swanlab"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": false,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "enable_channel_loss": false,
186
+ "check_model": true,
187
+ "acc_strategy": "token",
188
+ "train_dataloader_shuffle": true,
189
+ "max_epochs": null,
190
+ "aligner_lr": null,
191
+ "vit_lr": null,
192
+ "use_logits_to_keep": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": "grpo",
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
206
+ "model_type": "qwen2_5_vl",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5_vl",
221
+ "system": null,
222
+ "max_length": 128000,
223
+ "truncation_strategy": "left",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "last_round",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift_split/train_ambi_normal_train_messages.jsonl",
236
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift_split/train_mma_train_messages.jsonl",
237
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift_split/train_sp_train_messages.jsonl"
238
+ ],
239
+ "val_dataset": [
240
+ "/mnt/data/users/liamding/data/3AM_Plus/final/split/swift_split/test_02.jsonl"
241
+ ],
242
+ "split_dataset_ratio": 0.0,
243
+ "dataset_num_proc": 1,
244
+ "load_from_cache_file": true,
245
+ "dataset_shuffle": true,
246
+ "val_dataset_shuffle": false,
247
+ "streaming": false,
248
+ "interleave_prob": null,
249
+ "stopping_strategy": "first_exhausted",
250
+ "shuffle_buffer_size": 1000,
251
+ "download_mode": "reuse_dataset_if_exists",
252
+ "columns": {},
253
+ "strict": false,
254
+ "model_name": null,
255
+ "model_author": null,
256
+ "custom_dataset_info": [],
257
+ "quant_method": null,
258
+ "quant_bits": null,
259
+ "hqq_axis": null,
260
+ "bnb_4bit_compute_dtype": "bfloat16",
261
+ "bnb_4bit_quant_type": "nf4",
262
+ "bnb_4bit_use_double_quant": true,
263
+ "bnb_4bit_quant_storage": null,
264
+ "max_new_tokens": 2048,
265
+ "temperature": 1.0,
266
+ "top_k": 50,
267
+ "top_p": 0.9,
268
+ "repetition_penalty": 1.0,
269
+ "num_beams": 1,
270
+ "stream": false,
271
+ "stop_words": [],
272
+ "logprobs": false,
273
+ "top_logprobs": null,
274
+ "ckpt_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
275
+ "lora_modules": [],
276
+ "train_type": "full",
277
+ "adapters": [],
278
+ "external_plugins": [
279
+ "examples/train/grpo/plugin/plugin.py"
280
+ ],
281
+ "model_kwargs": {},
282
+ "load_args": false,
283
+ "load_data_args": false,
284
+ "packing": false,
285
+ "packing_length": null,
286
+ "lazy_tokenize": true,
287
+ "cached_dataset": [],
288
+ "custom_register_path": [],
289
+ "use_hf": false,
290
+ "ignore_args_error": false,
291
+ "use_swift_lora": false,
292
+ "freeze_parameters": [
293
+ "model.visual",
294
+ "model.visual.merger"
295
+ ],
296
+ "freeze_parameters_regex": null,
297
+ "freeze_parameters_ratio": 0.0,
298
+ "trainable_parameters": [],
299
+ "trainable_parameters_regex": null,
300
+ "freeze_llm": false,
301
+ "freeze_vit": true,
302
+ "freeze_aligner": true,
303
+ "target_modules": [
304
+ "all-linear"
305
+ ],
306
+ "target_regex": null,
307
+ "target_parameters": null,
308
+ "modules_to_save": [],
309
+ "lora_rank": 8,
310
+ "lora_alpha": 32,
311
+ "lora_dropout": 0.05,
312
+ "lora_bias": "none",
313
+ "lora_dtype": null,
314
+ "lorap_lr_ratio": null,
315
+ "use_rslora": false,
316
+ "use_dora": false,
317
+ "lora_ga_batch_size": 2,
318
+ "lora_ga_iters": 2,
319
+ "lora_ga_max_length": 1024,
320
+ "lora_ga_direction": "ArB2r",
321
+ "lora_ga_scale": "stable",
322
+ "lora_ga_stable_gamma": 16,
323
+ "init_weights": true,
324
+ "fourier_n_frequency": 2000,
325
+ "fourier_scaling": 300.0,
326
+ "boft_block_size": 4,
327
+ "boft_block_num": 0,
328
+ "boft_n_butterfly_factor": 1,
329
+ "boft_dropout": 0.0,
330
+ "vera_rank": 256,
331
+ "vera_projection_prng_key": 0,
332
+ "vera_dropout": 0.0,
333
+ "vera_d_initial": 0.1,
334
+ "adapter_act": "gelu",
335
+ "adapter_length": 128,
336
+ "use_galore": false,
337
+ "galore_target_modules": null,
338
+ "galore_rank": 128,
339
+ "galore_update_proj_gap": 50,
340
+ "galore_scale": 1.0,
341
+ "galore_proj_type": "std",
342
+ "galore_optim_per_parameter": false,
343
+ "galore_with_embedding": false,
344
+ "galore_quantization": false,
345
+ "galore_proj_quant": false,
346
+ "galore_proj_bits": 4,
347
+ "galore_proj_group_size": 256,
348
+ "galore_cos_threshold": 0.4,
349
+ "galore_gamma_proj": 2,
350
+ "galore_queue_size": 5,
351
+ "adalora_target_r": 8,
352
+ "adalora_init_r": 12,
353
+ "adalora_tinit": 0,
354
+ "adalora_tfinal": 0,
355
+ "adalora_deltaT": 1,
356
+ "adalora_beta1": 0.85,
357
+ "adalora_beta2": 0.85,
358
+ "adalora_orth_reg_weight": 0.5,
359
+ "llamapro_num_new_blocks": 4,
360
+ "llamapro_num_groups": null,
361
+ "lisa_activated_layers": 0,
362
+ "lisa_step_interval": 20,
363
+ "reft_layer_key": null,
364
+ "reft_layers": null,
365
+ "reft_rank": 4,
366
+ "reft_intervention_type": "LoreftIntervention",
367
+ "reft_args": null,
368
+ "swanlab_token": null,
369
+ "swanlab_project": null,
370
+ "swanlab_workspace": null,
371
+ "swanlab_exp_name": "/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657",
372
+ "swanlab_lark_webhook_url": null,
373
+ "swanlab_lark_secret": null,
374
+ "swanlab_mode": "cloud",
375
+ "add_version": true,
376
+ "create_checkpoint_symlink": false,
377
+ "zero_hpz_partition_size": null,
378
+ "deepspeed_autotp_size": null,
379
+ "early_stop_interval": null,
380
+ "sft_alpha": 0,
381
+ "reward_model": null,
382
+ "reward_adapters": [],
383
+ "reward_model_type": null,
384
+ "reward_model_revision": null,
385
+ "num_ppo_epochs": 4,
386
+ "whiten_rewards": false,
387
+ "kl_coef": 0.05,
388
+ "cliprange": 0.2,
389
+ "vf_coef": 0.1,
390
+ "cliprange_value": 0.2,
391
+ "gamma": 1.0,
392
+ "lam": 0.95,
393
+ "num_mini_batches": 1,
394
+ "local_rollout_forward_batch_size": 64,
395
+ "num_sample_generations": 10,
396
+ "response_length": 2048,
397
+ "missing_eos_penalty": null,
398
+ "vllm_gpu_memory_utilization": 0.9,
399
+ "vllm_tensor_parallel_size": 1,
400
+ "vllm_pipeline_parallel_size": 1,
401
+ "vllm_enable_expert_parallel": false,
402
+ "vllm_max_num_seqs": 256,
403
+ "vllm_max_model_len": null,
404
+ "vllm_disable_custom_all_reduce": true,
405
+ "vllm_enforce_eager": false,
406
+ "vllm_limit_mm_per_prompt": {},
407
+ "vllm_max_lora_rank": 16,
408
+ "vllm_enable_prefix_caching": true,
409
+ "vllm_use_async_engine": false,
410
+ "vllm_quantization": null,
411
+ "vllm_reasoning_parser": null,
412
+ "vllm_disable_cascade_attn": false,
413
+ "vllm_data_parallel_size": 1,
414
+ "gpu_memory_utilization": null,
415
+ "tensor_parallel_size": null,
416
+ "limit_mm_per_prompt": null,
417
+ "data_parallel_size": null,
418
+ "use_async_engine": null,
419
+ "epsilon": 0.2,
420
+ "epsilon_high": null,
421
+ "delta": null,
422
+ "vllm_mode": "server",
423
+ "vllm_server_base_url": null,
424
+ "vllm_server_host": [
425
+ "127.0.0.1"
426
+ ],
427
+ "vllm_server_port": [
428
+ 8000
429
+ ],
430
+ "vllm_server_timeout": 240.0,
431
+ "cosine_min_len_value_wrong": -0.5,
432
+ "cosine_max_len_value_wrong": 0.0,
433
+ "cosine_min_len_value_correct": 1.0,
434
+ "cosine_max_len_value_correct": 0.5,
435
+ "cosine_max_len": null,
436
+ "repetition_n_grams": 3,
437
+ "repetition_max_penalty": -1.0,
438
+ "reward_model_plugin": null,
439
+ "sync_ref_model": false,
440
+ "ref_model_sync_steps": 512,
441
+ "ref_model_mixup_alpha": 0.6,
442
+ "async_generate": false,
443
+ "sleep_level": 0,
444
+ "move_model_batches": null,
445
+ "offload_optimizer": true,
446
+ "offload_model": true,
447
+ "gc_collect_after_offload": false,
448
+ "multi_turn_func": null,
449
+ "multi_turn_scheduler": null,
450
+ "max_turns": null,
451
+ "completion_length_limit_scope": "per_round",
452
+ "vllm_server_pass_dataset": false,
453
+ "dynamic_sample": false,
454
+ "max_resample_times": 3,
455
+ "overlong_filter": false,
456
+ "soft_max_length": null,
457
+ "soft_cache_length": null,
458
+ "scale_rewards": true,
459
+ "log_entropy": false,
460
+ "top_entropy_quantile": 1.0,
461
+ "importance_sampling_level": "token",
462
+ "wandb_log_unique_prompts": null,
463
+ "generation_batch_size": null,
464
+ "steps_per_generation": null,
465
+ "num_generations": 6,
466
+ "reward_funcs": [
467
+ "combined_ambi_comet"
468
+ ],
469
+ "reward_weights": null,
470
+ "log_completions": true,
471
+ "use_vllm": true,
472
+ "num_iterations": 1,
473
+ "teacher_model": null,
474
+ "teacher_adapters": [],
475
+ "teacher_model_type": null,
476
+ "teacher_model_revision": null,
477
+ "rlhf_type": "grpo",
478
+ "ref_model": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
479
+ "ref_adapters": [],
480
+ "ref_model_type": "qwen2_5_vl",
481
+ "ref_model_revision": null,
482
+ "beta": 0.002,
483
+ "label_smoothing": 0,
484
+ "max_completion_length": 2048,
485
+ "rpo_alpha": null,
486
+ "ld_alpha": null,
487
+ "discopop_tau": 0.05,
488
+ "loss_weights": null,
489
+ "cpo_alpha": 1.0,
490
+ "simpo_gamma": 1,
491
+ "desirable_weight": 1.0,
492
+ "undesirable_weight": 1.0,
493
+ "center_rewards_coefficient": null,
494
+ "lmbda": 0.5,
495
+ "seq_kd": false,
496
+ "vllm_client": "<swift.trainers.rlhf_trainer.vllm_client.VLLMClient object at 0x7fed8a8676d0>",
497
+ "rank": 0,
498
+ "global_world_size": 3,
499
+ "local_world_size": 3,
500
+ "model_suffix": "checkpoint-280",
501
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
502
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fed8b3d9e10>, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
503
+ "model_dir": "/mnt/data/users/liamding/data/MMMT/lora/qwen2.5vl-7b-thinking_v2_full/v0-20250813-193210/checkpoint-280",
504
+ "hub": "<class 'swift.hub.hub.MSHub'>",
505
+ "evaluation_strategy": "steps",
506
+ "training_args": "GRPOConfig(output_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657', 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=4, per_device_eval_batch_size=4, 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=1e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=250, save_total_limit=10, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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=True, eval_steps=500, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/data/users/liamding/data/MMMT/ms-swift-main/output/qwen2.5vl-7b-thinking_v2_full_cls_comet_tau/v4-20250916-071657', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': 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=['swanlab'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=False, 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, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=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, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=6, max_completion_length=2048, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=24, steps_per_generation=2, temperature=1.0, top_p=0.9, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_server_base_url=None, vllm_mode='server', vllm_guided_decoding_regex=None, vllm_server_host=['127.0.0.1'], vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.9, vllm_tensor_parallel_size=1, beta=0.002, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, importance_sampling_level='token', reward_weights=None, scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=256, vllm_max_model_len=None, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, 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, reward_model=None, reward_model_plugin=None, async_generate=False, sleep_level=0, move_model_batches=None, offload_optimizer=True, offload_model=True, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, dataset_shuffle=True, stop_words=[])"
507
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
grpo/qwen2.5vl-7b-τ-checkpoint-1250/config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "text_config": {
33
+ "architectures": [
34
+ "Qwen2_5_VLForConditionalGeneration"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 3584,
41
+ "image_token_id": null,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention"
73
+ ],
74
+ "max_position_embeddings": 128000,
75
+ "max_window_layers": 28,
76
+ "model_type": "qwen2_5_vl_text",
77
+ "num_attention_heads": 28,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 4,
80
+ "pad_token_id": 151643,
81
+ "rms_norm_eps": 1e-06,
82
+ "rope_scaling": {
83
+ "mrope_section": [
84
+ 16,
85
+ 24,
86
+ 24
87
+ ],
88
+ "rope_type": "default",
89
+ "type": "default"
90
+ },
91
+ "rope_theta": 1000000.0,
92
+ "sliding_window": null,
93
+ "torch_dtype": "bfloat16",
94
+ "use_cache": false,
95
+ "use_sliding_window": false,
96
+ "video_token_id": null,
97
+ "vision_end_token_id": 151653,
98
+ "vision_start_token_id": 151652,
99
+ "vision_token_id": 151654,
100
+ "vocab_size": 152064
101
+ },
102
+ "tie_word_embeddings": false,
103
+ "torch_dtype": "bfloat16",
104
+ "transformers_version": "4.55.4",
105
+ "use_cache": false,
106
+ "use_sliding_window": false,
107
+ "video_token_id": 151656,
108
+ "vision_config": {
109
+ "depth": 32,
110
+ "fullatt_block_indexes": [
111
+ 7,
112
+ 15,
113
+ 23,
114
+ 31
115
+ ],
116
+ "hidden_act": "silu",
117
+ "hidden_size": 1280,
118
+ "in_channels": 3,
119
+ "in_chans": 3,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3420,
122
+ "model_type": "qwen2_5_vl",
123
+ "num_heads": 16,
124
+ "out_hidden_size": 3584,
125
+ "pad_token_id": 151643,
126
+ "patch_size": 14,
127
+ "spatial_merge_size": 2,
128
+ "spatial_patch_size": 14,
129
+ "temporal_patch_size": 2,
130
+ "tokens_per_second": 2,
131
+ "torch_dtype": "bfloat16",
132
+ "window_size": 112
133
+ },
134
+ "vision_end_token_id": 151653,
135
+ "vision_start_token_id": 151652,
136
+ "vision_token_id": 151654,
137
+ "vocab_size": 152064
138
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.55.4"
12
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step1250
grpo/qwen2.5vl-7b-τ-checkpoint-1250/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-τ-checkpoint-1250/model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 848896,
4
+ "total_size": 16584333312
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
grpo/qwen2.5vl-7b-τ-checkpoint-1250/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "size": {
36
+ "longest_edge": 12845056,
37
+ "shortest_edge": 3136
38
+ },
39
+ "size_divisor": null,
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
grpo/qwen2.5vl-7b-τ-checkpoint-1250/vocab.json ADDED
The diff for this file is too large to render. See raw diff