Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- args.json +692 -0
- chat_template.jinja +61 -0
- config.json +69 -0
- iter_0001024/.metadata +0 -0
- iter_0001024/common.pt +3 -0
- iter_0001024/metadata.json +1 -0
- latest_checkpointed_iteration.txt +1 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +405 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
args.json
ADDED
|
@@ -0,0 +1,692 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"use_ray": false,
|
| 3 |
+
"ray_exp_name": null,
|
| 4 |
+
"device_groups": null,
|
| 5 |
+
"model": "Qwen/Qwen3-4B-Instruct-2507",
|
| 6 |
+
"model_type": "qwen3",
|
| 7 |
+
"model_revision": null,
|
| 8 |
+
"task_type": "causal_lm",
|
| 9 |
+
"torch_dtype": "bfloat16",
|
| 10 |
+
"attn_impl": null,
|
| 11 |
+
"new_special_tokens": [],
|
| 12 |
+
"num_labels": null,
|
| 13 |
+
"problem_type": null,
|
| 14 |
+
"rope_scaling": null,
|
| 15 |
+
"device_map": null,
|
| 16 |
+
"max_memory": {},
|
| 17 |
+
"max_model_len": null,
|
| 18 |
+
"local_repo_path": null,
|
| 19 |
+
"init_strategy": null,
|
| 20 |
+
"template": "qwen3_nothinking",
|
| 21 |
+
"system": null,
|
| 22 |
+
"max_length": 32768,
|
| 23 |
+
"truncation_strategy": "left",
|
| 24 |
+
"max_pixels": null,
|
| 25 |
+
"agent_template": null,
|
| 26 |
+
"norm_bbox": null,
|
| 27 |
+
"use_chat_template": true,
|
| 28 |
+
"padding_side": "right",
|
| 29 |
+
"padding_free": true,
|
| 30 |
+
"loss_scale": "default",
|
| 31 |
+
"sequence_parallel_size": 1,
|
| 32 |
+
"template_backend": "swift",
|
| 33 |
+
"response_prefix": null,
|
| 34 |
+
"enable_thinking": null,
|
| 35 |
+
"add_non_thinking_prefix": true,
|
| 36 |
+
"dataset": [
|
| 37 |
+
"/data/repotune/data/agentic/bugfix/astropy_20201231_72ca3c07/v1/sft_all.jsonl#2048",
|
| 38 |
+
"/data/repotune/data/agentic/fim/astropy_20201231_72ca3c07/v0/sft_all.jsonl#2048",
|
| 39 |
+
"/data/repotune/data/agentic/testgen/astropy_20201231_72ca3c07/v0/sft_all.jsonl#2048",
|
| 40 |
+
"/data/repotune/data/agentic/ar/astropy_20201231_72ca3c07/sft_all.jsonl#2048"
|
| 41 |
+
],
|
| 42 |
+
"val_dataset": [
|
| 43 |
+
"/data/repotune/data/val/django_e13b714/sbv_msa_gemini25pro.jsonl",
|
| 44 |
+
"/data/repotune/data/val/django_e13b714/sbv_msa_gemini3pro.jsonl"
|
| 45 |
+
],
|
| 46 |
+
"cached_dataset": [],
|
| 47 |
+
"cached_val_dataset": [],
|
| 48 |
+
"split_dataset_ratio": 0.0,
|
| 49 |
+
"data_seed": 42,
|
| 50 |
+
"dataset_num_proc": 16,
|
| 51 |
+
"load_from_cache_file": true,
|
| 52 |
+
"dataset_shuffle": true,
|
| 53 |
+
"val_dataset_shuffle": false,
|
| 54 |
+
"streaming": false,
|
| 55 |
+
"interleave_prob": null,
|
| 56 |
+
"stopping_strategy": "first_exhausted",
|
| 57 |
+
"shuffle_buffer_size": 1000,
|
| 58 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 59 |
+
"columns": {},
|
| 60 |
+
"strict": false,
|
| 61 |
+
"remove_unused_columns": true,
|
| 62 |
+
"model_name": null,
|
| 63 |
+
"model_author": null,
|
| 64 |
+
"custom_dataset_info": [],
|
| 65 |
+
"quant_method": null,
|
| 66 |
+
"quant_bits": null,
|
| 67 |
+
"hqq_axis": null,
|
| 68 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 69 |
+
"bnb_4bit_quant_type": "nf4",
|
| 70 |
+
"bnb_4bit_use_double_quant": true,
|
| 71 |
+
"bnb_4bit_quant_storage": null,
|
| 72 |
+
"max_new_tokens": null,
|
| 73 |
+
"temperature": 0.9,
|
| 74 |
+
"top_k": 50,
|
| 75 |
+
"top_p": 0.9,
|
| 76 |
+
"repetition_penalty": 1.0,
|
| 77 |
+
"num_beams": 1,
|
| 78 |
+
"stream": false,
|
| 79 |
+
"stop_words": [],
|
| 80 |
+
"logprobs": false,
|
| 81 |
+
"top_logprobs": null,
|
| 82 |
+
"structured_outputs_regex": null,
|
| 83 |
+
"tuner_backend": "peft",
|
| 84 |
+
"tuner_type": "full",
|
| 85 |
+
"train_type": "full",
|
| 86 |
+
"adapters": [],
|
| 87 |
+
"external_plugins": [],
|
| 88 |
+
"custom_register_path": [],
|
| 89 |
+
"seed": 42,
|
| 90 |
+
"model_kwargs": {},
|
| 91 |
+
"load_args": false,
|
| 92 |
+
"load_data_args": false,
|
| 93 |
+
"packing": false,
|
| 94 |
+
"packing_length": null,
|
| 95 |
+
"packing_num_proc": 1,
|
| 96 |
+
"lazy_tokenize": false,
|
| 97 |
+
"use_hf": true,
|
| 98 |
+
"hub_token": null,
|
| 99 |
+
"ddp_timeout": 18000000,
|
| 100 |
+
"ddp_backend": null,
|
| 101 |
+
"ignore_args_error": false,
|
| 102 |
+
"use_swift_lora": false,
|
| 103 |
+
"freeze_llm": false,
|
| 104 |
+
"freeze_vit": true,
|
| 105 |
+
"freeze_aligner": true,
|
| 106 |
+
"freeze_parameters": [],
|
| 107 |
+
"freeze_parameters_regex": null,
|
| 108 |
+
"freeze_parameters_ratio": 0.0,
|
| 109 |
+
"trainable_parameters": [],
|
| 110 |
+
"trainable_parameters_regex": null,
|
| 111 |
+
"adapter_load": null,
|
| 112 |
+
"target_modules": [
|
| 113 |
+
"all-linear"
|
| 114 |
+
],
|
| 115 |
+
"target_regex": null,
|
| 116 |
+
"modules_to_save": [],
|
| 117 |
+
"lora_rank": 8,
|
| 118 |
+
"lora_alpha": 32,
|
| 119 |
+
"lora_dropout": 0.05,
|
| 120 |
+
"lora_bias": "none",
|
| 121 |
+
"lora_dtype": null,
|
| 122 |
+
"use_rslora": false,
|
| 123 |
+
"rlhf_type": null,
|
| 124 |
+
"ref_load": null,
|
| 125 |
+
"ref_adapter_load": null,
|
| 126 |
+
"beta": null,
|
| 127 |
+
"rpo_alpha": null,
|
| 128 |
+
"reference_free": false,
|
| 129 |
+
"label_smoothing": 0.0,
|
| 130 |
+
"f_divergence_type": "reverse_kl",
|
| 131 |
+
"loss_type": null,
|
| 132 |
+
"desirable_weight": 1.0,
|
| 133 |
+
"undesirable_weight": 1.0,
|
| 134 |
+
"calculate_KL": null,
|
| 135 |
+
"center_rewards_coefficient": null,
|
| 136 |
+
"teacher_model": null,
|
| 137 |
+
"teacher_model_type": null,
|
| 138 |
+
"teacher_model_revision": null,
|
| 139 |
+
"lmbda": 0.5,
|
| 140 |
+
"seq_kd": false,
|
| 141 |
+
"offload_teacher_model": false,
|
| 142 |
+
"sft_alpha": 0.0,
|
| 143 |
+
"generation_batch_size": null,
|
| 144 |
+
"steps_per_generation": null,
|
| 145 |
+
"num_generations": 8,
|
| 146 |
+
"num_generations_eval": null,
|
| 147 |
+
"max_completion_length": 512,
|
| 148 |
+
"importance_sampling_level": "token",
|
| 149 |
+
"tau_pos": 1.0,
|
| 150 |
+
"tau_neg": 1.05,
|
| 151 |
+
"epsilon": 0.2,
|
| 152 |
+
"epsilon_high": null,
|
| 153 |
+
"delta": null,
|
| 154 |
+
"use_vllm": true,
|
| 155 |
+
"vllm_mode": null,
|
| 156 |
+
"vllm_enable_prefix_caching": true,
|
| 157 |
+
"vllm_gpu_memory_utilization": 0.9,
|
| 158 |
+
"vllm_tensor_parallel_size": 1,
|
| 159 |
+
"vllm_max_model_len": null,
|
| 160 |
+
"vllm_enforce_eager": false,
|
| 161 |
+
"vllm_limit_mm_per_prompt": null,
|
| 162 |
+
"vllm_disable_cascade_attn": false,
|
| 163 |
+
"vllm_max_num_seqs": null,
|
| 164 |
+
"vllm_mm_processor_cache_gb": null,
|
| 165 |
+
"vllm_engine_kwargs": null,
|
| 166 |
+
"sleep_level": 0,
|
| 167 |
+
"offload_optimizer": false,
|
| 168 |
+
"offload_model": false,
|
| 169 |
+
"offload_bridge": false,
|
| 170 |
+
"vllm_server_base_url": null,
|
| 171 |
+
"vllm_server_host": null,
|
| 172 |
+
"vllm_server_port": [
|
| 173 |
+
8000
|
| 174 |
+
],
|
| 175 |
+
"vllm_server_timeout": 240.0,
|
| 176 |
+
"vllm_server_group_port": null,
|
| 177 |
+
"reward_funcs": [],
|
| 178 |
+
"reward_weights": null,
|
| 179 |
+
"cosine_min_len_value_wrong": -0.5,
|
| 180 |
+
"cosine_max_len_value_wrong": 0.0,
|
| 181 |
+
"cosine_min_len_value_correct": 1.0,
|
| 182 |
+
"cosine_max_len_value_correct": 0.5,
|
| 183 |
+
"cosine_max_len": null,
|
| 184 |
+
"repetition_n_grams": 3,
|
| 185 |
+
"repetition_max_penalty": -1.0,
|
| 186 |
+
"soft_max_length": null,
|
| 187 |
+
"soft_cache_length": null,
|
| 188 |
+
"dynamic_sample": false,
|
| 189 |
+
"max_resample_times": 3,
|
| 190 |
+
"overlong_filter": false,
|
| 191 |
+
"scale_rewards": "group",
|
| 192 |
+
"advantage_estimator": "grpo",
|
| 193 |
+
"kl_in_reward": false,
|
| 194 |
+
"wandb_log_unique_prompts": null,
|
| 195 |
+
"log_completions": false,
|
| 196 |
+
"rollout_importance_sampling_mode": null,
|
| 197 |
+
"rollout_importance_sampling_threshold": 2.0,
|
| 198 |
+
"log_rollout_offpolicy_metrics": false,
|
| 199 |
+
"off_policy_sequence_mask_delta": null,
|
| 200 |
+
"log_entropy": false,
|
| 201 |
+
"top_entropy_quantile": 1.0,
|
| 202 |
+
"reward_model": null,
|
| 203 |
+
"reward_model_plugin": null,
|
| 204 |
+
"sync_ref_model": false,
|
| 205 |
+
"ref_model_sync_steps": 512,
|
| 206 |
+
"ref_model_mixup_alpha": 0.6,
|
| 207 |
+
"async_generate": false,
|
| 208 |
+
"move_model_batches": null,
|
| 209 |
+
"multi_turn_scheduler": null,
|
| 210 |
+
"max_turns": null,
|
| 211 |
+
"completion_length_limit_scope": "per_round",
|
| 212 |
+
"vllm_server_pass_dataset": false,
|
| 213 |
+
"num_iterations": 1,
|
| 214 |
+
"check_model": true,
|
| 215 |
+
"padded_vocab_size": 151936,
|
| 216 |
+
"initialize_embedding": false,
|
| 217 |
+
"mlp_padding_free": false,
|
| 218 |
+
"load_safetensors": true,
|
| 219 |
+
"save_safetensors": true,
|
| 220 |
+
"ref_model": null,
|
| 221 |
+
"ref_adapters": [],
|
| 222 |
+
"merge_lora": true,
|
| 223 |
+
"max_shard_size": "5GB",
|
| 224 |
+
"train_dataloader_shuffle": true,
|
| 225 |
+
"dataloader_pin_memory": true,
|
| 226 |
+
"dataloader_persistent_workers": true,
|
| 227 |
+
"dataloader_prefetch_factor": 2,
|
| 228 |
+
"group_by_length": false,
|
| 229 |
+
"hf_model_type": "qwen3",
|
| 230 |
+
"llm_model_type": "qwen3",
|
| 231 |
+
"max_epochs": 2,
|
| 232 |
+
"enable_dft_loss": false,
|
| 233 |
+
"enable_channel_loss": false,
|
| 234 |
+
"save_strategy": "steps",
|
| 235 |
+
"original_max_position_embeddings": null,
|
| 236 |
+
"partial_rotary_factor": null,
|
| 237 |
+
"use_shared_expert_gate": false,
|
| 238 |
+
"report_to": null,
|
| 239 |
+
"vit_gradient_checkpointing": true,
|
| 240 |
+
"vit_lr": null,
|
| 241 |
+
"aligner_lr": null,
|
| 242 |
+
"gradient_checkpointing_kwargs": null,
|
| 243 |
+
"linear_num_value_heads": null,
|
| 244 |
+
"linear_num_key_heads": null,
|
| 245 |
+
"linear_key_head_dim": null,
|
| 246 |
+
"linear_value_head_dim": null,
|
| 247 |
+
"linear_conv_kernel_dim": null,
|
| 248 |
+
"layer_types": null,
|
| 249 |
+
"mrope_interleaved": false,
|
| 250 |
+
"micro_batch_size": 1,
|
| 251 |
+
"global_batch_size": 16,
|
| 252 |
+
"recompute_granularity": "full",
|
| 253 |
+
"recompute_method": "uniform",
|
| 254 |
+
"recompute_num_layers": 1,
|
| 255 |
+
"recompute_modules": [
|
| 256 |
+
"core_attn"
|
| 257 |
+
],
|
| 258 |
+
"use_cpu_initialization": false,
|
| 259 |
+
"deterministic_mode": false,
|
| 260 |
+
"train_iters": null,
|
| 261 |
+
"log_interval": 1,
|
| 262 |
+
"tensorboard_dir": "/data/repotune/train/outputs/mix/mix_8k_bfta_astropy_qwen34i_32k_2ep_v0/v0-20260123-232955/runs",
|
| 263 |
+
"no_masked_softmax_fusion": false,
|
| 264 |
+
"no_bias_dropout_fusion": false,
|
| 265 |
+
"no_bias_swiglu_fusion": false,
|
| 266 |
+
"no_rope_fusion": false,
|
| 267 |
+
"no_gradient_accumulation_fusion": false,
|
| 268 |
+
"cross_entropy_loss_fusion": true,
|
| 269 |
+
"cross_entropy_fusion_impl": "native",
|
| 270 |
+
"calculate_per_token_loss": true,
|
| 271 |
+
"use_flash_attn": false,
|
| 272 |
+
"attention_backend": "flash",
|
| 273 |
+
"optimizer": "adam",
|
| 274 |
+
"optimizer_cpu_offload": false,
|
| 275 |
+
"optimizer_offload_fraction": 1.0,
|
| 276 |
+
"use_precision_aware_optimizer": false,
|
| 277 |
+
"main_grads_dtype": "fp32",
|
| 278 |
+
"main_params_dtype": "fp32",
|
| 279 |
+
"exp_avg_dtype": "fp32",
|
| 280 |
+
"exp_avg_sq_dtype": "fp32",
|
| 281 |
+
"dataloader_type": "cyclic",
|
| 282 |
+
"manual_gc": false,
|
| 283 |
+
"manual_gc_interval": 0,
|
| 284 |
+
"lr": 1e-05,
|
| 285 |
+
"lr_decay_style": "cosine",
|
| 286 |
+
"lr_decay_iters": null,
|
| 287 |
+
"lr_warmup_iters": 0,
|
| 288 |
+
"lr_warmup_fraction": 0.03,
|
| 289 |
+
"min_lr": 1e-06,
|
| 290 |
+
"weight_decay": 0.1,
|
| 291 |
+
"clip_grad": 1.0,
|
| 292 |
+
"adam_beta1": 0.9,
|
| 293 |
+
"adam_beta2": 0.95,
|
| 294 |
+
"adam_eps": 1e-08,
|
| 295 |
+
"sgd_momentum": 0.9,
|
| 296 |
+
"save": "/data/repotune/train/outputs/mix/mix_8k_bfta_astropy_qwen34i_32k_2ep_v0/v0-20260123-232955",
|
| 297 |
+
"save_interval": 512,
|
| 298 |
+
"save_retain_interval": null,
|
| 299 |
+
"no_save_optim": true,
|
| 300 |
+
"no_save_rng": true,
|
| 301 |
+
"load": null,
|
| 302 |
+
"no_load_optim": false,
|
| 303 |
+
"no_load_rng": false,
|
| 304 |
+
"finetune": true,
|
| 305 |
+
"ckpt_format": "torch_dist",
|
| 306 |
+
"no_initialization": true,
|
| 307 |
+
"auto_detect_ckpt_format": true,
|
| 308 |
+
"exit_on_missing_checkpoint": true,
|
| 309 |
+
"async_save": false,
|
| 310 |
+
"use_persistent_ckpt_worker": false,
|
| 311 |
+
"ckpt_fully_parallel_load": false,
|
| 312 |
+
"ckpt_assume_constant_structure": false,
|
| 313 |
+
"distributed_backend": "nccl",
|
| 314 |
+
"local_rank": 0,
|
| 315 |
+
"use_distributed_optimizer": true,
|
| 316 |
+
"tensor_model_parallel_size": 1,
|
| 317 |
+
"pipeline_model_parallel_size": 1,
|
| 318 |
+
"decoder_first_pipeline_num_layers": null,
|
| 319 |
+
"decoder_last_pipeline_num_layers": null,
|
| 320 |
+
"account_for_embedding_in_pipeline_split": false,
|
| 321 |
+
"account_for_loss_in_pipeline_split": false,
|
| 322 |
+
"sequence_parallel": false,
|
| 323 |
+
"context_parallel_size": 1,
|
| 324 |
+
"tp_comm_overlap": false,
|
| 325 |
+
"overlap_grad_reduce": true,
|
| 326 |
+
"overlap_param_gather": true,
|
| 327 |
+
"distributed_timeout_minutes": 300000,
|
| 328 |
+
"num_layers_per_virtual_pipeline_stage": null,
|
| 329 |
+
"num_virtual_stages_per_pipeline_rank": null,
|
| 330 |
+
"microbatch_group_size_per_virtual_pipeline_stage": null,
|
| 331 |
+
"pipeline_model_parallel_layout": null,
|
| 332 |
+
"num_layers": 36,
|
| 333 |
+
"hidden_size": 2560,
|
| 334 |
+
"ffn_hidden_size": 9728,
|
| 335 |
+
"num_attention_heads": 32,
|
| 336 |
+
"group_query_attention": true,
|
| 337 |
+
"num_query_groups": 8,
|
| 338 |
+
"softmax_type": "vanilla",
|
| 339 |
+
"window_size": null,
|
| 340 |
+
"window_attn_skip_freq": null,
|
| 341 |
+
"max_position_embeddings": 262144,
|
| 342 |
+
"position_embedding_type": "rope",
|
| 343 |
+
"mrope_section": null,
|
| 344 |
+
"rotary_base": 5000000,
|
| 345 |
+
"rotary_percent": 1.0,
|
| 346 |
+
"rotary_interleaved": false,
|
| 347 |
+
"normalization": "RMSNorm",
|
| 348 |
+
"norm_epsilon": 1e-06,
|
| 349 |
+
"swiglu": true,
|
| 350 |
+
"quick_geglu": false,
|
| 351 |
+
"activation_func_clamp_value": null,
|
| 352 |
+
"glu_linear_offset": 0.0,
|
| 353 |
+
"untie_embeddings_and_output_weights": false,
|
| 354 |
+
"disable_bias_linear": true,
|
| 355 |
+
"add_qkv_bias": false,
|
| 356 |
+
"attention_dropout": 0.0,
|
| 357 |
+
"hidden_dropout": 0.0,
|
| 358 |
+
"kv_channels": 128,
|
| 359 |
+
"qk_layernorm": true,
|
| 360 |
+
"qk_l2_norm": null,
|
| 361 |
+
"no_rope_freq": null,
|
| 362 |
+
"moe_apply_probs_on_input": null,
|
| 363 |
+
"transformer_impl": "transformer_engine",
|
| 364 |
+
"num_experts": null,
|
| 365 |
+
"moe_layer_freq": 1,
|
| 366 |
+
"moe_ffn_hidden_size": null,
|
| 367 |
+
"moe_shared_expert_intermediate_size": null,
|
| 368 |
+
"moe_router_topk": 2,
|
| 369 |
+
"moe_router_num_groups": null,
|
| 370 |
+
"moe_router_group_topk": null,
|
| 371 |
+
"moe_router_pre_softmax": false,
|
| 372 |
+
"moe_router_dtype": "fp32",
|
| 373 |
+
"moe_router_score_function": "softmax",
|
| 374 |
+
"moe_router_bias_update_rate": null,
|
| 375 |
+
"moe_router_enable_expert_bias": false,
|
| 376 |
+
"moe_router_topk_scaling_factor": null,
|
| 377 |
+
"moe_router_load_balancing_type": "aux_loss",
|
| 378 |
+
"expert_model_parallel_size": 1,
|
| 379 |
+
"expert_tensor_parallel_size": 1,
|
| 380 |
+
"moe_token_dispatcher_type": null,
|
| 381 |
+
"moe_enable_deepep": false,
|
| 382 |
+
"moe_grouped_gemm": true,
|
| 383 |
+
"moe_permute_fusion": false,
|
| 384 |
+
"moe_aux_loss_coeff": 0.0,
|
| 385 |
+
"moe_z_loss_coeff": null,
|
| 386 |
+
"moe_shared_expert_overlap": false,
|
| 387 |
+
"moe_layer_recompute": false,
|
| 388 |
+
"moe_expert_capacity_factor": null,
|
| 389 |
+
"moe_pad_expert_input_to_capacity": false,
|
| 390 |
+
"moe_token_drop_policy": null,
|
| 391 |
+
"multi_latent_attention": false,
|
| 392 |
+
"q_lora_rank": null,
|
| 393 |
+
"kv_lora_rank": 32,
|
| 394 |
+
"qk_head_dim": 128,
|
| 395 |
+
"qk_pos_emb_head_dim": 64,
|
| 396 |
+
"mtp_num_layers": null,
|
| 397 |
+
"mtp_loss_scaling_factor": 0.1,
|
| 398 |
+
"fp8_format": null,
|
| 399 |
+
"fp8_recipe": "delayed",
|
| 400 |
+
"fp8_amax_history_len": 1024,
|
| 401 |
+
"fp8_amax_compute_algo": "max",
|
| 402 |
+
"fp8_param_gather": false,
|
| 403 |
+
"fp16": false,
|
| 404 |
+
"bf16": true,
|
| 405 |
+
"apply_query_key_layer_scaling": false,
|
| 406 |
+
"attention_softmax_in_fp32": true,
|
| 407 |
+
"log_params_norm": false,
|
| 408 |
+
"log_throughput": false,
|
| 409 |
+
"tensorboard_log_interval": 1,
|
| 410 |
+
"tensorboard_queue_size": 50,
|
| 411 |
+
"log_timers_to_tensorboard": true,
|
| 412 |
+
"no_log_learning_rate_to_tensorboard": false,
|
| 413 |
+
"log_validation_ppl_to_tensorboard": true,
|
| 414 |
+
"log_memory_to_tensorboard": true,
|
| 415 |
+
"logging_level": null,
|
| 416 |
+
"wandb_project": "repotune",
|
| 417 |
+
"wandb_exp_name": "mix_8k_bfta_astropy_qwen34i_32k_2ep_v0",
|
| 418 |
+
"wandb_save_dir": null,
|
| 419 |
+
"eval_iters": -1,
|
| 420 |
+
"eval_interval": 256,
|
| 421 |
+
"seq_length": 32768,
|
| 422 |
+
"num_workers": 16,
|
| 423 |
+
"no_data_sharding": false,
|
| 424 |
+
"megatron_extra_kwargs": {},
|
| 425 |
+
"add_version": true,
|
| 426 |
+
"swift_version": "4.0.0.dev0",
|
| 427 |
+
"ckpt_dir": null,
|
| 428 |
+
"rank": 0,
|
| 429 |
+
"global_world_size": 2,
|
| 430 |
+
"local_world_size": 2,
|
| 431 |
+
"model_suffix": "Qwen3-4B-Instruct-2507",
|
| 432 |
+
"model_info": "ModelInfo(model_type='qwen3', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
|
| 433 |
+
"model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', hf_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek_r1', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3Guard-Gen-0.6B', hf_model_id='Qwen/Qwen3Guard-Gen-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-4B', hf_model_id='Qwen/Qwen3Guard-Gen-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3Guard-Gen-8B', hf_model_id='Qwen/Qwen3Guard-Gen-8B', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_guard', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507', hf_model_id='Qwen/Qwen3-4B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_thinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_nothinking', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.register.ModelLoader'>, template='qwen3_nothinking', model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
|
| 434 |
+
"model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
|
| 435 |
+
"_val_dataset_exists": [
|
| 436 |
+
"/data/repotune/data/val/django_e13b714/sbv_msa_gemini25pro.jsonl",
|
| 437 |
+
"/data/repotune/data/val/django_e13b714/sbv_msa_gemini3pro.jsonl"
|
| 438 |
+
],
|
| 439 |
+
"hub": "<class 'swift.hub.hub.HFHub'>",
|
| 440 |
+
"megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'llama', 'codefuse_codellama', 'yi', 'openbuddy_llama', 'qwen3', 'qwen2_moe', 'qwen3_moe', 'internlm3', 'mimo', 'deepseek', 'deepseek_v2', 'deepseek_v3', 'dots1', 'ernie4_5', 'ernie4_5_moe', 'glm4_moe', 'gpt_oss'], is_multimodal=False, bridge_cls=<class 'swift.megatron.model.gpt_bridge.GPTBridge'>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x73a6f09c4400>, visual_cls=None, get_mtp_block_spec=None, extra_args_provider=None)",
|
| 441 |
+
"extra_args": {
|
| 442 |
+
"model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
|
| 443 |
+
"is_multimodal": false,
|
| 444 |
+
"hf_model_type": "qwen3",
|
| 445 |
+
"use_ray": false,
|
| 446 |
+
"ray_exp_name": null,
|
| 447 |
+
"device_groups": null,
|
| 448 |
+
"model": "Qwen/Qwen3-4B-Instruct-2507",
|
| 449 |
+
"model_type": "qwen3",
|
| 450 |
+
"model_revision": null,
|
| 451 |
+
"task_type": "causal_lm",
|
| 452 |
+
"torch_dtype": "bfloat16",
|
| 453 |
+
"attn_impl": null,
|
| 454 |
+
"new_special_tokens": [],
|
| 455 |
+
"num_labels": null,
|
| 456 |
+
"problem_type": null,
|
| 457 |
+
"rope_scaling": null,
|
| 458 |
+
"device_map": null,
|
| 459 |
+
"max_memory": {},
|
| 460 |
+
"max_model_len": null,
|
| 461 |
+
"local_repo_path": null,
|
| 462 |
+
"init_strategy": null,
|
| 463 |
+
"template": "qwen3_nothinking",
|
| 464 |
+
"system": null,
|
| 465 |
+
"max_length": 32768,
|
| 466 |
+
"truncation_strategy": "left",
|
| 467 |
+
"max_pixels": null,
|
| 468 |
+
"agent_template": null,
|
| 469 |
+
"norm_bbox": null,
|
| 470 |
+
"use_chat_template": true,
|
| 471 |
+
"padding_side": "right",
|
| 472 |
+
"padding_free": true,
|
| 473 |
+
"sequence_parallel_size": 1,
|
| 474 |
+
"template_backend": "swift",
|
| 475 |
+
"response_prefix": null,
|
| 476 |
+
"enable_thinking": null,
|
| 477 |
+
"add_non_thinking_prefix": true,
|
| 478 |
+
"dataset": [
|
| 479 |
+
"/data/repotune/data/agentic/bugfix/astropy_20201231_72ca3c07/v1/sft_all.jsonl#2048",
|
| 480 |
+
"/data/repotune/data/agentic/fim/astropy_20201231_72ca3c07/v0/sft_all.jsonl#2048",
|
| 481 |
+
"/data/repotune/data/agentic/testgen/astropy_20201231_72ca3c07/v0/sft_all.jsonl#2048",
|
| 482 |
+
"/data/repotune/data/agentic/ar/astropy_20201231_72ca3c07/sft_all.jsonl#2048"
|
| 483 |
+
],
|
| 484 |
+
"val_dataset": [
|
| 485 |
+
"/data/repotune/data/val/django_e13b714/sbv_msa_gemini25pro.jsonl",
|
| 486 |
+
"/data/repotune/data/val/django_e13b714/sbv_msa_gemini3pro.jsonl"
|
| 487 |
+
],
|
| 488 |
+
"cached_dataset": [],
|
| 489 |
+
"cached_val_dataset": [],
|
| 490 |
+
"split_dataset_ratio": 0.0,
|
| 491 |
+
"data_seed": 42,
|
| 492 |
+
"dataset_num_proc": 16,
|
| 493 |
+
"load_from_cache_file": true,
|
| 494 |
+
"dataset_shuffle": true,
|
| 495 |
+
"val_dataset_shuffle": false,
|
| 496 |
+
"streaming": false,
|
| 497 |
+
"interleave_prob": null,
|
| 498 |
+
"stopping_strategy": "first_exhausted",
|
| 499 |
+
"shuffle_buffer_size": 1000,
|
| 500 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 501 |
+
"columns": {},
|
| 502 |
+
"strict": false,
|
| 503 |
+
"remove_unused_columns": true,
|
| 504 |
+
"model_name": null,
|
| 505 |
+
"model_author": null,
|
| 506 |
+
"custom_dataset_info": [],
|
| 507 |
+
"quant_method": null,
|
| 508 |
+
"quant_bits": null,
|
| 509 |
+
"hqq_axis": null,
|
| 510 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 511 |
+
"bnb_4bit_quant_type": "nf4",
|
| 512 |
+
"bnb_4bit_use_double_quant": true,
|
| 513 |
+
"bnb_4bit_quant_storage": null,
|
| 514 |
+
"max_new_tokens": null,
|
| 515 |
+
"temperature": 0.9,
|
| 516 |
+
"top_k": 50,
|
| 517 |
+
"top_p": 0.9,
|
| 518 |
+
"repetition_penalty": 1.0,
|
| 519 |
+
"num_beams": 1,
|
| 520 |
+
"stream": false,
|
| 521 |
+
"stop_words": [],
|
| 522 |
+
"logprobs": false,
|
| 523 |
+
"top_logprobs": null,
|
| 524 |
+
"structured_outputs_regex": null,
|
| 525 |
+
"tuner_backend": "peft",
|
| 526 |
+
"tuner_type": "full",
|
| 527 |
+
"train_type": "full",
|
| 528 |
+
"adapters": [],
|
| 529 |
+
"external_plugins": [],
|
| 530 |
+
"custom_register_path": [],
|
| 531 |
+
"model_kwargs": {},
|
| 532 |
+
"load_args": false,
|
| 533 |
+
"load_data_args": false,
|
| 534 |
+
"packing": false,
|
| 535 |
+
"packing_length": null,
|
| 536 |
+
"packing_num_proc": 1,
|
| 537 |
+
"lazy_tokenize": false,
|
| 538 |
+
"use_hf": true,
|
| 539 |
+
"hub_token": null,
|
| 540 |
+
"ddp_timeout": 18000000,
|
| 541 |
+
"ddp_backend": null,
|
| 542 |
+
"ignore_args_error": false,
|
| 543 |
+
"use_swift_lora": false,
|
| 544 |
+
"freeze_llm": false,
|
| 545 |
+
"freeze_vit": true,
|
| 546 |
+
"freeze_aligner": true,
|
| 547 |
+
"freeze_parameters": [],
|
| 548 |
+
"freeze_parameters_regex": null,
|
| 549 |
+
"freeze_parameters_ratio": 0.0,
|
| 550 |
+
"trainable_parameters": [],
|
| 551 |
+
"trainable_parameters_regex": null,
|
| 552 |
+
"adapter_load": null,
|
| 553 |
+
"target_modules": [
|
| 554 |
+
"all-linear"
|
| 555 |
+
],
|
| 556 |
+
"target_regex": null,
|
| 557 |
+
"modules_to_save": [],
|
| 558 |
+
"lora_rank": 8,
|
| 559 |
+
"lora_alpha": 32,
|
| 560 |
+
"lora_dropout": 0.05,
|
| 561 |
+
"lora_bias": "none",
|
| 562 |
+
"lora_dtype": null,
|
| 563 |
+
"use_rslora": false,
|
| 564 |
+
"rlhf_type": null,
|
| 565 |
+
"ref_load": null,
|
| 566 |
+
"ref_adapter_load": null,
|
| 567 |
+
"beta": null,
|
| 568 |
+
"rpo_alpha": null,
|
| 569 |
+
"reference_free": false,
|
| 570 |
+
"label_smoothing": 0.0,
|
| 571 |
+
"f_divergence_type": "reverse_kl",
|
| 572 |
+
"loss_type": null,
|
| 573 |
+
"desirable_weight": 1.0,
|
| 574 |
+
"undesirable_weight": 1.0,
|
| 575 |
+
"calculate_KL": null,
|
| 576 |
+
"center_rewards_coefficient": null,
|
| 577 |
+
"teacher_model": null,
|
| 578 |
+
"teacher_model_type": null,
|
| 579 |
+
"teacher_model_revision": null,
|
| 580 |
+
"lmbda": 0.5,
|
| 581 |
+
"seq_kd": false,
|
| 582 |
+
"offload_teacher_model": false,
|
| 583 |
+
"sft_alpha": 0.0,
|
| 584 |
+
"generation_batch_size": null,
|
| 585 |
+
"steps_per_generation": null,
|
| 586 |
+
"num_generations": 8,
|
| 587 |
+
"num_generations_eval": null,
|
| 588 |
+
"max_completion_length": 512,
|
| 589 |
+
"importance_sampling_level": "token",
|
| 590 |
+
"tau_pos": 1.0,
|
| 591 |
+
"tau_neg": 1.05,
|
| 592 |
+
"epsilon": 0.2,
|
| 593 |
+
"epsilon_high": null,
|
| 594 |
+
"delta": null,
|
| 595 |
+
"use_vllm": true,
|
| 596 |
+
"vllm_mode": null,
|
| 597 |
+
"vllm_enable_prefix_caching": true,
|
| 598 |
+
"vllm_gpu_memory_utilization": 0.9,
|
| 599 |
+
"vllm_tensor_parallel_size": 1,
|
| 600 |
+
"vllm_max_model_len": null,
|
| 601 |
+
"vllm_enforce_eager": false,
|
| 602 |
+
"vllm_limit_mm_per_prompt": null,
|
| 603 |
+
"vllm_disable_cascade_attn": false,
|
| 604 |
+
"vllm_max_num_seqs": null,
|
| 605 |
+
"vllm_mm_processor_cache_gb": null,
|
| 606 |
+
"vllm_engine_kwargs": null,
|
| 607 |
+
"sleep_level": 0,
|
| 608 |
+
"offload_optimizer": false,
|
| 609 |
+
"offload_model": false,
|
| 610 |
+
"offload_bridge": false,
|
| 611 |
+
"vllm_server_base_url": null,
|
| 612 |
+
"vllm_server_host": null,
|
| 613 |
+
"vllm_server_port": [
|
| 614 |
+
8000
|
| 615 |
+
],
|
| 616 |
+
"vllm_server_timeout": 240.0,
|
| 617 |
+
"vllm_server_group_port": null,
|
| 618 |
+
"reward_funcs": [],
|
| 619 |
+
"reward_weights": null,
|
| 620 |
+
"cosine_min_len_value_wrong": -0.5,
|
| 621 |
+
"cosine_max_len_value_wrong": 0.0,
|
| 622 |
+
"cosine_min_len_value_correct": 1.0,
|
| 623 |
+
"cosine_max_len_value_correct": 0.5,
|
| 624 |
+
"cosine_max_len": null,
|
| 625 |
+
"repetition_n_grams": 3,
|
| 626 |
+
"repetition_max_penalty": -1.0,
|
| 627 |
+
"soft_max_length": null,
|
| 628 |
+
"soft_cache_length": null,
|
| 629 |
+
"dynamic_sample": false,
|
| 630 |
+
"max_resample_times": 3,
|
| 631 |
+
"overlong_filter": false,
|
| 632 |
+
"scale_rewards": "group",
|
| 633 |
+
"advantage_estimator": "grpo",
|
| 634 |
+
"kl_in_reward": false,
|
| 635 |
+
"wandb_log_unique_prompts": null,
|
| 636 |
+
"log_completions": false,
|
| 637 |
+
"rollout_importance_sampling_mode": null,
|
| 638 |
+
"rollout_importance_sampling_threshold": 2.0,
|
| 639 |
+
"log_rollout_offpolicy_metrics": false,
|
| 640 |
+
"off_policy_sequence_mask_delta": null,
|
| 641 |
+
"log_entropy": false,
|
| 642 |
+
"top_entropy_quantile": 1.0,
|
| 643 |
+
"reward_model": null,
|
| 644 |
+
"reward_model_plugin": null,
|
| 645 |
+
"sync_ref_model": false,
|
| 646 |
+
"ref_model_sync_steps": 512,
|
| 647 |
+
"ref_model_mixup_alpha": 0.6,
|
| 648 |
+
"async_generate": false,
|
| 649 |
+
"move_model_batches": null,
|
| 650 |
+
"multi_turn_scheduler": null,
|
| 651 |
+
"max_turns": null,
|
| 652 |
+
"completion_length_limit_scope": "per_round",
|
| 653 |
+
"vllm_server_pass_dataset": false,
|
| 654 |
+
"num_iterations": 1,
|
| 655 |
+
"check_model": true,
|
| 656 |
+
"padded_vocab_size": 151936,
|
| 657 |
+
"initialize_embedding": false,
|
| 658 |
+
"mlp_padding_free": false,
|
| 659 |
+
"load_safetensors": true,
|
| 660 |
+
"save_safetensors": true,
|
| 661 |
+
"ref_model": null,
|
| 662 |
+
"ref_adapters": [],
|
| 663 |
+
"merge_lora": true,
|
| 664 |
+
"max_shard_size": "5GB",
|
| 665 |
+
"train_dataloader_shuffle": true,
|
| 666 |
+
"dataloader_pin_memory": true,
|
| 667 |
+
"dataloader_persistent_workers": true,
|
| 668 |
+
"dataloader_prefetch_factor": 2,
|
| 669 |
+
"group_by_length": false,
|
| 670 |
+
"llm_model_type": "qwen3",
|
| 671 |
+
"max_epochs": 2,
|
| 672 |
+
"enable_dft_loss": false,
|
| 673 |
+
"enable_channel_loss": false,
|
| 674 |
+
"save_strategy": "steps",
|
| 675 |
+
"original_max_position_embeddings": null,
|
| 676 |
+
"partial_rotary_factor": null,
|
| 677 |
+
"use_shared_expert_gate": false,
|
| 678 |
+
"report_to": null,
|
| 679 |
+
"vit_gradient_checkpointing": true,
|
| 680 |
+
"vit_lr": null,
|
| 681 |
+
"aligner_lr": null,
|
| 682 |
+
"gradient_checkpointing_kwargs": null,
|
| 683 |
+
"linear_num_value_heads": null,
|
| 684 |
+
"linear_num_key_heads": null,
|
| 685 |
+
"linear_key_head_dim": null,
|
| 686 |
+
"linear_value_head_dim": null,
|
| 687 |
+
"linear_conv_kernel_dim": null,
|
| 688 |
+
"layer_types": null,
|
| 689 |
+
"mrope_interleaved": false,
|
| 690 |
+
"add_version": true
|
| 691 |
+
}
|
| 692 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 9728,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 262144,
|
| 54 |
+
"max_window_layers": 36,
|
| 55 |
+
"model_type": "qwen3",
|
| 56 |
+
"num_attention_heads": 32,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"pad_token_id": 151643,
|
| 60 |
+
"rms_norm_eps": 1e-06,
|
| 61 |
+
"rope_scaling": null,
|
| 62 |
+
"rope_theta": 5000000,
|
| 63 |
+
"sliding_window": null,
|
| 64 |
+
"tie_word_embeddings": true,
|
| 65 |
+
"transformers_version": "4.57.6",
|
| 66 |
+
"use_cache": true,
|
| 67 |
+
"use_sliding_window": false,
|
| 68 |
+
"vocab_size": 151936
|
| 69 |
+
}
|
iter_0001024/.metadata
ADDED
|
Binary file (560 Bytes). View file
|
|
|
iter_0001024/common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a2b15a7d18a3454e2c7645b51de6d532053abd1644858cadb55de7b32700928
|
| 3 |
+
size 28199
|
iter_0001024/metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
|
latest_checkpointed_iteration.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
1024
|
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 sha256:89c96b26fa5f9e62909070c0e692b9beaa4eccef0823e85ce4009038f259463d
|
| 3 |
+
size 4967220560
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04ca36fa0adcb68c02fb8c154d1841eaec6eb2270e10ca6c6ca5f5885e32dd5b
|
| 3 |
+
size 3077761384
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,405 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8044936192
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 377 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 378 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 379 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 380 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 381 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 382 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 383 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 384 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 387 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 389 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 393 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 399 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 401 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 402 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 404 |
+
}
|
| 405 |
+
}
|
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1010000,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|