Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- args.json +451 -0
- chat_template.json +3 -0
- config.json +52 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +831 -0
- preprocessor_config.json +19 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +210 -0
- trainer_state.json +831 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
args.json
ADDED
|
@@ -0,0 +1,451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "Qwen2.5-VL-3B",
|
| 3 |
+
"model_type": "qwen2_5_vl",
|
| 4 |
+
"model_revision": null,
|
| 5 |
+
"task_type": "causal_lm",
|
| 6 |
+
"torch_dtype": "bfloat16",
|
| 7 |
+
"attn_impl": null,
|
| 8 |
+
"num_labels": null,
|
| 9 |
+
"problem_type": null,
|
| 10 |
+
"rope_scaling": null,
|
| 11 |
+
"device_map": null,
|
| 12 |
+
"max_memory": {},
|
| 13 |
+
"local_repo_path": null,
|
| 14 |
+
"template": "qwen2_5_vl",
|
| 15 |
+
"system": null,
|
| 16 |
+
"max_length": null,
|
| 17 |
+
"truncation_strategy": "left",
|
| 18 |
+
"max_pixels": 524288,
|
| 19 |
+
"tools_prompt": "react_en",
|
| 20 |
+
"norm_bbox": null,
|
| 21 |
+
"response_prefix": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"loss_scale": "last_round",
|
| 24 |
+
"sequence_parallel_size": 1,
|
| 25 |
+
"use_chat_template": true,
|
| 26 |
+
"template_backend": "swift",
|
| 27 |
+
"dataset": [
|
| 28 |
+
"/mnt/geogpt-doc/docparser/data/table/v1.4/table2latex_grpo_hard_5936_swift.jsonl"
|
| 29 |
+
],
|
| 30 |
+
"val_dataset": [],
|
| 31 |
+
"split_dataset_ratio": 0.0,
|
| 32 |
+
"data_seed": 42,
|
| 33 |
+
"dataset_num_proc": 4,
|
| 34 |
+
"dataset_shuffle": true,
|
| 35 |
+
"val_dataset_shuffle": false,
|
| 36 |
+
"streaming": false,
|
| 37 |
+
"interleave_prob": null,
|
| 38 |
+
"stopping_strategy": "first_exhausted",
|
| 39 |
+
"shuffle_buffer_size": 1000,
|
| 40 |
+
"enable_cache": false,
|
| 41 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 42 |
+
"columns": {},
|
| 43 |
+
"strict": false,
|
| 44 |
+
"remove_unused_columns": false,
|
| 45 |
+
"model_name": [
|
| 46 |
+
null,
|
| 47 |
+
null
|
| 48 |
+
],
|
| 49 |
+
"model_author": [
|
| 50 |
+
null,
|
| 51 |
+
null
|
| 52 |
+
],
|
| 53 |
+
"custom_dataset_info": [],
|
| 54 |
+
"quant_method": null,
|
| 55 |
+
"quant_bits": null,
|
| 56 |
+
"hqq_axis": null,
|
| 57 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 58 |
+
"bnb_4bit_quant_type": "nf4",
|
| 59 |
+
"bnb_4bit_use_double_quant": true,
|
| 60 |
+
"bnb_4bit_quant_storage": null,
|
| 61 |
+
"max_new_tokens": 64,
|
| 62 |
+
"temperature": 0.9,
|
| 63 |
+
"top_k": 50,
|
| 64 |
+
"top_p": 0.9,
|
| 65 |
+
"repetition_penalty": 1.0,
|
| 66 |
+
"num_beams": 1,
|
| 67 |
+
"stream": false,
|
| 68 |
+
"stop_words": [],
|
| 69 |
+
"logprobs": false,
|
| 70 |
+
"top_logprobs": null,
|
| 71 |
+
"ckpt_dir": null,
|
| 72 |
+
"load_dataset_config": null,
|
| 73 |
+
"lora_modules": [],
|
| 74 |
+
"tuner_backend": "peft",
|
| 75 |
+
"train_type": "full",
|
| 76 |
+
"adapters": [],
|
| 77 |
+
"external_plugins": [
|
| 78 |
+
"examples/train/grpo/plugin/plugin.py"
|
| 79 |
+
],
|
| 80 |
+
"seed": 42,
|
| 81 |
+
"model_kwargs": {},
|
| 82 |
+
"load_args": false,
|
| 83 |
+
"load_data_args": false,
|
| 84 |
+
"use_hf": false,
|
| 85 |
+
"hub_token": null,
|
| 86 |
+
"custom_register_path": [],
|
| 87 |
+
"ignore_args_error": false,
|
| 88 |
+
"use_swift_lora": false,
|
| 89 |
+
"output_dir": "/mnt/life-science-protein/test/code/ms-swift/output/v4-20250421-144136",
|
| 90 |
+
"overwrite_output_dir": false,
|
| 91 |
+
"do_train": false,
|
| 92 |
+
"do_eval": false,
|
| 93 |
+
"do_predict": false,
|
| 94 |
+
"eval_strategy": "epoch",
|
| 95 |
+
"prediction_loss_only": false,
|
| 96 |
+
"per_device_train_batch_size": 4,
|
| 97 |
+
"per_device_eval_batch_size": 4,
|
| 98 |
+
"per_gpu_train_batch_size": null,
|
| 99 |
+
"per_gpu_eval_batch_size": null,
|
| 100 |
+
"gradient_accumulation_steps": 2,
|
| 101 |
+
"eval_accumulation_steps": null,
|
| 102 |
+
"eval_delay": 0,
|
| 103 |
+
"torch_empty_cache_steps": null,
|
| 104 |
+
"learning_rate": 1e-06,
|
| 105 |
+
"weight_decay": 0.1,
|
| 106 |
+
"adam_beta1": 0.9,
|
| 107 |
+
"adam_beta2": 0.95,
|
| 108 |
+
"adam_epsilon": 1e-08,
|
| 109 |
+
"max_grad_norm": 1.0,
|
| 110 |
+
"num_train_epochs": 5.0,
|
| 111 |
+
"max_steps": -1,
|
| 112 |
+
"lr_scheduler_type": "cosine",
|
| 113 |
+
"lr_scheduler_kwargs": null,
|
| 114 |
+
"warmup_ratio": 0.05,
|
| 115 |
+
"warmup_steps": 0,
|
| 116 |
+
"log_level": "passive",
|
| 117 |
+
"log_level_replica": "warning",
|
| 118 |
+
"log_on_each_node": true,
|
| 119 |
+
"logging_dir": "/mnt/life-science-protein/test/code/ms-swift/output/v4-20250421-144136/runs",
|
| 120 |
+
"logging_strategy": "steps",
|
| 121 |
+
"logging_first_step": true,
|
| 122 |
+
"logging_steps": 5,
|
| 123 |
+
"logging_nan_inf_filter": true,
|
| 124 |
+
"save_strategy": "epoch",
|
| 125 |
+
"save_steps": 500,
|
| 126 |
+
"save_total_limit": 100,
|
| 127 |
+
"save_safetensors": true,
|
| 128 |
+
"save_on_each_node": false,
|
| 129 |
+
"save_only_model": true,
|
| 130 |
+
"restore_callback_states_from_checkpoint": false,
|
| 131 |
+
"no_cuda": false,
|
| 132 |
+
"use_cpu": false,
|
| 133 |
+
"use_mps_device": false,
|
| 134 |
+
"jit_mode_eval": false,
|
| 135 |
+
"use_ipex": false,
|
| 136 |
+
"bf16": true,
|
| 137 |
+
"fp16": false,
|
| 138 |
+
"fp16_opt_level": "O1",
|
| 139 |
+
"half_precision_backend": "auto",
|
| 140 |
+
"bf16_full_eval": false,
|
| 141 |
+
"fp16_full_eval": false,
|
| 142 |
+
"tf32": null,
|
| 143 |
+
"local_rank": 0,
|
| 144 |
+
"ddp_backend": null,
|
| 145 |
+
"tpu_num_cores": null,
|
| 146 |
+
"tpu_metrics_debug": false,
|
| 147 |
+
"debug": null,
|
| 148 |
+
"dataloader_drop_last": false,
|
| 149 |
+
"eval_steps": null,
|
| 150 |
+
"dataloader_num_workers": 4,
|
| 151 |
+
"dataloader_prefetch_factor": null,
|
| 152 |
+
"past_index": -1,
|
| 153 |
+
"run_name": null,
|
| 154 |
+
"disable_tqdm": null,
|
| 155 |
+
"label_names": null,
|
| 156 |
+
"load_best_model_at_end": false,
|
| 157 |
+
"metric_for_best_model": "reward",
|
| 158 |
+
"greater_is_better": true,
|
| 159 |
+
"ignore_data_skip": false,
|
| 160 |
+
"fsdp": "",
|
| 161 |
+
"fsdp_min_num_params": 0,
|
| 162 |
+
"fsdp_config": null,
|
| 163 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 164 |
+
"accelerator_config": {
|
| 165 |
+
"dispatch_batches": false
|
| 166 |
+
},
|
| 167 |
+
"deepspeed": {
|
| 168 |
+
"fp16": {
|
| 169 |
+
"enabled": "auto",
|
| 170 |
+
"loss_scale": 0,
|
| 171 |
+
"loss_scale_window": 1000,
|
| 172 |
+
"initial_scale_power": 16,
|
| 173 |
+
"hysteresis": 2,
|
| 174 |
+
"min_loss_scale": 1
|
| 175 |
+
},
|
| 176 |
+
"bf16": {
|
| 177 |
+
"enabled": "auto"
|
| 178 |
+
},
|
| 179 |
+
"zero_optimization": {
|
| 180 |
+
"stage": 3,
|
| 181 |
+
"offload_optimizer": {
|
| 182 |
+
"device": "none",
|
| 183 |
+
"pin_memory": true
|
| 184 |
+
},
|
| 185 |
+
"offload_param": {
|
| 186 |
+
"device": "none",
|
| 187 |
+
"pin_memory": true
|
| 188 |
+
},
|
| 189 |
+
"overlap_comm": false,
|
| 190 |
+
"contiguous_gradients": true,
|
| 191 |
+
"sub_group_size": 1000000000.0,
|
| 192 |
+
"reduce_bucket_size": "auto",
|
| 193 |
+
"zero_quantized_weights": false,
|
| 194 |
+
"zero_quantized_gradients": false,
|
| 195 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 196 |
+
"stage3_param_persistence_threshold": "auto",
|
| 197 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 198 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 199 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 200 |
+
},
|
| 201 |
+
"gradient_accumulation_steps": "auto",
|
| 202 |
+
"gradient_clipping": "auto",
|
| 203 |
+
"steps_per_print": 2000,
|
| 204 |
+
"train_batch_size": "auto",
|
| 205 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 206 |
+
"wall_clock_breakdown": false
|
| 207 |
+
},
|
| 208 |
+
"label_smoothing_factor": 0.0,
|
| 209 |
+
"optim": "adamw_torch",
|
| 210 |
+
"optim_args": null,
|
| 211 |
+
"adafactor": false,
|
| 212 |
+
"group_by_length": false,
|
| 213 |
+
"length_column_name": "length",
|
| 214 |
+
"report_to": [
|
| 215 |
+
"tensorboard"
|
| 216 |
+
],
|
| 217 |
+
"ddp_find_unused_parameters": null,
|
| 218 |
+
"ddp_bucket_cap_mb": null,
|
| 219 |
+
"ddp_broadcast_buffers": null,
|
| 220 |
+
"dataloader_pin_memory": true,
|
| 221 |
+
"dataloader_persistent_workers": false,
|
| 222 |
+
"skip_memory_metrics": true,
|
| 223 |
+
"use_legacy_prediction_loop": false,
|
| 224 |
+
"push_to_hub": false,
|
| 225 |
+
"resume_from_checkpoint": null,
|
| 226 |
+
"hub_model_id": null,
|
| 227 |
+
"hub_strategy": "every_save",
|
| 228 |
+
"hub_private_repo": null,
|
| 229 |
+
"hub_always_push": false,
|
| 230 |
+
"gradient_checkpointing": true,
|
| 231 |
+
"gradient_checkpointing_kwargs": null,
|
| 232 |
+
"include_inputs_for_metrics": false,
|
| 233 |
+
"include_for_metrics": [],
|
| 234 |
+
"eval_do_concat_batches": true,
|
| 235 |
+
"fp16_backend": "auto",
|
| 236 |
+
"evaluation_strategy": "epoch",
|
| 237 |
+
"push_to_hub_model_id": null,
|
| 238 |
+
"push_to_hub_organization": null,
|
| 239 |
+
"push_to_hub_token": null,
|
| 240 |
+
"mp_parameters": "",
|
| 241 |
+
"auto_find_batch_size": false,
|
| 242 |
+
"full_determinism": false,
|
| 243 |
+
"torchdynamo": null,
|
| 244 |
+
"ray_scope": "last",
|
| 245 |
+
"ddp_timeout": 1800,
|
| 246 |
+
"torch_compile": false,
|
| 247 |
+
"torch_compile_backend": null,
|
| 248 |
+
"torch_compile_mode": null,
|
| 249 |
+
"dispatch_batches": null,
|
| 250 |
+
"split_batches": null,
|
| 251 |
+
"include_tokens_per_second": false,
|
| 252 |
+
"include_num_input_tokens_seen": false,
|
| 253 |
+
"neftune_noise_alpha": null,
|
| 254 |
+
"optim_target_modules": null,
|
| 255 |
+
"batch_eval_metrics": false,
|
| 256 |
+
"eval_on_start": false,
|
| 257 |
+
"use_liger_kernel": false,
|
| 258 |
+
"eval_use_gather_object": false,
|
| 259 |
+
"average_tokens_across_devices": false,
|
| 260 |
+
"sortish_sampler": false,
|
| 261 |
+
"predict_with_generate": false,
|
| 262 |
+
"generation_max_length": null,
|
| 263 |
+
"generation_num_beams": null,
|
| 264 |
+
"generation_config": null,
|
| 265 |
+
"check_model": true,
|
| 266 |
+
"acc_strategy": "token",
|
| 267 |
+
"train_dataloader_shuffle": true,
|
| 268 |
+
"metric_warmup_step": 0,
|
| 269 |
+
"fsdp_num": 1,
|
| 270 |
+
"acc_steps": 1,
|
| 271 |
+
"eval_use_evalscope": false,
|
| 272 |
+
"eval_datasets": [],
|
| 273 |
+
"eval_limit": null,
|
| 274 |
+
"eval_datasets_args": null,
|
| 275 |
+
"eval_generation_config": null,
|
| 276 |
+
"freeze_parameters": [
|
| 277 |
+
"visual",
|
| 278 |
+
"visual",
|
| 279 |
+
"visual.merger"
|
| 280 |
+
],
|
| 281 |
+
"freeze_parameters_ratio": 0.0,
|
| 282 |
+
"trainable_parameters": [],
|
| 283 |
+
"freeze_llm": false,
|
| 284 |
+
"freeze_vit": true,
|
| 285 |
+
"freeze_aligner": true,
|
| 286 |
+
"target_modules": [
|
| 287 |
+
"all-linear"
|
| 288 |
+
],
|
| 289 |
+
"target_regex": null,
|
| 290 |
+
"modules_to_save": [],
|
| 291 |
+
"lora_rank": 8,
|
| 292 |
+
"lora_alpha": 32,
|
| 293 |
+
"lora_dropout": 0.05,
|
| 294 |
+
"lora_bias": "none",
|
| 295 |
+
"lora_dtype": null,
|
| 296 |
+
"lorap_lr_ratio": null,
|
| 297 |
+
"use_rslora": false,
|
| 298 |
+
"use_dora": false,
|
| 299 |
+
"lora_ga_batch_size": 2,
|
| 300 |
+
"lora_ga_iters": 2,
|
| 301 |
+
"lora_ga_max_length": 1024,
|
| 302 |
+
"lora_ga_direction": "ArB2r",
|
| 303 |
+
"lora_ga_scale": "stable",
|
| 304 |
+
"lora_ga_stable_gamma": 16,
|
| 305 |
+
"init_weights": true,
|
| 306 |
+
"fourier_n_frequency": 2000,
|
| 307 |
+
"fourier_scaling": 300.0,
|
| 308 |
+
"boft_block_size": 4,
|
| 309 |
+
"boft_block_num": 0,
|
| 310 |
+
"boft_n_butterfly_factor": 1,
|
| 311 |
+
"boft_dropout": 0.0,
|
| 312 |
+
"vera_rank": 256,
|
| 313 |
+
"vera_projection_prng_key": 0,
|
| 314 |
+
"vera_dropout": 0.0,
|
| 315 |
+
"vera_d_initial": 0.1,
|
| 316 |
+
"adapter_act": "gelu",
|
| 317 |
+
"adapter_length": 128,
|
| 318 |
+
"use_galore": false,
|
| 319 |
+
"galore_target_modules": null,
|
| 320 |
+
"galore_rank": 128,
|
| 321 |
+
"galore_update_proj_gap": 50,
|
| 322 |
+
"galore_scale": 1.0,
|
| 323 |
+
"galore_proj_type": "std",
|
| 324 |
+
"galore_optim_per_parameter": false,
|
| 325 |
+
"galore_with_embedding": false,
|
| 326 |
+
"galore_quantization": false,
|
| 327 |
+
"galore_proj_quant": false,
|
| 328 |
+
"galore_proj_bits": 4,
|
| 329 |
+
"galore_proj_group_size": 256,
|
| 330 |
+
"galore_cos_threshold": 0.4,
|
| 331 |
+
"galore_gamma_proj": 2,
|
| 332 |
+
"galore_queue_size": 5,
|
| 333 |
+
"adalora_target_r": 8,
|
| 334 |
+
"adalora_init_r": 12,
|
| 335 |
+
"adalora_tinit": 0,
|
| 336 |
+
"adalora_tfinal": 0,
|
| 337 |
+
"adalora_deltaT": 1,
|
| 338 |
+
"adalora_beta1": 0.85,
|
| 339 |
+
"adalora_beta2": 0.85,
|
| 340 |
+
"adalora_orth_reg_weight": 0.5,
|
| 341 |
+
"llamapro_num_new_blocks": 4,
|
| 342 |
+
"llamapro_num_groups": null,
|
| 343 |
+
"lisa_activated_layers": 0,
|
| 344 |
+
"lisa_step_interval": 20,
|
| 345 |
+
"reft_layer_key": null,
|
| 346 |
+
"reft_layers": null,
|
| 347 |
+
"reft_rank": 4,
|
| 348 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 349 |
+
"reft_args": null,
|
| 350 |
+
"swanlab_token": null,
|
| 351 |
+
"swanlab_project": null,
|
| 352 |
+
"swanlab_workspace": null,
|
| 353 |
+
"swanlab_exp_name": null,
|
| 354 |
+
"swanlab_mode": "cloud",
|
| 355 |
+
"add_version": true,
|
| 356 |
+
"resume_only_model": false,
|
| 357 |
+
"create_checkpoint_symlink": false,
|
| 358 |
+
"packing": false,
|
| 359 |
+
"lazy_tokenize": true,
|
| 360 |
+
"loss_type": null,
|
| 361 |
+
"optimizer": null,
|
| 362 |
+
"metric": null,
|
| 363 |
+
"zero_hpz_partition_size": null,
|
| 364 |
+
"reward_model": null,
|
| 365 |
+
"reward_adapters": [],
|
| 366 |
+
"reward_model_type": null,
|
| 367 |
+
"reward_model_revision": null,
|
| 368 |
+
"num_ppo_epochs": 4,
|
| 369 |
+
"whiten_rewards": false,
|
| 370 |
+
"kl_coef": 0.05,
|
| 371 |
+
"cliprange": 0.2,
|
| 372 |
+
"vf_coef": 0.1,
|
| 373 |
+
"cliprange_value": 0.2,
|
| 374 |
+
"gamma": 1.0,
|
| 375 |
+
"lam": 0.95,
|
| 376 |
+
"num_mini_batches": 1,
|
| 377 |
+
"local_rollout_forward_batch_size": 64,
|
| 378 |
+
"num_sample_generations": 10,
|
| 379 |
+
"response_length": 512,
|
| 380 |
+
"missing_eos_penalty": null,
|
| 381 |
+
"epsilon": 0.2,
|
| 382 |
+
"epsilon_high": null,
|
| 383 |
+
"num_infer_workers": 1,
|
| 384 |
+
"vllm_max_num_seqs": 256,
|
| 385 |
+
"vllm_enforce_eager": false,
|
| 386 |
+
"vllm_limit_mm_per_prompt": null,
|
| 387 |
+
"vllm_enable_prefix_caching": true,
|
| 388 |
+
"cosine_min_len_value_wrong": -0.5,
|
| 389 |
+
"cosine_max_len_value_wrong": 0.0,
|
| 390 |
+
"cosine_min_len_value_correct": 1.0,
|
| 391 |
+
"cosine_max_len_value_correct": 0.5,
|
| 392 |
+
"cosine_max_len": null,
|
| 393 |
+
"repetition_n_grams": 3,
|
| 394 |
+
"repetition_max_penalty": -1.0,
|
| 395 |
+
"use_lmdeploy": false,
|
| 396 |
+
"lmdeploy_device": "auto",
|
| 397 |
+
"lmdeploy_session_len": null,
|
| 398 |
+
"lmdeploy_cache_max_entry_count": 0.8,
|
| 399 |
+
"async_generate": false,
|
| 400 |
+
"tensor_parallel_size": 1,
|
| 401 |
+
"sleep_level": 0,
|
| 402 |
+
"move_model_batches": null,
|
| 403 |
+
"offload_optimizer": false,
|
| 404 |
+
"offload_model": false,
|
| 405 |
+
"gc_collect_after_offload": false,
|
| 406 |
+
"multi_turn_func": null,
|
| 407 |
+
"mini_batch_size": null,
|
| 408 |
+
"dynamic_sample": false,
|
| 409 |
+
"max_resample_times": 3,
|
| 410 |
+
"overlong_filter": false,
|
| 411 |
+
"soft_max_length": null,
|
| 412 |
+
"soft_cache_length": null,
|
| 413 |
+
"scale_rewards": true,
|
| 414 |
+
"wandb_log_unique_prompts": null,
|
| 415 |
+
"num_generations": 4,
|
| 416 |
+
"max_completion_length": 3000,
|
| 417 |
+
"ds3_gather_for_generation": true,
|
| 418 |
+
"reward_funcs": [
|
| 419 |
+
"external_table2latex_acc",
|
| 420 |
+
"external_table2latex_form"
|
| 421 |
+
],
|
| 422 |
+
"reward_weights": null,
|
| 423 |
+
"log_completions": false,
|
| 424 |
+
"use_vllm": false,
|
| 425 |
+
"vllm_device": [
|
| 426 |
+
"auto"
|
| 427 |
+
],
|
| 428 |
+
"vllm_gpu_memory_utilization": 0.9,
|
| 429 |
+
"vllm_max_model_len": null,
|
| 430 |
+
"num_iterations": 1,
|
| 431 |
+
"rlhf_type": "grpo",
|
| 432 |
+
"ref_model": "Qwen2.5-VL-3B",
|
| 433 |
+
"ref_model_type": "qwen2_5_vl",
|
| 434 |
+
"ref_model_revision": null,
|
| 435 |
+
"beta": 0.04,
|
| 436 |
+
"label_smoothing": 0,
|
| 437 |
+
"rpo_alpha": 1.0,
|
| 438 |
+
"cpo_alpha": 1.0,
|
| 439 |
+
"simpo_gamma": 1,
|
| 440 |
+
"desirable_weight": 1.0,
|
| 441 |
+
"undesirable_weight": 1.0,
|
| 442 |
+
"rank": 0,
|
| 443 |
+
"global_world_size": 16,
|
| 444 |
+
"local_world_size": 8,
|
| 445 |
+
"model_suffix": "Qwen2.5-VL-3B",
|
| 446 |
+
"model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/life-science-protein/test/code/ms-swift/Qwen2.5-VL-3B', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
|
| 447 |
+
"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 0x7f88ebfd3b50>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
|
| 448 |
+
"model_dir": "/mnt/life-science-protein/test/code/ms-swift/Qwen2.5-VL-3B",
|
| 449 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 450 |
+
"training_args": "GRPOConfig(output_dir='/mnt/life-science-protein/test/code/ms-swift/output/v4-20250421-144136', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, 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=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/life-science-protein/test/code/ms-swift/output/v4-20250421-144136/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=100, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=True, eval_steps=None, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/life-science-protein/test/code/ms-swift/output/v4-20250421-144136', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 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=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=<IntervalStrategy.NO: 'no'>, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, max_prompt_length=512, num_generations=4, max_completion_length=3000, ds3_gather_for_generation=True, temperature=0.9, top_p=0.9, top_k=50, min_p=None, repetition_penalty=1.0, cache_implementation=None, use_vllm=False, vllm_server_host='0.0.0.0', vllm_server_port=8000, vllm_server_timeout=120.0, vllm_guided_decoding_regex=None, beta=0.04, num_iterations=1, epsilon=0.2, epsilon_high=None, reward_weights=None, scale_rewards=True, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, log_completions=False, vllm_device=['auto'], vllm_gpu_memory_utilization=0.9, vllm_dtype=None, vllm_max_model_len=None, vllm_enable_prefix_caching=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None, num_infer_workers=1, vllm_max_num_seqs=256, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=3000, repetition_n_grams=3, repetition_max_penalty=-1.0, use_lmdeploy=False, lmdeploy_device='auto', lmdeploy_session_len=None, lmdeploy_cache_max_entry_count=0.8, async_generate=False, tensor_parallel_size=1, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, gc_collect_after_offload=False, multi_turn_func=None, mini_batch_size=None, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, wandb_log_unique_prompts=None, stop_words=[])"
|
| 451 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/life-science-protein/test/code/ms-swift/Qwen2.5-VL-3B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 70,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"pad_token_id": 151643,
|
| 21 |
+
"rms_norm_eps": 1e-06,
|
| 22 |
+
"rope_scaling": {
|
| 23 |
+
"mrope_section": [
|
| 24 |
+
16,
|
| 25 |
+
24,
|
| 26 |
+
24
|
| 27 |
+
],
|
| 28 |
+
"rope_type": "default",
|
| 29 |
+
"type": "default"
|
| 30 |
+
},
|
| 31 |
+
"rope_theta": 1000000.0,
|
| 32 |
+
"sliding_window": 32768,
|
| 33 |
+
"tie_word_embeddings": true,
|
| 34 |
+
"torch_dtype": "bfloat16",
|
| 35 |
+
"transformers_version": "4.49.0",
|
| 36 |
+
"use_cache": false,
|
| 37 |
+
"use_sliding_window": false,
|
| 38 |
+
"video_token_id": 151656,
|
| 39 |
+
"vision_config": {
|
| 40 |
+
"hidden_size": 1280,
|
| 41 |
+
"in_chans": 3,
|
| 42 |
+
"model_type": "qwen2_5_vl",
|
| 43 |
+
"out_hidden_size": 2048,
|
| 44 |
+
"spatial_patch_size": 14,
|
| 45 |
+
"tokens_per_second": 2,
|
| 46 |
+
"torch_dtype": "bfloat16"
|
| 47 |
+
},
|
| 48 |
+
"vision_end_token_id": 151653,
|
| 49 |
+
"vision_start_token_id": 151652,
|
| 50 |
+
"vision_token_id": 151654,
|
| 51 |
+
"vocab_size": 151936
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.1,
|
| 11 |
+
"top_k": 1,
|
| 12 |
+
"top_p": 0.001,
|
| 13 |
+
"transformers_version": "4.49.0"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e8a24c2eda39b643dec2c491e853a335c0dad05a3dc5284002fb0e99fc5495e
|
| 3 |
+
size 4997750760
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26cf70677a0c36f4a2e6f12c8b178d2c079785509ab7500c8d961d6591a67cd9
|
| 3 |
+
size 2511587184
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,831 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7509245952
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 763 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 775 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 799 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 810 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 811 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 816 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 822 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 823 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 825 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 827 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 829 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
| 830 |
+
}
|
| 831 |
+
}
|
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 |
+
}
|
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 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"padding_side": "right",
|
| 206 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 207 |
+
"split_special_tokens": false,
|
| 208 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 209 |
+
"unk_token": null
|
| 210 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,831 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9973045822102425,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 185,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"clip_ratio": 0.0,
|
| 13 |
+
"completions/clipped_ratio": 0.0,
|
| 14 |
+
"completions/max_length": 3001.0,
|
| 15 |
+
"completions/mean_length": 1635.390625,
|
| 16 |
+
"completions/min_length": 880.0,
|
| 17 |
+
"epoch": 0.005390835579514825,
|
| 18 |
+
"grad_norm": 0.07817294615231643,
|
| 19 |
+
"kl": 0.0,
|
| 20 |
+
"learning_rate": 2.127659574468085e-08,
|
| 21 |
+
"loss": 0.01464410312473774,
|
| 22 |
+
"memory(GiB)": 53.08,
|
| 23 |
+
"reward": 1.3704201579093933,
|
| 24 |
+
"reward_std": 0.19254888594150543,
|
| 25 |
+
"rewards/Table2LatexAcc/mean": 0.5549997389316559,
|
| 26 |
+
"rewards/Table2LatexAcc/std": 0.2269514873623848,
|
| 27 |
+
"rewards/Table2Latexform/mean": 0.815420389175415,
|
| 28 |
+
"rewards/Table2Latexform/std": 0.27713412046432495,
|
| 29 |
+
"step": 1,
|
| 30 |
+
"train_speed(iter/s)": 0.003012
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"clip_ratio": 0.0,
|
| 34 |
+
"completions/clipped_ratio": 0.0,
|
| 35 |
+
"completions/max_length": 2923.875,
|
| 36 |
+
"completions/mean_length": 1629.7890625,
|
| 37 |
+
"completions/min_length": 886.0,
|
| 38 |
+
"epoch": 0.026954177897574125,
|
| 39 |
+
"grad_norm": 0.07213148347345341,
|
| 40 |
+
"kl": 1.5087425708770752e-05,
|
| 41 |
+
"learning_rate": 1.0638297872340425e-07,
|
| 42 |
+
"loss": 0.028215568512678146,
|
| 43 |
+
"memory(GiB)": 74.0,
|
| 44 |
+
"reward": 1.3842923939228058,
|
| 45 |
+
"reward_std": 0.18567332532256842,
|
| 46 |
+
"rewards/Table2LatexAcc/mean": 0.5712194591760635,
|
| 47 |
+
"rewards/Table2LatexAcc/std": 0.19849798548966646,
|
| 48 |
+
"rewards/Table2Latexform/mean": 0.8130729347467422,
|
| 49 |
+
"rewards/Table2Latexform/std": 0.2439529187977314,
|
| 50 |
+
"step": 5,
|
| 51 |
+
"train_speed(iter/s)": 0.003096
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"clip_ratio": 0.0,
|
| 55 |
+
"completions/clipped_ratio": 0.0,
|
| 56 |
+
"completions/max_length": 2889.2,
|
| 57 |
+
"completions/mean_length": 1723.5890625,
|
| 58 |
+
"completions/min_length": 962.5,
|
| 59 |
+
"epoch": 0.05390835579514825,
|
| 60 |
+
"grad_norm": 0.06916726038351133,
|
| 61 |
+
"kl": 1.736283302307129e-05,
|
| 62 |
+
"learning_rate": 2.127659574468085e-07,
|
| 63 |
+
"loss": 0.019673459231853485,
|
| 64 |
+
"memory(GiB)": 74.0,
|
| 65 |
+
"reward": 1.3981751084327698,
|
| 66 |
+
"reward_std": 0.16928213015198706,
|
| 67 |
+
"rewards/Table2LatexAcc/mean": 0.573980861902237,
|
| 68 |
+
"rewards/Table2LatexAcc/std": 0.19604488760232924,
|
| 69 |
+
"rewards/Table2Latexform/mean": 0.8241942763328552,
|
| 70 |
+
"rewards/Table2Latexform/std": 0.23927551954984666,
|
| 71 |
+
"step": 10,
|
| 72 |
+
"train_speed(iter/s)": 0.003101
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"clip_ratio": 0.0,
|
| 76 |
+
"completions/clipped_ratio": 0.0,
|
| 77 |
+
"completions/max_length": 2915.4,
|
| 78 |
+
"completions/mean_length": 1641.03125,
|
| 79 |
+
"completions/min_length": 704.9,
|
| 80 |
+
"epoch": 0.08086253369272237,
|
| 81 |
+
"grad_norm": 0.07279863906405569,
|
| 82 |
+
"kl": 2.1731853485107423e-05,
|
| 83 |
+
"learning_rate": 3.1914893617021275e-07,
|
| 84 |
+
"loss": 0.02381864786148071,
|
| 85 |
+
"memory(GiB)": 74.0,
|
| 86 |
+
"reward": 1.379032826423645,
|
| 87 |
+
"reward_std": 0.15062467977404595,
|
| 88 |
+
"rewards/Table2LatexAcc/mean": 0.5421488165855408,
|
| 89 |
+
"rewards/Table2LatexAcc/std": 0.19123097956180574,
|
| 90 |
+
"rewards/Table2Latexform/mean": 0.8368840157985687,
|
| 91 |
+
"rewards/Table2Latexform/std": 0.21790579557418824,
|
| 92 |
+
"step": 15,
|
| 93 |
+
"train_speed(iter/s)": 0.003068
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"clip_ratio": 0.0,
|
| 97 |
+
"completions/clipped_ratio": 0.0,
|
| 98 |
+
"completions/max_length": 2961.5,
|
| 99 |
+
"completions/mean_length": 1699.853125,
|
| 100 |
+
"completions/min_length": 861.8,
|
| 101 |
+
"epoch": 0.1078167115902965,
|
| 102 |
+
"grad_norm": 0.07154949573308267,
|
| 103 |
+
"kl": 2.1332502365112303e-05,
|
| 104 |
+
"learning_rate": 4.25531914893617e-07,
|
| 105 |
+
"loss": 0.027176868915557862,
|
| 106 |
+
"memory(GiB)": 74.0,
|
| 107 |
+
"reward": 1.3628795862197876,
|
| 108 |
+
"reward_std": 0.19128143787384033,
|
| 109 |
+
"rewards/Table2LatexAcc/mean": 0.5719542324542999,
|
| 110 |
+
"rewards/Table2LatexAcc/std": 0.1954931139945984,
|
| 111 |
+
"rewards/Table2Latexform/mean": 0.7909253478050232,
|
| 112 |
+
"rewards/Table2Latexform/std": 0.278898648917675,
|
| 113 |
+
"step": 20,
|
| 114 |
+
"train_speed(iter/s)": 0.003057
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"clip_ratio": 0.0,
|
| 118 |
+
"completions/clipped_ratio": 0.0,
|
| 119 |
+
"completions/max_length": 2639.0,
|
| 120 |
+
"completions/mean_length": 1594.8921875,
|
| 121 |
+
"completions/min_length": 790.5,
|
| 122 |
+
"epoch": 0.1347708894878706,
|
| 123 |
+
"grad_norm": 0.13131531927012402,
|
| 124 |
+
"kl": 2.13623046875e-05,
|
| 125 |
+
"learning_rate": 5.319148936170212e-07,
|
| 126 |
+
"loss": 0.01629452407360077,
|
| 127 |
+
"memory(GiB)": 74.0,
|
| 128 |
+
"reward": 1.4447253465652465,
|
| 129 |
+
"reward_std": 0.15758238062262536,
|
| 130 |
+
"rewards/Table2LatexAcc/mean": 0.6045001387596131,
|
| 131 |
+
"rewards/Table2LatexAcc/std": 0.18096636980772018,
|
| 132 |
+
"rewards/Table2Latexform/mean": 0.840225213766098,
|
| 133 |
+
"rewards/Table2Latexform/std": 0.22630088329315184,
|
| 134 |
+
"step": 25,
|
| 135 |
+
"train_speed(iter/s)": 0.003093
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"clip_ratio": 0.0,
|
| 139 |
+
"completions/clipped_ratio": 0.0,
|
| 140 |
+
"completions/max_length": 2905.0,
|
| 141 |
+
"completions/mean_length": 1642.709375,
|
| 142 |
+
"completions/min_length": 804.4,
|
| 143 |
+
"epoch": 0.16172506738544473,
|
| 144 |
+
"grad_norm": 0.06595082858040417,
|
| 145 |
+
"kl": 2.499222755432129e-05,
|
| 146 |
+
"learning_rate": 6.382978723404255e-07,
|
| 147 |
+
"loss": 0.027088361978530883,
|
| 148 |
+
"memory(GiB)": 74.0,
|
| 149 |
+
"reward": 1.3934171557426454,
|
| 150 |
+
"reward_std": 0.17848547250032426,
|
| 151 |
+
"rewards/Table2LatexAcc/mean": 0.5714545011520386,
|
| 152 |
+
"rewards/Table2LatexAcc/std": 0.1947036311030388,
|
| 153 |
+
"rewards/Table2Latexform/mean": 0.8219626545906067,
|
| 154 |
+
"rewards/Table2Latexform/std": 0.26306993812322615,
|
| 155 |
+
"step": 30,
|
| 156 |
+
"train_speed(iter/s)": 0.003089
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"clip_ratio": 0.0,
|
| 160 |
+
"completions/clipped_ratio": 0.0,
|
| 161 |
+
"completions/max_length": 2934.1,
|
| 162 |
+
"completions/mean_length": 1610.1421875,
|
| 163 |
+
"completions/min_length": 755.4,
|
| 164 |
+
"epoch": 0.18867924528301888,
|
| 165 |
+
"grad_norm": 0.06925838510518537,
|
| 166 |
+
"kl": 4.082918167114258e-05,
|
| 167 |
+
"learning_rate": 7.446808510638297e-07,
|
| 168 |
+
"loss": 0.026965773105621337,
|
| 169 |
+
"memory(GiB)": 74.0,
|
| 170 |
+
"reward": 1.3997071743011475,
|
| 171 |
+
"reward_std": 0.1628158211708069,
|
| 172 |
+
"rewards/Table2LatexAcc/mean": 0.5788642525672912,
|
| 173 |
+
"rewards/Table2LatexAcc/std": 0.1913457229733467,
|
| 174 |
+
"rewards/Table2Latexform/mean": 0.8208428978919983,
|
| 175 |
+
"rewards/Table2Latexform/std": 0.24103213250637054,
|
| 176 |
+
"step": 35,
|
| 177 |
+
"train_speed(iter/s)": 0.003093
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"clip_ratio": 0.0,
|
| 181 |
+
"completions/clipped_ratio": 0.0,
|
| 182 |
+
"completions/max_length": 2921.4,
|
| 183 |
+
"completions/mean_length": 1588.996875,
|
| 184 |
+
"completions/min_length": 877.3,
|
| 185 |
+
"epoch": 0.215633423180593,
|
| 186 |
+
"grad_norm": 0.07126416986934427,
|
| 187 |
+
"kl": 7.665157318115234e-05,
|
| 188 |
+
"learning_rate": 8.51063829787234e-07,
|
| 189 |
+
"loss": 0.019620102643966675,
|
| 190 |
+
"memory(GiB)": 74.0,
|
| 191 |
+
"reward": 1.3808103442192077,
|
| 192 |
+
"reward_std": 0.16285659074783326,
|
| 193 |
+
"rewards/Table2LatexAcc/mean": 0.575913542509079,
|
| 194 |
+
"rewards/Table2LatexAcc/std": 0.1952654466032982,
|
| 195 |
+
"rewards/Table2Latexform/mean": 0.8048967957496643,
|
| 196 |
+
"rewards/Table2Latexform/std": 0.26039574593305587,
|
| 197 |
+
"step": 40,
|
| 198 |
+
"train_speed(iter/s)": 0.003098
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"clip_ratio": 0.0,
|
| 202 |
+
"completions/clipped_ratio": 0.0,
|
| 203 |
+
"completions/max_length": 2788.6,
|
| 204 |
+
"completions/mean_length": 1593.7375,
|
| 205 |
+
"completions/min_length": 759.5,
|
| 206 |
+
"epoch": 0.24258760107816713,
|
| 207 |
+
"grad_norm": 0.08624615635734913,
|
| 208 |
+
"kl": 0.0001492023468017578,
|
| 209 |
+
"learning_rate": 9.574468085106384e-07,
|
| 210 |
+
"loss": 0.015057304501533508,
|
| 211 |
+
"memory(GiB)": 74.0,
|
| 212 |
+
"reward": 1.4499380350112916,
|
| 213 |
+
"reward_std": 0.13701159432530402,
|
| 214 |
+
"rewards/Table2LatexAcc/mean": 0.6036670506000519,
|
| 215 |
+
"rewards/Table2LatexAcc/std": 0.19481946676969528,
|
| 216 |
+
"rewards/Table2Latexform/mean": 0.8462709665298462,
|
| 217 |
+
"rewards/Table2Latexform/std": 0.2081604614853859,
|
| 218 |
+
"step": 45,
|
| 219 |
+
"train_speed(iter/s)": 0.00312
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"clip_ratio": 0.0,
|
| 223 |
+
"completions/clipped_ratio": 0.0,
|
| 224 |
+
"completions/max_length": 2874.3,
|
| 225 |
+
"completions/mean_length": 1671.671875,
|
| 226 |
+
"completions/min_length": 803.0,
|
| 227 |
+
"epoch": 0.2695417789757412,
|
| 228 |
+
"grad_norm": 0.0716967712923244,
|
| 229 |
+
"kl": 0.00020017623901367188,
|
| 230 |
+
"learning_rate": 9.99971193595054e-07,
|
| 231 |
+
"loss": 0.01770862340927124,
|
| 232 |
+
"memory(GiB)": 74.0,
|
| 233 |
+
"reward": 1.4406983852386475,
|
| 234 |
+
"reward_std": 0.13970830887556077,
|
| 235 |
+
"rewards/Table2LatexAcc/mean": 0.5882811903953552,
|
| 236 |
+
"rewards/Table2LatexAcc/std": 0.1866762012243271,
|
| 237 |
+
"rewards/Table2Latexform/mean": 0.8524171948432923,
|
| 238 |
+
"rewards/Table2Latexform/std": 0.20919820815324783,
|
| 239 |
+
"step": 50,
|
| 240 |
+
"train_speed(iter/s)": 0.003122
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"clip_ratio": 0.0,
|
| 244 |
+
"completions/clipped_ratio": 0.0,
|
| 245 |
+
"completions/max_length": 2952.4,
|
| 246 |
+
"completions/mean_length": 1598.51875,
|
| 247 |
+
"completions/min_length": 714.2,
|
| 248 |
+
"epoch": 0.29649595687331537,
|
| 249 |
+
"grad_norm": 0.06459857928181523,
|
| 250 |
+
"kl": 0.000313568115234375,
|
| 251 |
+
"learning_rate": 9.99795166473852e-07,
|
| 252 |
+
"loss": 0.028602027893066408,
|
| 253 |
+
"memory(GiB)": 74.0,
|
| 254 |
+
"reward": 1.4819077610969544,
|
| 255 |
+
"reward_std": 0.13568009808659554,
|
| 256 |
+
"rewards/Table2LatexAcc/mean": 0.6212433338165283,
|
| 257 |
+
"rewards/Table2LatexAcc/std": 0.2183626562356949,
|
| 258 |
+
"rewards/Table2Latexform/mean": 0.860664427280426,
|
| 259 |
+
"rewards/Table2Latexform/std": 0.22936906069517135,
|
| 260 |
+
"step": 55,
|
| 261 |
+
"train_speed(iter/s)": 0.003116
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"clip_ratio": 0.0,
|
| 265 |
+
"completions/clipped_ratio": 0.0,
|
| 266 |
+
"completions/max_length": 2717.5,
|
| 267 |
+
"completions/mean_length": 1575.8484375,
|
| 268 |
+
"completions/min_length": 791.8,
|
| 269 |
+
"epoch": 0.32345013477088946,
|
| 270 |
+
"grad_norm": 0.0685119094996376,
|
| 271 |
+
"kl": 0.0005132675170898438,
|
| 272 |
+
"learning_rate": 9.994591720616975e-07,
|
| 273 |
+
"loss": 0.009688837081193924,
|
| 274 |
+
"memory(GiB)": 74.0,
|
| 275 |
+
"reward": 1.4809726119041442,
|
| 276 |
+
"reward_std": 0.12747596204280853,
|
| 277 |
+
"rewards/Table2LatexAcc/mean": 0.6219225466251374,
|
| 278 |
+
"rewards/Table2LatexAcc/std": 0.18778605610132218,
|
| 279 |
+
"rewards/Table2Latexform/mean": 0.8590500473976135,
|
| 280 |
+
"rewards/Table2Latexform/std": 0.2048894114792347,
|
| 281 |
+
"step": 60,
|
| 282 |
+
"train_speed(iter/s)": 0.003124
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"clip_ratio": 0.0,
|
| 286 |
+
"completions/clipped_ratio": 0.0,
|
| 287 |
+
"completions/max_length": 2847.6,
|
| 288 |
+
"completions/mean_length": 1657.3984375,
|
| 289 |
+
"completions/min_length": 848.6,
|
| 290 |
+
"epoch": 0.3504043126684636,
|
| 291 |
+
"grad_norm": 0.08157608763386034,
|
| 292 |
+
"kl": 0.0006221771240234375,
|
| 293 |
+
"learning_rate": 9.98963317898878e-07,
|
| 294 |
+
"loss": 0.019288820028305054,
|
| 295 |
+
"memory(GiB)": 74.0,
|
| 296 |
+
"reward": 1.5079341650009155,
|
| 297 |
+
"reward_std": 0.14110046178102492,
|
| 298 |
+
"rewards/Table2LatexAcc/mean": 0.634680551290512,
|
| 299 |
+
"rewards/Table2LatexAcc/std": 0.20506853014230728,
|
| 300 |
+
"rewards/Table2Latexform/mean": 0.8732536375522614,
|
| 301 |
+
"rewards/Table2Latexform/std": 0.2030529037117958,
|
| 302 |
+
"step": 65,
|
| 303 |
+
"train_speed(iter/s)": 0.003131
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"clip_ratio": 0.0,
|
| 307 |
+
"completions/clipped_ratio": 0.0,
|
| 308 |
+
"completions/max_length": 2604.5,
|
| 309 |
+
"completions/mean_length": 1594.03125,
|
| 310 |
+
"completions/min_length": 874.2,
|
| 311 |
+
"epoch": 0.37735849056603776,
|
| 312 |
+
"grad_norm": 0.08207408816722973,
|
| 313 |
+
"kl": 0.0008758544921875,
|
| 314 |
+
"learning_rate": 9.983077626913043e-07,
|
| 315 |
+
"loss": 0.01205739676952362,
|
| 316 |
+
"memory(GiB)": 74.0,
|
| 317 |
+
"reward": 1.507494068145752,
|
| 318 |
+
"reward_std": 0.11759327277541161,
|
| 319 |
+
"rewards/Table2LatexAcc/mean": 0.6351809322834014,
|
| 320 |
+
"rewards/Table2LatexAcc/std": 0.20378359854221345,
|
| 321 |
+
"rewards/Table2Latexform/mean": 0.8723131835460662,
|
| 322 |
+
"rewards/Table2Latexform/std": 0.19805027171969414,
|
| 323 |
+
"step": 70,
|
| 324 |
+
"train_speed(iter/s)": 0.003146
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"clip_ratio": 0.0,
|
| 328 |
+
"completions/clipped_ratio": 0.0,
|
| 329 |
+
"completions/max_length": 2689.8,
|
| 330 |
+
"completions/mean_length": 1616.209375,
|
| 331 |
+
"completions/min_length": 859.7,
|
| 332 |
+
"epoch": 0.40431266846361186,
|
| 333 |
+
"grad_norm": 0.07397791319392964,
|
| 334 |
+
"kl": 0.0009979248046875,
|
| 335 |
+
"learning_rate": 9.974927162597145e-07,
|
| 336 |
+
"loss": 0.00553036704659462,
|
| 337 |
+
"memory(GiB)": 74.0,
|
| 338 |
+
"reward": 1.4614445567131042,
|
| 339 |
+
"reward_std": 0.09695540629327297,
|
| 340 |
+
"rewards/Table2LatexAcc/mean": 0.5970049917697906,
|
| 341 |
+
"rewards/Table2LatexAcc/std": 0.19226298183202745,
|
| 342 |
+
"rewards/Table2Latexform/mean": 0.8644395887851715,
|
| 343 |
+
"rewards/Table2Latexform/std": 0.19864091277122498,
|
| 344 |
+
"step": 75,
|
| 345 |
+
"train_speed(iter/s)": 0.003149
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"clip_ratio": 0.0,
|
| 349 |
+
"completions/clipped_ratio": 0.0,
|
| 350 |
+
"completions/max_length": 2567.9,
|
| 351 |
+
"completions/mean_length": 1566.4984375,
|
| 352 |
+
"completions/min_length": 893.1,
|
| 353 |
+
"epoch": 0.431266846361186,
|
| 354 |
+
"grad_norm": 0.07175621361462335,
|
| 355 |
+
"kl": 0.0010894775390625,
|
| 356 |
+
"learning_rate": 9.965184394725169e-07,
|
| 357 |
+
"loss": 0.0031857024878263474,
|
| 358 |
+
"memory(GiB)": 74.0,
|
| 359 |
+
"reward": 1.519572389125824,
|
| 360 |
+
"reward_std": 0.11443859413266182,
|
| 361 |
+
"rewards/Table2LatexAcc/mean": 0.6457596719264984,
|
| 362 |
+
"rewards/Table2LatexAcc/std": 0.19394133985042572,
|
| 363 |
+
"rewards/Table2Latexform/mean": 0.8738127529621125,
|
| 364 |
+
"rewards/Table2Latexform/std": 0.2086488611996174,
|
| 365 |
+
"step": 80,
|
| 366 |
+
"train_speed(iter/s)": 0.003163
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"clip_ratio": 0.0,
|
| 370 |
+
"completions/clipped_ratio": 0.0,
|
| 371 |
+
"completions/max_length": 2495.6,
|
| 372 |
+
"completions/mean_length": 1533.6078125,
|
| 373 |
+
"completions/min_length": 824.4,
|
| 374 |
+
"epoch": 0.4582210242587601,
|
| 375 |
+
"grad_norm": 0.07293410493568253,
|
| 376 |
+
"kl": 0.0012256622314453125,
|
| 377 |
+
"learning_rate": 9.953852441622956e-07,
|
| 378 |
+
"loss": 0.010935479402542114,
|
| 379 |
+
"memory(GiB)": 74.0,
|
| 380 |
+
"reward": 1.5418180227279663,
|
| 381 |
+
"reward_std": 0.09861706346273422,
|
| 382 |
+
"rewards/Table2LatexAcc/mean": 0.6385594129562377,
|
| 383 |
+
"rewards/Table2LatexAcc/std": 0.20701712965965272,
|
| 384 |
+
"rewards/Table2Latexform/mean": 0.9032586097717286,
|
| 385 |
+
"rewards/Table2Latexform/std": 0.13576763048768042,
|
| 386 |
+
"step": 85,
|
| 387 |
+
"train_speed(iter/s)": 0.003179
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"clip_ratio": 0.0,
|
| 391 |
+
"completions/clipped_ratio": 0.0,
|
| 392 |
+
"completions/max_length": 2680.3,
|
| 393 |
+
"completions/mean_length": 1574.1953125,
|
| 394 |
+
"completions/min_length": 785.9,
|
| 395 |
+
"epoch": 0.48517520215633425,
|
| 396 |
+
"grad_norm": 0.06793751628944666,
|
| 397 |
+
"kl": 0.0012157440185546875,
|
| 398 |
+
"learning_rate": 9.940934930260036e-07,
|
| 399 |
+
"loss": 5.354555323719978e-05,
|
| 400 |
+
"memory(GiB)": 74.0,
|
| 401 |
+
"reward": 1.4896148085594176,
|
| 402 |
+
"reward_std": 0.09992180205881596,
|
| 403 |
+
"rewards/Table2LatexAcc/mean": 0.6215297818183899,
|
| 404 |
+
"rewards/Table2LatexAcc/std": 0.19945850372314453,
|
| 405 |
+
"rewards/Table2Latexform/mean": 0.8680850267410278,
|
| 406 |
+
"rewards/Table2Latexform/std": 0.21053530871868134,
|
| 407 |
+
"step": 90,
|
| 408 |
+
"train_speed(iter/s)": 0.003182
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"clip_ratio": 0.0,
|
| 412 |
+
"completions/clipped_ratio": 0.0,
|
| 413 |
+
"completions/max_length": 2833.6,
|
| 414 |
+
"completions/mean_length": 1614.984375,
|
| 415 |
+
"completions/min_length": 836.7,
|
| 416 |
+
"epoch": 0.5121293800539084,
|
| 417 |
+
"grad_norm": 0.07800355989359384,
|
| 418 |
+
"kl": 0.001270294189453125,
|
| 419 |
+
"learning_rate": 9.92643599508875e-07,
|
| 420 |
+
"loss": 0.01619407832622528,
|
| 421 |
+
"memory(GiB)": 74.0,
|
| 422 |
+
"reward": 1.4949531078338623,
|
| 423 |
+
"reward_std": 0.13312736451625823,
|
| 424 |
+
"rewards/Table2LatexAcc/mean": 0.6362012684345245,
|
| 425 |
+
"rewards/Table2LatexAcc/std": 0.20503575205802918,
|
| 426 |
+
"rewards/Table2Latexform/mean": 0.8587518692016601,
|
| 427 |
+
"rewards/Table2Latexform/std": 0.21175305247306825,
|
| 428 |
+
"step": 95,
|
| 429 |
+
"train_speed(iter/s)": 0.003179
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"clip_ratio": 0.0,
|
| 433 |
+
"completions/clipped_ratio": 0.0,
|
| 434 |
+
"completions/max_length": 2672.2,
|
| 435 |
+
"completions/mean_length": 1541.909375,
|
| 436 |
+
"completions/min_length": 850.3,
|
| 437 |
+
"epoch": 0.5390835579514824,
|
| 438 |
+
"grad_norm": 0.06742732491254022,
|
| 439 |
+
"kl": 0.001406097412109375,
|
| 440 |
+
"learning_rate": 9.910360276720974e-07,
|
| 441 |
+
"loss": 0.011617515981197358,
|
| 442 |
+
"memory(GiB)": 74.0,
|
| 443 |
+
"reward": 1.5225663423538207,
|
| 444 |
+
"reward_std": 0.12018043175339699,
|
| 445 |
+
"rewards/Table2LatexAcc/mean": 0.634308785200119,
|
| 446 |
+
"rewards/Table2LatexAcc/std": 0.19708103239536284,
|
| 447 |
+
"rewards/Table2Latexform/mean": 0.8882575571537018,
|
| 448 |
+
"rewards/Table2Latexform/std": 0.1708666443824768,
|
| 449 |
+
"step": 100,
|
| 450 |
+
"train_speed(iter/s)": 0.003187
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"clip_ratio": 0.0,
|
| 454 |
+
"completions/clipped_ratio": 0.0,
|
| 455 |
+
"completions/max_length": 2863.4,
|
| 456 |
+
"completions/mean_length": 1613.728125,
|
| 457 |
+
"completions/min_length": 945.5,
|
| 458 |
+
"epoch": 0.5660377358490566,
|
| 459 |
+
"grad_norm": 0.0656531441071073,
|
| 460 |
+
"kl": 0.0012493133544921875,
|
| 461 |
+
"learning_rate": 9.89271292044279e-07,
|
| 462 |
+
"loss": 0.016812124848365785,
|
| 463 |
+
"memory(GiB)": 74.0,
|
| 464 |
+
"reward": 1.494718039035797,
|
| 465 |
+
"reward_std": 0.13982294127345085,
|
| 466 |
+
"rewards/Table2LatexAcc/mean": 0.6318223595619201,
|
| 467 |
+
"rewards/Table2LatexAcc/std": 0.2267067864537239,
|
| 468 |
+
"rewards/Table2Latexform/mean": 0.862895667552948,
|
| 469 |
+
"rewards/Table2Latexform/std": 0.21887822449207306,
|
| 470 |
+
"step": 105,
|
| 471 |
+
"train_speed(iter/s)": 0.003185
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"clip_ratio": 0.0,
|
| 475 |
+
"completions/clipped_ratio": 0.0,
|
| 476 |
+
"completions/max_length": 2608.4,
|
| 477 |
+
"completions/mean_length": 1581.09375,
|
| 478 |
+
"completions/min_length": 790.2,
|
| 479 |
+
"epoch": 0.5929919137466307,
|
| 480 |
+
"grad_norm": 0.06582315254735907,
|
| 481 |
+
"kl": 0.001549530029296875,
|
| 482 |
+
"learning_rate": 9.873499574567681e-07,
|
| 483 |
+
"loss": 0.010095475614070893,
|
| 484 |
+
"memory(GiB)": 74.0,
|
| 485 |
+
"reward": 1.4990519642829896,
|
| 486 |
+
"reward_std": 0.10162455774843693,
|
| 487 |
+
"rewards/Table2LatexAcc/mean": 0.6363059639930725,
|
| 488 |
+
"rewards/Table2LatexAcc/std": 0.19157345294952394,
|
| 489 |
+
"rewards/Table2Latexform/mean": 0.862746000289917,
|
| 490 |
+
"rewards/Table2Latexform/std": 0.20280475318431854,
|
| 491 |
+
"step": 110,
|
| 492 |
+
"train_speed(iter/s)": 0.003195
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"clip_ratio": 0.0,
|
| 496 |
+
"completions/clipped_ratio": 0.0,
|
| 497 |
+
"completions/max_length": 2667.1,
|
| 498 |
+
"completions/mean_length": 1623.0609375,
|
| 499 |
+
"completions/min_length": 862.5,
|
| 500 |
+
"epoch": 0.6199460916442049,
|
| 501 |
+
"grad_norm": 0.0676327840344494,
|
| 502 |
+
"kl": 0.0012561798095703125,
|
| 503 |
+
"learning_rate": 9.852726388628688e-07,
|
| 504 |
+
"loss": 0.009667134284973145,
|
| 505 |
+
"memory(GiB)": 74.0,
|
| 506 |
+
"reward": 1.499183714389801,
|
| 507 |
+
"reward_std": 0.11013109833002091,
|
| 508 |
+
"rewards/Table2LatexAcc/mean": 0.6425846576690674,
|
| 509 |
+
"rewards/Table2LatexAcc/std": 0.20786909610033036,
|
| 510 |
+
"rewards/Table2Latexform/mean": 0.8565990567207337,
|
| 511 |
+
"rewards/Table2Latexform/std": 0.22757124677300453,
|
| 512 |
+
"step": 115,
|
| 513 |
+
"train_speed(iter/s)": 0.003199
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"clip_ratio": 0.0,
|
| 517 |
+
"completions/clipped_ratio": 0.0,
|
| 518 |
+
"completions/max_length": 2648.9,
|
| 519 |
+
"completions/mean_length": 1617.8234375,
|
| 520 |
+
"completions/min_length": 878.5,
|
| 521 |
+
"epoch": 0.6469002695417789,
|
| 522 |
+
"grad_norm": 0.05968134371530777,
|
| 523 |
+
"kl": 0.00138702392578125,
|
| 524 |
+
"learning_rate": 9.830400011410156e-07,
|
| 525 |
+
"loss": 0.003092067874968052,
|
| 526 |
+
"memory(GiB)": 74.0,
|
| 527 |
+
"reward": 1.4849407434463502,
|
| 528 |
+
"reward_std": 0.08951778598129749,
|
| 529 |
+
"rewards/Table2LatexAcc/mean": 0.6164660751819611,
|
| 530 |
+
"rewards/Table2LatexAcc/std": 0.204762826859951,
|
| 531 |
+
"rewards/Table2Latexform/mean": 0.8684746503829956,
|
| 532 |
+
"rewards/Table2Latexform/std": 0.20679847225546838,
|
| 533 |
+
"step": 120,
|
| 534 |
+
"train_speed(iter/s)": 0.003203
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"clip_ratio": 0.0,
|
| 538 |
+
"completions/clipped_ratio": 0.0,
|
| 539 |
+
"completions/max_length": 2692.2,
|
| 540 |
+
"completions/mean_length": 1548.7328125,
|
| 541 |
+
"completions/min_length": 787.5,
|
| 542 |
+
"epoch": 0.6738544474393531,
|
| 543 |
+
"grad_norm": 0.08102589945740883,
|
| 544 |
+
"kl": 0.0015228271484375,
|
| 545 |
+
"learning_rate": 9.806527588819692e-07,
|
| 546 |
+
"loss": 0.010635277628898621,
|
| 547 |
+
"memory(GiB)": 74.0,
|
| 548 |
+
"reward": 1.4484204292297362,
|
| 549 |
+
"reward_std": 0.12051350250840187,
|
| 550 |
+
"rewards/Table2LatexAcc/mean": 0.5983371019363404,
|
| 551 |
+
"rewards/Table2LatexAcc/std": 0.19683932662010192,
|
| 552 |
+
"rewards/Table2Latexform/mean": 0.8500832915306091,
|
| 553 |
+
"rewards/Table2Latexform/std": 0.22092146053910255,
|
| 554 |
+
"step": 125,
|
| 555 |
+
"train_speed(iter/s)": 0.003201
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"clip_ratio": 0.0,
|
| 559 |
+
"completions/clipped_ratio": 0.0,
|
| 560 |
+
"completions/max_length": 2778.3,
|
| 561 |
+
"completions/mean_length": 1625.8203125,
|
| 562 |
+
"completions/min_length": 975.0,
|
| 563 |
+
"epoch": 0.7008086253369272,
|
| 564 |
+
"grad_norm": 0.06581718834736765,
|
| 565 |
+
"kl": 0.0013751983642578125,
|
| 566 |
+
"learning_rate": 9.781116761600992e-07,
|
| 567 |
+
"loss": 0.008332135528326035,
|
| 568 |
+
"memory(GiB)": 74.0,
|
| 569 |
+
"reward": 1.4899320960044862,
|
| 570 |
+
"reward_std": 0.1020436353981495,
|
| 571 |
+
"rewards/Table2LatexAcc/mean": 0.6282051384449006,
|
| 572 |
+
"rewards/Table2LatexAcc/std": 0.18501487672328948,
|
| 573 |
+
"rewards/Table2Latexform/mean": 0.8617269277572632,
|
| 574 |
+
"rewards/Table2Latexform/std": 0.21871328055858613,
|
| 575 |
+
"step": 130,
|
| 576 |
+
"train_speed(iter/s)": 0.003199
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"clip_ratio": 0.0,
|
| 580 |
+
"completions/clipped_ratio": 0.0,
|
| 581 |
+
"completions/max_length": 2638.1,
|
| 582 |
+
"completions/mean_length": 1558.1703125,
|
| 583 |
+
"completions/min_length": 627.1,
|
| 584 |
+
"epoch": 0.7277628032345014,
|
| 585 |
+
"grad_norm": 0.08042871559451785,
|
| 586 |
+
"kl": 0.0016143798828125,
|
| 587 |
+
"learning_rate": 9.75417566288832e-07,
|
| 588 |
+
"loss": 0.022313964366912842,
|
| 589 |
+
"memory(GiB)": 74.0,
|
| 590 |
+
"reward": 1.4969127774238586,
|
| 591 |
+
"reward_std": 0.09756124764680862,
|
| 592 |
+
"rewards/Table2LatexAcc/mean": 0.6259892284870148,
|
| 593 |
+
"rewards/Table2LatexAcc/std": 0.18883997797966004,
|
| 594 |
+
"rewards/Table2Latexform/mean": 0.8709235429763794,
|
| 595 |
+
"rewards/Table2Latexform/std": 0.20598914995789527,
|
| 596 |
+
"step": 135,
|
| 597 |
+
"train_speed(iter/s)": 0.003199
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"clip_ratio": 0.0,
|
| 601 |
+
"completions/clipped_ratio": 0.0,
|
| 602 |
+
"completions/max_length": 2594.9,
|
| 603 |
+
"completions/mean_length": 1566.1609375,
|
| 604 |
+
"completions/min_length": 858.8,
|
| 605 |
+
"epoch": 0.7547169811320755,
|
| 606 |
+
"grad_norm": 0.06451190019619368,
|
| 607 |
+
"kl": 0.00159912109375,
|
| 608 |
+
"learning_rate": 9.725712915603353e-07,
|
| 609 |
+
"loss": 0.00471530370414257,
|
| 610 |
+
"memory(GiB)": 74.0,
|
| 611 |
+
"reward": 1.4983545541763306,
|
| 612 |
+
"reward_std": 0.10673168860375881,
|
| 613 |
+
"rewards/Table2LatexAcc/mean": 0.6402543127536774,
|
| 614 |
+
"rewards/Table2LatexAcc/std": 0.20193217247724532,
|
| 615 |
+
"rewards/Table2Latexform/mean": 0.8581002414226532,
|
| 616 |
+
"rewards/Table2Latexform/std": 0.2166273184120655,
|
| 617 |
+
"step": 140,
|
| 618 |
+
"train_speed(iter/s)": 0.003204
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"clip_ratio": 0.0,
|
| 622 |
+
"completions/clipped_ratio": 0.0,
|
| 623 |
+
"completions/max_length": 2585.7,
|
| 624 |
+
"completions/mean_length": 1566.3171875,
|
| 625 |
+
"completions/min_length": 783.5,
|
| 626 |
+
"epoch": 0.7816711590296496,
|
| 627 |
+
"grad_norm": 0.06842850537031975,
|
| 628 |
+
"kl": 0.0016510009765625,
|
| 629 |
+
"learning_rate": 9.69573762969529e-07,
|
| 630 |
+
"loss": 0.008447134494781494,
|
| 631 |
+
"memory(GiB)": 74.0,
|
| 632 |
+
"reward": 1.5043591618537904,
|
| 633 |
+
"reward_std": 0.10398341864347457,
|
| 634 |
+
"rewards/Table2LatexAcc/mean": 0.6323516488075256,
|
| 635 |
+
"rewards/Table2LatexAcc/std": 0.19334442913532257,
|
| 636 |
+
"rewards/Table2Latexform/mean": 0.8720075249671936,
|
| 637 |
+
"rewards/Table2Latexform/std": 0.18240121901035308,
|
| 638 |
+
"step": 145,
|
| 639 |
+
"train_speed(iter/s)": 0.00321
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"clip_ratio": 0.0,
|
| 643 |
+
"completions/clipped_ratio": 0.0,
|
| 644 |
+
"completions/max_length": 2677.8,
|
| 645 |
+
"completions/mean_length": 1609.378125,
|
| 646 |
+
"completions/min_length": 905.7,
|
| 647 |
+
"epoch": 0.8086253369272237,
|
| 648 |
+
"grad_norm": 0.06551621158024094,
|
| 649 |
+
"kl": 0.0015777587890625,
|
| 650 |
+
"learning_rate": 9.664259399225067e-07,
|
| 651 |
+
"loss": 0.005352784693241119,
|
| 652 |
+
"memory(GiB)": 74.0,
|
| 653 |
+
"reward": 1.5480861902236938,
|
| 654 |
+
"reward_std": 0.0993690624833107,
|
| 655 |
+
"rewards/Table2LatexAcc/mean": 0.6449747204780578,
|
| 656 |
+
"rewards/Table2LatexAcc/std": 0.1948181599378586,
|
| 657 |
+
"rewards/Table2Latexform/mean": 0.9031114995479583,
|
| 658 |
+
"rewards/Table2Latexform/std": 0.15625113472342492,
|
| 659 |
+
"step": 150,
|
| 660 |
+
"train_speed(iter/s)": 0.003209
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"clip_ratio": 0.0,
|
| 664 |
+
"completions/clipped_ratio": 0.0,
|
| 665 |
+
"completions/max_length": 2549.0,
|
| 666 |
+
"completions/mean_length": 1590.425,
|
| 667 |
+
"completions/min_length": 906.1,
|
| 668 |
+
"epoch": 0.8355795148247979,
|
| 669 |
+
"grad_norm": 0.062419199774521504,
|
| 670 |
+
"kl": 0.001617431640625,
|
| 671 |
+
"learning_rate": 9.631288299294624e-07,
|
| 672 |
+
"loss": 0.005914273858070374,
|
| 673 |
+
"memory(GiB)": 74.0,
|
| 674 |
+
"reward": 1.5300285577774049,
|
| 675 |
+
"reward_std": 0.07754914276301861,
|
| 676 |
+
"rewards/Table2LatexAcc/mean": 0.6536247074604035,
|
| 677 |
+
"rewards/Table2LatexAcc/std": 0.1888583406805992,
|
| 678 |
+
"rewards/Table2Latexform/mean": 0.8764038562774659,
|
| 679 |
+
"rewards/Table2Latexform/std": 0.19668345972895623,
|
| 680 |
+
"step": 155,
|
| 681 |
+
"train_speed(iter/s)": 0.003214
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"clip_ratio": 0.0,
|
| 685 |
+
"completions/clipped_ratio": 0.0,
|
| 686 |
+
"completions/max_length": 2675.8,
|
| 687 |
+
"completions/mean_length": 1594.9125,
|
| 688 |
+
"completions/min_length": 904.8,
|
| 689 |
+
"epoch": 0.862533692722372,
|
| 690 |
+
"grad_norm": 0.07381311561133726,
|
| 691 |
+
"kl": 0.001567840576171875,
|
| 692 |
+
"learning_rate": 9.596834882822218e-07,
|
| 693 |
+
"loss": 0.0008831036277115345,
|
| 694 |
+
"memory(GiB)": 74.0,
|
| 695 |
+
"reward": 1.5059723734855652,
|
| 696 |
+
"reward_std": 0.11190913170576096,
|
| 697 |
+
"rewards/Table2LatexAcc/mean": 0.6299772620201111,
|
| 698 |
+
"rewards/Table2LatexAcc/std": 0.18921414837241174,
|
| 699 |
+
"rewards/Table2Latexform/mean": 0.8759951233863831,
|
| 700 |
+
"rewards/Table2Latexform/std": 0.18999719768762588,
|
| 701 |
+
"step": 160,
|
| 702 |
+
"train_speed(iter/s)": 0.003217
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"clip_ratio": 0.0,
|
| 706 |
+
"completions/clipped_ratio": 0.0,
|
| 707 |
+
"completions/max_length": 2556.4,
|
| 708 |
+
"completions/mean_length": 1544.603125,
|
| 709 |
+
"completions/min_length": 762.6,
|
| 710 |
+
"epoch": 0.889487870619946,
|
| 711 |
+
"grad_norm": 0.05908311708682426,
|
| 712 |
+
"kl": 0.00150909423828125,
|
| 713 |
+
"learning_rate": 9.560910177164787e-07,
|
| 714 |
+
"loss": 0.007628290355205536,
|
| 715 |
+
"memory(GiB)": 74.0,
|
| 716 |
+
"reward": 1.5502776145935058,
|
| 717 |
+
"reward_std": 0.07942587062716484,
|
| 718 |
+
"rewards/Table2LatexAcc/mean": 0.6583487272262574,
|
| 719 |
+
"rewards/Table2LatexAcc/std": 0.18620822578668594,
|
| 720 |
+
"rewards/Table2Latexform/mean": 0.8919288635253906,
|
| 721 |
+
"rewards/Table2Latexform/std": 0.18032970726490022,
|
| 722 |
+
"step": 165,
|
| 723 |
+
"train_speed(iter/s)": 0.003222
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"clip_ratio": 0.0,
|
| 727 |
+
"completions/clipped_ratio": 0.0,
|
| 728 |
+
"completions/max_length": 2511.0,
|
| 729 |
+
"completions/mean_length": 1593.021875,
|
| 730 |
+
"completions/min_length": 835.0,
|
| 731 |
+
"epoch": 0.9164420485175202,
|
| 732 |
+
"grad_norm": 0.059058153054454235,
|
| 733 |
+
"kl": 0.00181427001953125,
|
| 734 |
+
"learning_rate": 9.523525680588476e-07,
|
| 735 |
+
"loss": 0.008848436921834946,
|
| 736 |
+
"memory(GiB)": 74.0,
|
| 737 |
+
"reward": 1.5144242644309998,
|
| 738 |
+
"reward_std": 0.09105739071965217,
|
| 739 |
+
"rewards/Table2LatexAcc/mean": 0.6321313917636872,
|
| 740 |
+
"rewards/Table2LatexAcc/std": 0.18138092905282974,
|
| 741 |
+
"rewards/Table2Latexform/mean": 0.8822928845882416,
|
| 742 |
+
"rewards/Table2Latexform/std": 0.19216497614979744,
|
| 743 |
+
"step": 170,
|
| 744 |
+
"train_speed(iter/s)": 0.003226
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"clip_ratio": 0.0,
|
| 748 |
+
"completions/clipped_ratio": 0.0,
|
| 749 |
+
"completions/max_length": 2540.9,
|
| 750 |
+
"completions/mean_length": 1593.3265625,
|
| 751 |
+
"completions/min_length": 730.9,
|
| 752 |
+
"epoch": 0.9433962264150944,
|
| 753 |
+
"grad_norm": 0.060705012485582154,
|
| 754 |
+
"kl": 0.00139312744140625,
|
| 755 |
+
"learning_rate": 9.484693358588434e-07,
|
| 756 |
+
"loss": 0.007192098349332809,
|
| 757 |
+
"memory(GiB)": 74.0,
|
| 758 |
+
"reward": 1.5356804728507996,
|
| 759 |
+
"reward_std": 0.09475091025233269,
|
| 760 |
+
"rewards/Table2LatexAcc/mean": 0.6415718376636506,
|
| 761 |
+
"rewards/Table2LatexAcc/std": 0.1903410866856575,
|
| 762 |
+
"rewards/Table2Latexform/mean": 0.8941086232662201,
|
| 763 |
+
"rewards/Table2Latexform/std": 0.1649520058184862,
|
| 764 |
+
"step": 175,
|
| 765 |
+
"train_speed(iter/s)": 0.003229
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"clip_ratio": 0.0,
|
| 769 |
+
"completions/clipped_ratio": 0.0,
|
| 770 |
+
"completions/max_length": 2650.3,
|
| 771 |
+
"completions/mean_length": 1586.671875,
|
| 772 |
+
"completions/min_length": 818.4,
|
| 773 |
+
"epoch": 0.9703504043126685,
|
| 774 |
+
"grad_norm": 0.07391935117978014,
|
| 775 |
+
"kl": 0.001525115966796875,
|
| 776 |
+
"learning_rate": 9.444425640059076e-07,
|
| 777 |
+
"loss": 0.007059115171432495,
|
| 778 |
+
"memory(GiB)": 74.0,
|
| 779 |
+
"reward": 1.5181043028831482,
|
| 780 |
+
"reward_std": 0.09545421227812767,
|
| 781 |
+
"rewards/Table2LatexAcc/mean": 0.638035798072815,
|
| 782 |
+
"rewards/Table2LatexAcc/std": 0.20127029120922088,
|
| 783 |
+
"rewards/Table2Latexform/mean": 0.8800684928894043,
|
| 784 |
+
"rewards/Table2Latexform/std": 0.18569674119353294,
|
| 785 |
+
"step": 180,
|
| 786 |
+
"train_speed(iter/s)": 0.00323
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"clip_ratio": 0.0,
|
| 790 |
+
"completions/clipped_ratio": 0.0,
|
| 791 |
+
"completions/max_length": 2459.1,
|
| 792 |
+
"completions/mean_length": 1533.0296875,
|
| 793 |
+
"completions/min_length": 935.5,
|
| 794 |
+
"epoch": 0.9973045822102425,
|
| 795 |
+
"grad_norm": 0.07964238807994012,
|
| 796 |
+
"kl": 0.00167999267578125,
|
| 797 |
+
"learning_rate": 9.402735413316011e-07,
|
| 798 |
+
"loss": -0.00023833760060369967,
|
| 799 |
+
"memory(GiB)": 74.0,
|
| 800 |
+
"reward": 1.5326952815055848,
|
| 801 |
+
"reward_std": 0.08919371329247952,
|
| 802 |
+
"rewards/Table2LatexAcc/mean": 0.6511692225933075,
|
| 803 |
+
"rewards/Table2LatexAcc/std": 0.1804724305868149,
|
| 804 |
+
"rewards/Table2Latexform/mean": 0.8815260589122772,
|
| 805 |
+
"rewards/Table2Latexform/std": 0.19189485386013985,
|
| 806 |
+
"step": 185,
|
| 807 |
+
"train_speed(iter/s)": 0.003237
|
| 808 |
+
}
|
| 809 |
+
],
|
| 810 |
+
"logging_steps": 5,
|
| 811 |
+
"max_steps": 925,
|
| 812 |
+
"num_input_tokens_seen": 0,
|
| 813 |
+
"num_train_epochs": 5,
|
| 814 |
+
"save_steps": 500,
|
| 815 |
+
"stateful_callbacks": {
|
| 816 |
+
"TrainerControl": {
|
| 817 |
+
"args": {
|
| 818 |
+
"should_epoch_stop": false,
|
| 819 |
+
"should_evaluate": false,
|
| 820 |
+
"should_log": false,
|
| 821 |
+
"should_save": true,
|
| 822 |
+
"should_training_stop": false
|
| 823 |
+
},
|
| 824 |
+
"attributes": {}
|
| 825 |
+
}
|
| 826 |
+
},
|
| 827 |
+
"total_flos": 0.0,
|
| 828 |
+
"train_batch_size": 4,
|
| 829 |
+
"trial_name": null,
|
| 830 |
+
"trial_params": null
|
| 831 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1869fbedd18c0166b30143746f7f584e880598dcaf321b22d2685860e3dcf6ba
|
| 3 |
+
size 9976
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|