upload model
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- merge_sft_o3/added_tokens.json +24 -0
- merge_sft_o3/chat_template.json +3 -0
- merge_sft_o3/config.json +65 -0
- merge_sft_o3/generation_config.json +6 -0
- merge_sft_o3/info.txt +891 -0
- merge_sft_o3/merges.txt +0 -0
- merge_sft_o3/model-00001-of-00002.safetensors +3 -0
- merge_sft_o3/model-00002-of-00002.safetensors +3 -0
- merge_sft_o3/model.safetensors.index.json +832 -0
- merge_sft_o3/preprocessor_config.json +29 -0
- merge_sft_o3/special_tokens_map.json +1031 -0
- merge_sft_o3/tokenizer_config.json +0 -0
- merge_sft_o3/trainer_state.json +2136 -0
- merge_sft_o3/training_args.bin +3 -0
- merge_sft_o3/vocab.json +0 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/added_tokens.json +24 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/chat_template.json +3 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/config.json +65 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/generation_config.json +7 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/merges.txt +0 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/model-00001-of-00002.safetensors +3 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/model-00002-of-00002.safetensors +3 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/model.safetensors.index.json +832 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/preprocessor_config.json +29 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/special_tokens_map.json +1031 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/tokenizer_config.json +0 -0
- version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/vocab.json +0 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/added_tokens.json +24 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/chat_template.json +3 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/config.json +65 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/generation_config.json +7 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/merges.txt +0 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/model-00001-of-00002.safetensors +3 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/model-00002-of-00002.safetensors +3 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/model.safetensors.index.json +832 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/preprocessor_config.json +29 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/special_tokens_map.json +1031 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/tokenizer_config.json +0 -0
- version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/vocab.json +0 -0
- version2_ori_from_1200_reward1_crop/latest_global_step.txt +1 -0
- version2_ori_from_1200_reward1_crop/log.txt +0 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/added_tokens.json +24 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/chat_template.json +3 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/config.json +65 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/generation_config.json +7 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/merges.txt +0 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/model-00001-of-00002.safetensors +3 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/model-00002-of-00002.safetensors +3 -0
- version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/model.safetensors.index.json +832 -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 |
+
version2_ori_from_1200_reward1_mixed/log.txt filter=lfs diff=lfs merge=lfs -text
|
merge_sft_o3/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
merge_sft_o3/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
merge_sft_o3/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 2048,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
+
"max_window_layers": 70,
|
| 14 |
+
"model_type": "qwen2_5_vl",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_hidden_layers": 36,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"depth": 32,
|
| 39 |
+
"fullatt_block_indexes": [
|
| 40 |
+
7,
|
| 41 |
+
15,
|
| 42 |
+
23,
|
| 43 |
+
31
|
| 44 |
+
],
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 1280,
|
| 47 |
+
"in_channels": 3,
|
| 48 |
+
"in_chans": 3,
|
| 49 |
+
"intermediate_size": 3420,
|
| 50 |
+
"model_type": "qwen2_5_vl",
|
| 51 |
+
"num_heads": 16,
|
| 52 |
+
"out_hidden_size": 2048,
|
| 53 |
+
"patch_size": 14,
|
| 54 |
+
"spatial_merge_size": 2,
|
| 55 |
+
"spatial_patch_size": 14,
|
| 56 |
+
"temporal_patch_size": 2,
|
| 57 |
+
"tokens_per_second": 2,
|
| 58 |
+
"torch_dtype": "bfloat16",
|
| 59 |
+
"window_size": 112
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652,
|
| 63 |
+
"vision_token_id": 151654,
|
| 64 |
+
"vocab_size": 151936
|
| 65 |
+
}
|
merge_sft_o3/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
merge_sft_o3/info.txt
ADDED
|
@@ -0,0 +1,891 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[02/15 15:31:58.881]: git:
|
| 2 |
+
sha: N/A, status: clean, branch: N/A
|
| 3 |
+
|
| 4 |
+
[02/15 15:31:58.882]: Command: train.py --config configs/sft.py --deepspeed scripts/zero2.json --data_flatten False --tune_mm_vision True --tune_mm_mlp True --tune_mm_llm True --bf16 --output_dir work_dirs/merge_sft_o3 --num_train_epochs 0.5 --per_device_train_batch_size 1 --gradient_accumulation_steps 1 --eval_strategy no --save_strategy steps --save_steps 100 --save_total_limit 5 --learning_rate 1e-5 --mm_projector_lr 1e-5 --vision_tower_lr 1e-6 --optim adamw_torch --warmup_ratio 0.03 --weight_decay 0.01 --max_grad_norm 1 --lr_scheduler_type cosine --logging_steps 1 --model_max_length 12800 --gradient_checkpointing True --dataloader_num_workers 0 --run_name merge_sft_o3 --report_to wandb
|
| 5 |
+
[02/15 15:32:01.044]: number of training params:3754622976
|
| 6 |
+
[02/15 15:32:01.046]: Training params:
|
| 7 |
+
{
|
| 8 |
+
"visual.patch_embed.proj.weight": 1505280,
|
| 9 |
+
"visual.blocks.0.norm1.weight": 1280,
|
| 10 |
+
"visual.blocks.0.norm2.weight": 1280,
|
| 11 |
+
"visual.blocks.0.attn.qkv.weight": 4915200,
|
| 12 |
+
"visual.blocks.0.attn.qkv.bias": 3840,
|
| 13 |
+
"visual.blocks.0.attn.proj.weight": 1638400,
|
| 14 |
+
"visual.blocks.0.attn.proj.bias": 1280,
|
| 15 |
+
"visual.blocks.0.mlp.gate_proj.weight": 4377600,
|
| 16 |
+
"visual.blocks.0.mlp.gate_proj.bias": 3420,
|
| 17 |
+
"visual.blocks.0.mlp.up_proj.weight": 4377600,
|
| 18 |
+
"visual.blocks.0.mlp.up_proj.bias": 3420,
|
| 19 |
+
"visual.blocks.0.mlp.down_proj.weight": 4377600,
|
| 20 |
+
"visual.blocks.0.mlp.down_proj.bias": 1280,
|
| 21 |
+
"visual.blocks.1.norm1.weight": 1280,
|
| 22 |
+
"visual.blocks.1.norm2.weight": 1280,
|
| 23 |
+
"visual.blocks.1.attn.qkv.weight": 4915200,
|
| 24 |
+
"visual.blocks.1.attn.qkv.bias": 3840,
|
| 25 |
+
"visual.blocks.1.attn.proj.weight": 1638400,
|
| 26 |
+
"visual.blocks.1.attn.proj.bias": 1280,
|
| 27 |
+
"visual.blocks.1.mlp.gate_proj.weight": 4377600,
|
| 28 |
+
"visual.blocks.1.mlp.gate_proj.bias": 3420,
|
| 29 |
+
"visual.blocks.1.mlp.up_proj.weight": 4377600,
|
| 30 |
+
"visual.blocks.1.mlp.up_proj.bias": 3420,
|
| 31 |
+
"visual.blocks.1.mlp.down_proj.weight": 4377600,
|
| 32 |
+
"visual.blocks.1.mlp.down_proj.bias": 1280,
|
| 33 |
+
"visual.blocks.2.norm1.weight": 1280,
|
| 34 |
+
"visual.blocks.2.norm2.weight": 1280,
|
| 35 |
+
"visual.blocks.2.attn.qkv.weight": 4915200,
|
| 36 |
+
"visual.blocks.2.attn.qkv.bias": 3840,
|
| 37 |
+
"visual.blocks.2.attn.proj.weight": 1638400,
|
| 38 |
+
"visual.blocks.2.attn.proj.bias": 1280,
|
| 39 |
+
"visual.blocks.2.mlp.gate_proj.weight": 4377600,
|
| 40 |
+
"visual.blocks.2.mlp.gate_proj.bias": 3420,
|
| 41 |
+
"visual.blocks.2.mlp.up_proj.weight": 4377600,
|
| 42 |
+
"visual.blocks.2.mlp.up_proj.bias": 3420,
|
| 43 |
+
"visual.blocks.2.mlp.down_proj.weight": 4377600,
|
| 44 |
+
"visual.blocks.2.mlp.down_proj.bias": 1280,
|
| 45 |
+
"visual.blocks.3.norm1.weight": 1280,
|
| 46 |
+
"visual.blocks.3.norm2.weight": 1280,
|
| 47 |
+
"visual.blocks.3.attn.qkv.weight": 4915200,
|
| 48 |
+
"visual.blocks.3.attn.qkv.bias": 3840,
|
| 49 |
+
"visual.blocks.3.attn.proj.weight": 1638400,
|
| 50 |
+
"visual.blocks.3.attn.proj.bias": 1280,
|
| 51 |
+
"visual.blocks.3.mlp.gate_proj.weight": 4377600,
|
| 52 |
+
"visual.blocks.3.mlp.gate_proj.bias": 3420,
|
| 53 |
+
"visual.blocks.3.mlp.up_proj.weight": 4377600,
|
| 54 |
+
"visual.blocks.3.mlp.up_proj.bias": 3420,
|
| 55 |
+
"visual.blocks.3.mlp.down_proj.weight": 4377600,
|
| 56 |
+
"visual.blocks.3.mlp.down_proj.bias": 1280,
|
| 57 |
+
"visual.blocks.4.norm1.weight": 1280,
|
| 58 |
+
"visual.blocks.4.norm2.weight": 1280,
|
| 59 |
+
"visual.blocks.4.attn.qkv.weight": 4915200,
|
| 60 |
+
"visual.blocks.4.attn.qkv.bias": 3840,
|
| 61 |
+
"visual.blocks.4.attn.proj.weight": 1638400,
|
| 62 |
+
"visual.blocks.4.attn.proj.bias": 1280,
|
| 63 |
+
"visual.blocks.4.mlp.gate_proj.weight": 4377600,
|
| 64 |
+
"visual.blocks.4.mlp.gate_proj.bias": 3420,
|
| 65 |
+
"visual.blocks.4.mlp.up_proj.weight": 4377600,
|
| 66 |
+
"visual.blocks.4.mlp.up_proj.bias": 3420,
|
| 67 |
+
"visual.blocks.4.mlp.down_proj.weight": 4377600,
|
| 68 |
+
"visual.blocks.4.mlp.down_proj.bias": 1280,
|
| 69 |
+
"visual.blocks.5.norm1.weight": 1280,
|
| 70 |
+
"visual.blocks.5.norm2.weight": 1280,
|
| 71 |
+
"visual.blocks.5.attn.qkv.weight": 4915200,
|
| 72 |
+
"visual.blocks.5.attn.qkv.bias": 3840,
|
| 73 |
+
"visual.blocks.5.attn.proj.weight": 1638400,
|
| 74 |
+
"visual.blocks.5.attn.proj.bias": 1280,
|
| 75 |
+
"visual.blocks.5.mlp.gate_proj.weight": 4377600,
|
| 76 |
+
"visual.blocks.5.mlp.gate_proj.bias": 3420,
|
| 77 |
+
"visual.blocks.5.mlp.up_proj.weight": 4377600,
|
| 78 |
+
"visual.blocks.5.mlp.up_proj.bias": 3420,
|
| 79 |
+
"visual.blocks.5.mlp.down_proj.weight": 4377600,
|
| 80 |
+
"visual.blocks.5.mlp.down_proj.bias": 1280,
|
| 81 |
+
"visual.blocks.6.norm1.weight": 1280,
|
| 82 |
+
"visual.blocks.6.norm2.weight": 1280,
|
| 83 |
+
"visual.blocks.6.attn.qkv.weight": 4915200,
|
| 84 |
+
"visual.blocks.6.attn.qkv.bias": 3840,
|
| 85 |
+
"visual.blocks.6.attn.proj.weight": 1638400,
|
| 86 |
+
"visual.blocks.6.attn.proj.bias": 1280,
|
| 87 |
+
"visual.blocks.6.mlp.gate_proj.weight": 4377600,
|
| 88 |
+
"visual.blocks.6.mlp.gate_proj.bias": 3420,
|
| 89 |
+
"visual.blocks.6.mlp.up_proj.weight": 4377600,
|
| 90 |
+
"visual.blocks.6.mlp.up_proj.bias": 3420,
|
| 91 |
+
"visual.blocks.6.mlp.down_proj.weight": 4377600,
|
| 92 |
+
"visual.blocks.6.mlp.down_proj.bias": 1280,
|
| 93 |
+
"visual.blocks.7.norm1.weight": 1280,
|
| 94 |
+
"visual.blocks.7.norm2.weight": 1280,
|
| 95 |
+
"visual.blocks.7.attn.qkv.weight": 4915200,
|
| 96 |
+
"visual.blocks.7.attn.qkv.bias": 3840,
|
| 97 |
+
"visual.blocks.7.attn.proj.weight": 1638400,
|
| 98 |
+
"visual.blocks.7.attn.proj.bias": 1280,
|
| 99 |
+
"visual.blocks.7.mlp.gate_proj.weight": 4377600,
|
| 100 |
+
"visual.blocks.7.mlp.gate_proj.bias": 3420,
|
| 101 |
+
"visual.blocks.7.mlp.up_proj.weight": 4377600,
|
| 102 |
+
"visual.blocks.7.mlp.up_proj.bias": 3420,
|
| 103 |
+
"visual.blocks.7.mlp.down_proj.weight": 4377600,
|
| 104 |
+
"visual.blocks.7.mlp.down_proj.bias": 1280,
|
| 105 |
+
"visual.blocks.8.norm1.weight": 1280,
|
| 106 |
+
"visual.blocks.8.norm2.weight": 1280,
|
| 107 |
+
"visual.blocks.8.attn.qkv.weight": 4915200,
|
| 108 |
+
"visual.blocks.8.attn.qkv.bias": 3840,
|
| 109 |
+
"visual.blocks.8.attn.proj.weight": 1638400,
|
| 110 |
+
"visual.blocks.8.attn.proj.bias": 1280,
|
| 111 |
+
"visual.blocks.8.mlp.gate_proj.weight": 4377600,
|
| 112 |
+
"visual.blocks.8.mlp.gate_proj.bias": 3420,
|
| 113 |
+
"visual.blocks.8.mlp.up_proj.weight": 4377600,
|
| 114 |
+
"visual.blocks.8.mlp.up_proj.bias": 3420,
|
| 115 |
+
"visual.blocks.8.mlp.down_proj.weight": 4377600,
|
| 116 |
+
"visual.blocks.8.mlp.down_proj.bias": 1280,
|
| 117 |
+
"visual.blocks.9.norm1.weight": 1280,
|
| 118 |
+
"visual.blocks.9.norm2.weight": 1280,
|
| 119 |
+
"visual.blocks.9.attn.qkv.weight": 4915200,
|
| 120 |
+
"visual.blocks.9.attn.qkv.bias": 3840,
|
| 121 |
+
"visual.blocks.9.attn.proj.weight": 1638400,
|
| 122 |
+
"visual.blocks.9.attn.proj.bias": 1280,
|
| 123 |
+
"visual.blocks.9.mlp.gate_proj.weight": 4377600,
|
| 124 |
+
"visual.blocks.9.mlp.gate_proj.bias": 3420,
|
| 125 |
+
"visual.blocks.9.mlp.up_proj.weight": 4377600,
|
| 126 |
+
"visual.blocks.9.mlp.up_proj.bias": 3420,
|
| 127 |
+
"visual.blocks.9.mlp.down_proj.weight": 4377600,
|
| 128 |
+
"visual.blocks.9.mlp.down_proj.bias": 1280,
|
| 129 |
+
"visual.blocks.10.norm1.weight": 1280,
|
| 130 |
+
"visual.blocks.10.norm2.weight": 1280,
|
| 131 |
+
"visual.blocks.10.attn.qkv.weight": 4915200,
|
| 132 |
+
"visual.blocks.10.attn.qkv.bias": 3840,
|
| 133 |
+
"visual.blocks.10.attn.proj.weight": 1638400,
|
| 134 |
+
"visual.blocks.10.attn.proj.bias": 1280,
|
| 135 |
+
"visual.blocks.10.mlp.gate_proj.weight": 4377600,
|
| 136 |
+
"visual.blocks.10.mlp.gate_proj.bias": 3420,
|
| 137 |
+
"visual.blocks.10.mlp.up_proj.weight": 4377600,
|
| 138 |
+
"visual.blocks.10.mlp.up_proj.bias": 3420,
|
| 139 |
+
"visual.blocks.10.mlp.down_proj.weight": 4377600,
|
| 140 |
+
"visual.blocks.10.mlp.down_proj.bias": 1280,
|
| 141 |
+
"visual.blocks.11.norm1.weight": 1280,
|
| 142 |
+
"visual.blocks.11.norm2.weight": 1280,
|
| 143 |
+
"visual.blocks.11.attn.qkv.weight": 4915200,
|
| 144 |
+
"visual.blocks.11.attn.qkv.bias": 3840,
|
| 145 |
+
"visual.blocks.11.attn.proj.weight": 1638400,
|
| 146 |
+
"visual.blocks.11.attn.proj.bias": 1280,
|
| 147 |
+
"visual.blocks.11.mlp.gate_proj.weight": 4377600,
|
| 148 |
+
"visual.blocks.11.mlp.gate_proj.bias": 3420,
|
| 149 |
+
"visual.blocks.11.mlp.up_proj.weight": 4377600,
|
| 150 |
+
"visual.blocks.11.mlp.up_proj.bias": 3420,
|
| 151 |
+
"visual.blocks.11.mlp.down_proj.weight": 4377600,
|
| 152 |
+
"visual.blocks.11.mlp.down_proj.bias": 1280,
|
| 153 |
+
"visual.blocks.12.norm1.weight": 1280,
|
| 154 |
+
"visual.blocks.12.norm2.weight": 1280,
|
| 155 |
+
"visual.blocks.12.attn.qkv.weight": 4915200,
|
| 156 |
+
"visual.blocks.12.attn.qkv.bias": 3840,
|
| 157 |
+
"visual.blocks.12.attn.proj.weight": 1638400,
|
| 158 |
+
"visual.blocks.12.attn.proj.bias": 1280,
|
| 159 |
+
"visual.blocks.12.mlp.gate_proj.weight": 4377600,
|
| 160 |
+
"visual.blocks.12.mlp.gate_proj.bias": 3420,
|
| 161 |
+
"visual.blocks.12.mlp.up_proj.weight": 4377600,
|
| 162 |
+
"visual.blocks.12.mlp.up_proj.bias": 3420,
|
| 163 |
+
"visual.blocks.12.mlp.down_proj.weight": 4377600,
|
| 164 |
+
"visual.blocks.12.mlp.down_proj.bias": 1280,
|
| 165 |
+
"visual.blocks.13.norm1.weight": 1280,
|
| 166 |
+
"visual.blocks.13.norm2.weight": 1280,
|
| 167 |
+
"visual.blocks.13.attn.qkv.weight": 4915200,
|
| 168 |
+
"visual.blocks.13.attn.qkv.bias": 3840,
|
| 169 |
+
"visual.blocks.13.attn.proj.weight": 1638400,
|
| 170 |
+
"visual.blocks.13.attn.proj.bias": 1280,
|
| 171 |
+
"visual.blocks.13.mlp.gate_proj.weight": 4377600,
|
| 172 |
+
"visual.blocks.13.mlp.gate_proj.bias": 3420,
|
| 173 |
+
"visual.blocks.13.mlp.up_proj.weight": 4377600,
|
| 174 |
+
"visual.blocks.13.mlp.up_proj.bias": 3420,
|
| 175 |
+
"visual.blocks.13.mlp.down_proj.weight": 4377600,
|
| 176 |
+
"visual.blocks.13.mlp.down_proj.bias": 1280,
|
| 177 |
+
"visual.blocks.14.norm1.weight": 1280,
|
| 178 |
+
"visual.blocks.14.norm2.weight": 1280,
|
| 179 |
+
"visual.blocks.14.attn.qkv.weight": 4915200,
|
| 180 |
+
"visual.blocks.14.attn.qkv.bias": 3840,
|
| 181 |
+
"visual.blocks.14.attn.proj.weight": 1638400,
|
| 182 |
+
"visual.blocks.14.attn.proj.bias": 1280,
|
| 183 |
+
"visual.blocks.14.mlp.gate_proj.weight": 4377600,
|
| 184 |
+
"visual.blocks.14.mlp.gate_proj.bias": 3420,
|
| 185 |
+
"visual.blocks.14.mlp.up_proj.weight": 4377600,
|
| 186 |
+
"visual.blocks.14.mlp.up_proj.bias": 3420,
|
| 187 |
+
"visual.blocks.14.mlp.down_proj.weight": 4377600,
|
| 188 |
+
"visual.blocks.14.mlp.down_proj.bias": 1280,
|
| 189 |
+
"visual.blocks.15.norm1.weight": 1280,
|
| 190 |
+
"visual.blocks.15.norm2.weight": 1280,
|
| 191 |
+
"visual.blocks.15.attn.qkv.weight": 4915200,
|
| 192 |
+
"visual.blocks.15.attn.qkv.bias": 3840,
|
| 193 |
+
"visual.blocks.15.attn.proj.weight": 1638400,
|
| 194 |
+
"visual.blocks.15.attn.proj.bias": 1280,
|
| 195 |
+
"visual.blocks.15.mlp.gate_proj.weight": 4377600,
|
| 196 |
+
"visual.blocks.15.mlp.gate_proj.bias": 3420,
|
| 197 |
+
"visual.blocks.15.mlp.up_proj.weight": 4377600,
|
| 198 |
+
"visual.blocks.15.mlp.up_proj.bias": 3420,
|
| 199 |
+
"visual.blocks.15.mlp.down_proj.weight": 4377600,
|
| 200 |
+
"visual.blocks.15.mlp.down_proj.bias": 1280,
|
| 201 |
+
"visual.blocks.16.norm1.weight": 1280,
|
| 202 |
+
"visual.blocks.16.norm2.weight": 1280,
|
| 203 |
+
"visual.blocks.16.attn.qkv.weight": 4915200,
|
| 204 |
+
"visual.blocks.16.attn.qkv.bias": 3840,
|
| 205 |
+
"visual.blocks.16.attn.proj.weight": 1638400,
|
| 206 |
+
"visual.blocks.16.attn.proj.bias": 1280,
|
| 207 |
+
"visual.blocks.16.mlp.gate_proj.weight": 4377600,
|
| 208 |
+
"visual.blocks.16.mlp.gate_proj.bias": 3420,
|
| 209 |
+
"visual.blocks.16.mlp.up_proj.weight": 4377600,
|
| 210 |
+
"visual.blocks.16.mlp.up_proj.bias": 3420,
|
| 211 |
+
"visual.blocks.16.mlp.down_proj.weight": 4377600,
|
| 212 |
+
"visual.blocks.16.mlp.down_proj.bias": 1280,
|
| 213 |
+
"visual.blocks.17.norm1.weight": 1280,
|
| 214 |
+
"visual.blocks.17.norm2.weight": 1280,
|
| 215 |
+
"visual.blocks.17.attn.qkv.weight": 4915200,
|
| 216 |
+
"visual.blocks.17.attn.qkv.bias": 3840,
|
| 217 |
+
"visual.blocks.17.attn.proj.weight": 1638400,
|
| 218 |
+
"visual.blocks.17.attn.proj.bias": 1280,
|
| 219 |
+
"visual.blocks.17.mlp.gate_proj.weight": 4377600,
|
| 220 |
+
"visual.blocks.17.mlp.gate_proj.bias": 3420,
|
| 221 |
+
"visual.blocks.17.mlp.up_proj.weight": 4377600,
|
| 222 |
+
"visual.blocks.17.mlp.up_proj.bias": 3420,
|
| 223 |
+
"visual.blocks.17.mlp.down_proj.weight": 4377600,
|
| 224 |
+
"visual.blocks.17.mlp.down_proj.bias": 1280,
|
| 225 |
+
"visual.blocks.18.norm1.weight": 1280,
|
| 226 |
+
"visual.blocks.18.norm2.weight": 1280,
|
| 227 |
+
"visual.blocks.18.attn.qkv.weight": 4915200,
|
| 228 |
+
"visual.blocks.18.attn.qkv.bias": 3840,
|
| 229 |
+
"visual.blocks.18.attn.proj.weight": 1638400,
|
| 230 |
+
"visual.blocks.18.attn.proj.bias": 1280,
|
| 231 |
+
"visual.blocks.18.mlp.gate_proj.weight": 4377600,
|
| 232 |
+
"visual.blocks.18.mlp.gate_proj.bias": 3420,
|
| 233 |
+
"visual.blocks.18.mlp.up_proj.weight": 4377600,
|
| 234 |
+
"visual.blocks.18.mlp.up_proj.bias": 3420,
|
| 235 |
+
"visual.blocks.18.mlp.down_proj.weight": 4377600,
|
| 236 |
+
"visual.blocks.18.mlp.down_proj.bias": 1280,
|
| 237 |
+
"visual.blocks.19.norm1.weight": 1280,
|
| 238 |
+
"visual.blocks.19.norm2.weight": 1280,
|
| 239 |
+
"visual.blocks.19.attn.qkv.weight": 4915200,
|
| 240 |
+
"visual.blocks.19.attn.qkv.bias": 3840,
|
| 241 |
+
"visual.blocks.19.attn.proj.weight": 1638400,
|
| 242 |
+
"visual.blocks.19.attn.proj.bias": 1280,
|
| 243 |
+
"visual.blocks.19.mlp.gate_proj.weight": 4377600,
|
| 244 |
+
"visual.blocks.19.mlp.gate_proj.bias": 3420,
|
| 245 |
+
"visual.blocks.19.mlp.up_proj.weight": 4377600,
|
| 246 |
+
"visual.blocks.19.mlp.up_proj.bias": 3420,
|
| 247 |
+
"visual.blocks.19.mlp.down_proj.weight": 4377600,
|
| 248 |
+
"visual.blocks.19.mlp.down_proj.bias": 1280,
|
| 249 |
+
"visual.blocks.20.norm1.weight": 1280,
|
| 250 |
+
"visual.blocks.20.norm2.weight": 1280,
|
| 251 |
+
"visual.blocks.20.attn.qkv.weight": 4915200,
|
| 252 |
+
"visual.blocks.20.attn.qkv.bias": 3840,
|
| 253 |
+
"visual.blocks.20.attn.proj.weight": 1638400,
|
| 254 |
+
"visual.blocks.20.attn.proj.bias": 1280,
|
| 255 |
+
"visual.blocks.20.mlp.gate_proj.weight": 4377600,
|
| 256 |
+
"visual.blocks.20.mlp.gate_proj.bias": 3420,
|
| 257 |
+
"visual.blocks.20.mlp.up_proj.weight": 4377600,
|
| 258 |
+
"visual.blocks.20.mlp.up_proj.bias": 3420,
|
| 259 |
+
"visual.blocks.20.mlp.down_proj.weight": 4377600,
|
| 260 |
+
"visual.blocks.20.mlp.down_proj.bias": 1280,
|
| 261 |
+
"visual.blocks.21.norm1.weight": 1280,
|
| 262 |
+
"visual.blocks.21.norm2.weight": 1280,
|
| 263 |
+
"visual.blocks.21.attn.qkv.weight": 4915200,
|
| 264 |
+
"visual.blocks.21.attn.qkv.bias": 3840,
|
| 265 |
+
"visual.blocks.21.attn.proj.weight": 1638400,
|
| 266 |
+
"visual.blocks.21.attn.proj.bias": 1280,
|
| 267 |
+
"visual.blocks.21.mlp.gate_proj.weight": 4377600,
|
| 268 |
+
"visual.blocks.21.mlp.gate_proj.bias": 3420,
|
| 269 |
+
"visual.blocks.21.mlp.up_proj.weight": 4377600,
|
| 270 |
+
"visual.blocks.21.mlp.up_proj.bias": 3420,
|
| 271 |
+
"visual.blocks.21.mlp.down_proj.weight": 4377600,
|
| 272 |
+
"visual.blocks.21.mlp.down_proj.bias": 1280,
|
| 273 |
+
"visual.blocks.22.norm1.weight": 1280,
|
| 274 |
+
"visual.blocks.22.norm2.weight": 1280,
|
| 275 |
+
"visual.blocks.22.attn.qkv.weight": 4915200,
|
| 276 |
+
"visual.blocks.22.attn.qkv.bias": 3840,
|
| 277 |
+
"visual.blocks.22.attn.proj.weight": 1638400,
|
| 278 |
+
"visual.blocks.22.attn.proj.bias": 1280,
|
| 279 |
+
"visual.blocks.22.mlp.gate_proj.weight": 4377600,
|
| 280 |
+
"visual.blocks.22.mlp.gate_proj.bias": 3420,
|
| 281 |
+
"visual.blocks.22.mlp.up_proj.weight": 4377600,
|
| 282 |
+
"visual.blocks.22.mlp.up_proj.bias": 3420,
|
| 283 |
+
"visual.blocks.22.mlp.down_proj.weight": 4377600,
|
| 284 |
+
"visual.blocks.22.mlp.down_proj.bias": 1280,
|
| 285 |
+
"visual.blocks.23.norm1.weight": 1280,
|
| 286 |
+
"visual.blocks.23.norm2.weight": 1280,
|
| 287 |
+
"visual.blocks.23.attn.qkv.weight": 4915200,
|
| 288 |
+
"visual.blocks.23.attn.qkv.bias": 3840,
|
| 289 |
+
"visual.blocks.23.attn.proj.weight": 1638400,
|
| 290 |
+
"visual.blocks.23.attn.proj.bias": 1280,
|
| 291 |
+
"visual.blocks.23.mlp.gate_proj.weight": 4377600,
|
| 292 |
+
"visual.blocks.23.mlp.gate_proj.bias": 3420,
|
| 293 |
+
"visual.blocks.23.mlp.up_proj.weight": 4377600,
|
| 294 |
+
"visual.blocks.23.mlp.up_proj.bias": 3420,
|
| 295 |
+
"visual.blocks.23.mlp.down_proj.weight": 4377600,
|
| 296 |
+
"visual.blocks.23.mlp.down_proj.bias": 1280,
|
| 297 |
+
"visual.blocks.24.norm1.weight": 1280,
|
| 298 |
+
"visual.blocks.24.norm2.weight": 1280,
|
| 299 |
+
"visual.blocks.24.attn.qkv.weight": 4915200,
|
| 300 |
+
"visual.blocks.24.attn.qkv.bias": 3840,
|
| 301 |
+
"visual.blocks.24.attn.proj.weight": 1638400,
|
| 302 |
+
"visual.blocks.24.attn.proj.bias": 1280,
|
| 303 |
+
"visual.blocks.24.mlp.gate_proj.weight": 4377600,
|
| 304 |
+
"visual.blocks.24.mlp.gate_proj.bias": 3420,
|
| 305 |
+
"visual.blocks.24.mlp.up_proj.weight": 4377600,
|
| 306 |
+
"visual.blocks.24.mlp.up_proj.bias": 3420,
|
| 307 |
+
"visual.blocks.24.mlp.down_proj.weight": 4377600,
|
| 308 |
+
"visual.blocks.24.mlp.down_proj.bias": 1280,
|
| 309 |
+
"visual.blocks.25.norm1.weight": 1280,
|
| 310 |
+
"visual.blocks.25.norm2.weight": 1280,
|
| 311 |
+
"visual.blocks.25.attn.qkv.weight": 4915200,
|
| 312 |
+
"visual.blocks.25.attn.qkv.bias": 3840,
|
| 313 |
+
"visual.blocks.25.attn.proj.weight": 1638400,
|
| 314 |
+
"visual.blocks.25.attn.proj.bias": 1280,
|
| 315 |
+
"visual.blocks.25.mlp.gate_proj.weight": 4377600,
|
| 316 |
+
"visual.blocks.25.mlp.gate_proj.bias": 3420,
|
| 317 |
+
"visual.blocks.25.mlp.up_proj.weight": 4377600,
|
| 318 |
+
"visual.blocks.25.mlp.up_proj.bias": 3420,
|
| 319 |
+
"visual.blocks.25.mlp.down_proj.weight": 4377600,
|
| 320 |
+
"visual.blocks.25.mlp.down_proj.bias": 1280,
|
| 321 |
+
"visual.blocks.26.norm1.weight": 1280,
|
| 322 |
+
"visual.blocks.26.norm2.weight": 1280,
|
| 323 |
+
"visual.blocks.26.attn.qkv.weight": 4915200,
|
| 324 |
+
"visual.blocks.26.attn.qkv.bias": 3840,
|
| 325 |
+
"visual.blocks.26.attn.proj.weight": 1638400,
|
| 326 |
+
"visual.blocks.26.attn.proj.bias": 1280,
|
| 327 |
+
"visual.blocks.26.mlp.gate_proj.weight": 4377600,
|
| 328 |
+
"visual.blocks.26.mlp.gate_proj.bias": 3420,
|
| 329 |
+
"visual.blocks.26.mlp.up_proj.weight": 4377600,
|
| 330 |
+
"visual.blocks.26.mlp.up_proj.bias": 3420,
|
| 331 |
+
"visual.blocks.26.mlp.down_proj.weight": 4377600,
|
| 332 |
+
"visual.blocks.26.mlp.down_proj.bias": 1280,
|
| 333 |
+
"visual.blocks.27.norm1.weight": 1280,
|
| 334 |
+
"visual.blocks.27.norm2.weight": 1280,
|
| 335 |
+
"visual.blocks.27.attn.qkv.weight": 4915200,
|
| 336 |
+
"visual.blocks.27.attn.qkv.bias": 3840,
|
| 337 |
+
"visual.blocks.27.attn.proj.weight": 1638400,
|
| 338 |
+
"visual.blocks.27.attn.proj.bias": 1280,
|
| 339 |
+
"visual.blocks.27.mlp.gate_proj.weight": 4377600,
|
| 340 |
+
"visual.blocks.27.mlp.gate_proj.bias": 3420,
|
| 341 |
+
"visual.blocks.27.mlp.up_proj.weight": 4377600,
|
| 342 |
+
"visual.blocks.27.mlp.up_proj.bias": 3420,
|
| 343 |
+
"visual.blocks.27.mlp.down_proj.weight": 4377600,
|
| 344 |
+
"visual.blocks.27.mlp.down_proj.bias": 1280,
|
| 345 |
+
"visual.blocks.28.norm1.weight": 1280,
|
| 346 |
+
"visual.blocks.28.norm2.weight": 1280,
|
| 347 |
+
"visual.blocks.28.attn.qkv.weight": 4915200,
|
| 348 |
+
"visual.blocks.28.attn.qkv.bias": 3840,
|
| 349 |
+
"visual.blocks.28.attn.proj.weight": 1638400,
|
| 350 |
+
"visual.blocks.28.attn.proj.bias": 1280,
|
| 351 |
+
"visual.blocks.28.mlp.gate_proj.weight": 4377600,
|
| 352 |
+
"visual.blocks.28.mlp.gate_proj.bias": 3420,
|
| 353 |
+
"visual.blocks.28.mlp.up_proj.weight": 4377600,
|
| 354 |
+
"visual.blocks.28.mlp.up_proj.bias": 3420,
|
| 355 |
+
"visual.blocks.28.mlp.down_proj.weight": 4377600,
|
| 356 |
+
"visual.blocks.28.mlp.down_proj.bias": 1280,
|
| 357 |
+
"visual.blocks.29.norm1.weight": 1280,
|
| 358 |
+
"visual.blocks.29.norm2.weight": 1280,
|
| 359 |
+
"visual.blocks.29.attn.qkv.weight": 4915200,
|
| 360 |
+
"visual.blocks.29.attn.qkv.bias": 3840,
|
| 361 |
+
"visual.blocks.29.attn.proj.weight": 1638400,
|
| 362 |
+
"visual.blocks.29.attn.proj.bias": 1280,
|
| 363 |
+
"visual.blocks.29.mlp.gate_proj.weight": 4377600,
|
| 364 |
+
"visual.blocks.29.mlp.gate_proj.bias": 3420,
|
| 365 |
+
"visual.blocks.29.mlp.up_proj.weight": 4377600,
|
| 366 |
+
"visual.blocks.29.mlp.up_proj.bias": 3420,
|
| 367 |
+
"visual.blocks.29.mlp.down_proj.weight": 4377600,
|
| 368 |
+
"visual.blocks.29.mlp.down_proj.bias": 1280,
|
| 369 |
+
"visual.blocks.30.norm1.weight": 1280,
|
| 370 |
+
"visual.blocks.30.norm2.weight": 1280,
|
| 371 |
+
"visual.blocks.30.attn.qkv.weight": 4915200,
|
| 372 |
+
"visual.blocks.30.attn.qkv.bias": 3840,
|
| 373 |
+
"visual.blocks.30.attn.proj.weight": 1638400,
|
| 374 |
+
"visual.blocks.30.attn.proj.bias": 1280,
|
| 375 |
+
"visual.blocks.30.mlp.gate_proj.weight": 4377600,
|
| 376 |
+
"visual.blocks.30.mlp.gate_proj.bias": 3420,
|
| 377 |
+
"visual.blocks.30.mlp.up_proj.weight": 4377600,
|
| 378 |
+
"visual.blocks.30.mlp.up_proj.bias": 3420,
|
| 379 |
+
"visual.blocks.30.mlp.down_proj.weight": 4377600,
|
| 380 |
+
"visual.blocks.30.mlp.down_proj.bias": 1280,
|
| 381 |
+
"visual.blocks.31.norm1.weight": 1280,
|
| 382 |
+
"visual.blocks.31.norm2.weight": 1280,
|
| 383 |
+
"visual.blocks.31.attn.qkv.weight": 4915200,
|
| 384 |
+
"visual.blocks.31.attn.qkv.bias": 3840,
|
| 385 |
+
"visual.blocks.31.attn.proj.weight": 1638400,
|
| 386 |
+
"visual.blocks.31.attn.proj.bias": 1280,
|
| 387 |
+
"visual.blocks.31.mlp.gate_proj.weight": 4377600,
|
| 388 |
+
"visual.blocks.31.mlp.gate_proj.bias": 3420,
|
| 389 |
+
"visual.blocks.31.mlp.up_proj.weight": 4377600,
|
| 390 |
+
"visual.blocks.31.mlp.up_proj.bias": 3420,
|
| 391 |
+
"visual.blocks.31.mlp.down_proj.weight": 4377600,
|
| 392 |
+
"visual.blocks.31.mlp.down_proj.bias": 1280,
|
| 393 |
+
"visual.merger.ln_q.weight": 1280,
|
| 394 |
+
"visual.merger.mlp.0.weight": 26214400,
|
| 395 |
+
"visual.merger.mlp.0.bias": 5120,
|
| 396 |
+
"visual.merger.mlp.2.weight": 10485760,
|
| 397 |
+
"visual.merger.mlp.2.bias": 2048,
|
| 398 |
+
"model.embed_tokens.weight": 311164928,
|
| 399 |
+
"model.layers.0.self_attn.q_proj.weight": 4194304,
|
| 400 |
+
"model.layers.0.self_attn.q_proj.bias": 2048,
|
| 401 |
+
"model.layers.0.self_attn.k_proj.weight": 524288,
|
| 402 |
+
"model.layers.0.self_attn.k_proj.bias": 256,
|
| 403 |
+
"model.layers.0.self_attn.v_proj.weight": 524288,
|
| 404 |
+
"model.layers.0.self_attn.v_proj.bias": 256,
|
| 405 |
+
"model.layers.0.self_attn.o_proj.weight": 4194304,
|
| 406 |
+
"model.layers.0.mlp.gate_proj.weight": 22544384,
|
| 407 |
+
"model.layers.0.mlp.up_proj.weight": 22544384,
|
| 408 |
+
"model.layers.0.mlp.down_proj.weight": 22544384,
|
| 409 |
+
"model.layers.0.input_layernorm.weight": 2048,
|
| 410 |
+
"model.layers.0.post_attention_layernorm.weight": 2048,
|
| 411 |
+
"model.layers.1.self_attn.q_proj.weight": 4194304,
|
| 412 |
+
"model.layers.1.self_attn.q_proj.bias": 2048,
|
| 413 |
+
"model.layers.1.self_attn.k_proj.weight": 524288,
|
| 414 |
+
"model.layers.1.self_attn.k_proj.bias": 256,
|
| 415 |
+
"model.layers.1.self_attn.v_proj.weight": 524288,
|
| 416 |
+
"model.layers.1.self_attn.v_proj.bias": 256,
|
| 417 |
+
"model.layers.1.self_attn.o_proj.weight": 4194304,
|
| 418 |
+
"model.layers.1.mlp.gate_proj.weight": 22544384,
|
| 419 |
+
"model.layers.1.mlp.up_proj.weight": 22544384,
|
| 420 |
+
"model.layers.1.mlp.down_proj.weight": 22544384,
|
| 421 |
+
"model.layers.1.input_layernorm.weight": 2048,
|
| 422 |
+
"model.layers.1.post_attention_layernorm.weight": 2048,
|
| 423 |
+
"model.layers.2.self_attn.q_proj.weight": 4194304,
|
| 424 |
+
"model.layers.2.self_attn.q_proj.bias": 2048,
|
| 425 |
+
"model.layers.2.self_attn.k_proj.weight": 524288,
|
| 426 |
+
"model.layers.2.self_attn.k_proj.bias": 256,
|
| 427 |
+
"model.layers.2.self_attn.v_proj.weight": 524288,
|
| 428 |
+
"model.layers.2.self_attn.v_proj.bias": 256,
|
| 429 |
+
"model.layers.2.self_attn.o_proj.weight": 4194304,
|
| 430 |
+
"model.layers.2.mlp.gate_proj.weight": 22544384,
|
| 431 |
+
"model.layers.2.mlp.up_proj.weight": 22544384,
|
| 432 |
+
"model.layers.2.mlp.down_proj.weight": 22544384,
|
| 433 |
+
"model.layers.2.input_layernorm.weight": 2048,
|
| 434 |
+
"model.layers.2.post_attention_layernorm.weight": 2048,
|
| 435 |
+
"model.layers.3.self_attn.q_proj.weight": 4194304,
|
| 436 |
+
"model.layers.3.self_attn.q_proj.bias": 2048,
|
| 437 |
+
"model.layers.3.self_attn.k_proj.weight": 524288,
|
| 438 |
+
"model.layers.3.self_attn.k_proj.bias": 256,
|
| 439 |
+
"model.layers.3.self_attn.v_proj.weight": 524288,
|
| 440 |
+
"model.layers.3.self_attn.v_proj.bias": 256,
|
| 441 |
+
"model.layers.3.self_attn.o_proj.weight": 4194304,
|
| 442 |
+
"model.layers.3.mlp.gate_proj.weight": 22544384,
|
| 443 |
+
"model.layers.3.mlp.up_proj.weight": 22544384,
|
| 444 |
+
"model.layers.3.mlp.down_proj.weight": 22544384,
|
| 445 |
+
"model.layers.3.input_layernorm.weight": 2048,
|
| 446 |
+
"model.layers.3.post_attention_layernorm.weight": 2048,
|
| 447 |
+
"model.layers.4.self_attn.q_proj.weight": 4194304,
|
| 448 |
+
"model.layers.4.self_attn.q_proj.bias": 2048,
|
| 449 |
+
"model.layers.4.self_attn.k_proj.weight": 524288,
|
| 450 |
+
"model.layers.4.self_attn.k_proj.bias": 256,
|
| 451 |
+
"model.layers.4.self_attn.v_proj.weight": 524288,
|
| 452 |
+
"model.layers.4.self_attn.v_proj.bias": 256,
|
| 453 |
+
"model.layers.4.self_attn.o_proj.weight": 4194304,
|
| 454 |
+
"model.layers.4.mlp.gate_proj.weight": 22544384,
|
| 455 |
+
"model.layers.4.mlp.up_proj.weight": 22544384,
|
| 456 |
+
"model.layers.4.mlp.down_proj.weight": 22544384,
|
| 457 |
+
"model.layers.4.input_layernorm.weight": 2048,
|
| 458 |
+
"model.layers.4.post_attention_layernorm.weight": 2048,
|
| 459 |
+
"model.layers.5.self_attn.q_proj.weight": 4194304,
|
| 460 |
+
"model.layers.5.self_attn.q_proj.bias": 2048,
|
| 461 |
+
"model.layers.5.self_attn.k_proj.weight": 524288,
|
| 462 |
+
"model.layers.5.self_attn.k_proj.bias": 256,
|
| 463 |
+
"model.layers.5.self_attn.v_proj.weight": 524288,
|
| 464 |
+
"model.layers.5.self_attn.v_proj.bias": 256,
|
| 465 |
+
"model.layers.5.self_attn.o_proj.weight": 4194304,
|
| 466 |
+
"model.layers.5.mlp.gate_proj.weight": 22544384,
|
| 467 |
+
"model.layers.5.mlp.up_proj.weight": 22544384,
|
| 468 |
+
"model.layers.5.mlp.down_proj.weight": 22544384,
|
| 469 |
+
"model.layers.5.input_layernorm.weight": 2048,
|
| 470 |
+
"model.layers.5.post_attention_layernorm.weight": 2048,
|
| 471 |
+
"model.layers.6.self_attn.q_proj.weight": 4194304,
|
| 472 |
+
"model.layers.6.self_attn.q_proj.bias": 2048,
|
| 473 |
+
"model.layers.6.self_attn.k_proj.weight": 524288,
|
| 474 |
+
"model.layers.6.self_attn.k_proj.bias": 256,
|
| 475 |
+
"model.layers.6.self_attn.v_proj.weight": 524288,
|
| 476 |
+
"model.layers.6.self_attn.v_proj.bias": 256,
|
| 477 |
+
"model.layers.6.self_attn.o_proj.weight": 4194304,
|
| 478 |
+
"model.layers.6.mlp.gate_proj.weight": 22544384,
|
| 479 |
+
"model.layers.6.mlp.up_proj.weight": 22544384,
|
| 480 |
+
"model.layers.6.mlp.down_proj.weight": 22544384,
|
| 481 |
+
"model.layers.6.input_layernorm.weight": 2048,
|
| 482 |
+
"model.layers.6.post_attention_layernorm.weight": 2048,
|
| 483 |
+
"model.layers.7.self_attn.q_proj.weight": 4194304,
|
| 484 |
+
"model.layers.7.self_attn.q_proj.bias": 2048,
|
| 485 |
+
"model.layers.7.self_attn.k_proj.weight": 524288,
|
| 486 |
+
"model.layers.7.self_attn.k_proj.bias": 256,
|
| 487 |
+
"model.layers.7.self_attn.v_proj.weight": 524288,
|
| 488 |
+
"model.layers.7.self_attn.v_proj.bias": 256,
|
| 489 |
+
"model.layers.7.self_attn.o_proj.weight": 4194304,
|
| 490 |
+
"model.layers.7.mlp.gate_proj.weight": 22544384,
|
| 491 |
+
"model.layers.7.mlp.up_proj.weight": 22544384,
|
| 492 |
+
"model.layers.7.mlp.down_proj.weight": 22544384,
|
| 493 |
+
"model.layers.7.input_layernorm.weight": 2048,
|
| 494 |
+
"model.layers.7.post_attention_layernorm.weight": 2048,
|
| 495 |
+
"model.layers.8.self_attn.q_proj.weight": 4194304,
|
| 496 |
+
"model.layers.8.self_attn.q_proj.bias": 2048,
|
| 497 |
+
"model.layers.8.self_attn.k_proj.weight": 524288,
|
| 498 |
+
"model.layers.8.self_attn.k_proj.bias": 256,
|
| 499 |
+
"model.layers.8.self_attn.v_proj.weight": 524288,
|
| 500 |
+
"model.layers.8.self_attn.v_proj.bias": 256,
|
| 501 |
+
"model.layers.8.self_attn.o_proj.weight": 4194304,
|
| 502 |
+
"model.layers.8.mlp.gate_proj.weight": 22544384,
|
| 503 |
+
"model.layers.8.mlp.up_proj.weight": 22544384,
|
| 504 |
+
"model.layers.8.mlp.down_proj.weight": 22544384,
|
| 505 |
+
"model.layers.8.input_layernorm.weight": 2048,
|
| 506 |
+
"model.layers.8.post_attention_layernorm.weight": 2048,
|
| 507 |
+
"model.layers.9.self_attn.q_proj.weight": 4194304,
|
| 508 |
+
"model.layers.9.self_attn.q_proj.bias": 2048,
|
| 509 |
+
"model.layers.9.self_attn.k_proj.weight": 524288,
|
| 510 |
+
"model.layers.9.self_attn.k_proj.bias": 256,
|
| 511 |
+
"model.layers.9.self_attn.v_proj.weight": 524288,
|
| 512 |
+
"model.layers.9.self_attn.v_proj.bias": 256,
|
| 513 |
+
"model.layers.9.self_attn.o_proj.weight": 4194304,
|
| 514 |
+
"model.layers.9.mlp.gate_proj.weight": 22544384,
|
| 515 |
+
"model.layers.9.mlp.up_proj.weight": 22544384,
|
| 516 |
+
"model.layers.9.mlp.down_proj.weight": 22544384,
|
| 517 |
+
"model.layers.9.input_layernorm.weight": 2048,
|
| 518 |
+
"model.layers.9.post_attention_layernorm.weight": 2048,
|
| 519 |
+
"model.layers.10.self_attn.q_proj.weight": 4194304,
|
| 520 |
+
"model.layers.10.self_attn.q_proj.bias": 2048,
|
| 521 |
+
"model.layers.10.self_attn.k_proj.weight": 524288,
|
| 522 |
+
"model.layers.10.self_attn.k_proj.bias": 256,
|
| 523 |
+
"model.layers.10.self_attn.v_proj.weight": 524288,
|
| 524 |
+
"model.layers.10.self_attn.v_proj.bias": 256,
|
| 525 |
+
"model.layers.10.self_attn.o_proj.weight": 4194304,
|
| 526 |
+
"model.layers.10.mlp.gate_proj.weight": 22544384,
|
| 527 |
+
"model.layers.10.mlp.up_proj.weight": 22544384,
|
| 528 |
+
"model.layers.10.mlp.down_proj.weight": 22544384,
|
| 529 |
+
"model.layers.10.input_layernorm.weight": 2048,
|
| 530 |
+
"model.layers.10.post_attention_layernorm.weight": 2048,
|
| 531 |
+
"model.layers.11.self_attn.q_proj.weight": 4194304,
|
| 532 |
+
"model.layers.11.self_attn.q_proj.bias": 2048,
|
| 533 |
+
"model.layers.11.self_attn.k_proj.weight": 524288,
|
| 534 |
+
"model.layers.11.self_attn.k_proj.bias": 256,
|
| 535 |
+
"model.layers.11.self_attn.v_proj.weight": 524288,
|
| 536 |
+
"model.layers.11.self_attn.v_proj.bias": 256,
|
| 537 |
+
"model.layers.11.self_attn.o_proj.weight": 4194304,
|
| 538 |
+
"model.layers.11.mlp.gate_proj.weight": 22544384,
|
| 539 |
+
"model.layers.11.mlp.up_proj.weight": 22544384,
|
| 540 |
+
"model.layers.11.mlp.down_proj.weight": 22544384,
|
| 541 |
+
"model.layers.11.input_layernorm.weight": 2048,
|
| 542 |
+
"model.layers.11.post_attention_layernorm.weight": 2048,
|
| 543 |
+
"model.layers.12.self_attn.q_proj.weight": 4194304,
|
| 544 |
+
"model.layers.12.self_attn.q_proj.bias": 2048,
|
| 545 |
+
"model.layers.12.self_attn.k_proj.weight": 524288,
|
| 546 |
+
"model.layers.12.self_attn.k_proj.bias": 256,
|
| 547 |
+
"model.layers.12.self_attn.v_proj.weight": 524288,
|
| 548 |
+
"model.layers.12.self_attn.v_proj.bias": 256,
|
| 549 |
+
"model.layers.12.self_attn.o_proj.weight": 4194304,
|
| 550 |
+
"model.layers.12.mlp.gate_proj.weight": 22544384,
|
| 551 |
+
"model.layers.12.mlp.up_proj.weight": 22544384,
|
| 552 |
+
"model.layers.12.mlp.down_proj.weight": 22544384,
|
| 553 |
+
"model.layers.12.input_layernorm.weight": 2048,
|
| 554 |
+
"model.layers.12.post_attention_layernorm.weight": 2048,
|
| 555 |
+
"model.layers.13.self_attn.q_proj.weight": 4194304,
|
| 556 |
+
"model.layers.13.self_attn.q_proj.bias": 2048,
|
| 557 |
+
"model.layers.13.self_attn.k_proj.weight": 524288,
|
| 558 |
+
"model.layers.13.self_attn.k_proj.bias": 256,
|
| 559 |
+
"model.layers.13.self_attn.v_proj.weight": 524288,
|
| 560 |
+
"model.layers.13.self_attn.v_proj.bias": 256,
|
| 561 |
+
"model.layers.13.self_attn.o_proj.weight": 4194304,
|
| 562 |
+
"model.layers.13.mlp.gate_proj.weight": 22544384,
|
| 563 |
+
"model.layers.13.mlp.up_proj.weight": 22544384,
|
| 564 |
+
"model.layers.13.mlp.down_proj.weight": 22544384,
|
| 565 |
+
"model.layers.13.input_layernorm.weight": 2048,
|
| 566 |
+
"model.layers.13.post_attention_layernorm.weight": 2048,
|
| 567 |
+
"model.layers.14.self_attn.q_proj.weight": 4194304,
|
| 568 |
+
"model.layers.14.self_attn.q_proj.bias": 2048,
|
| 569 |
+
"model.layers.14.self_attn.k_proj.weight": 524288,
|
| 570 |
+
"model.layers.14.self_attn.k_proj.bias": 256,
|
| 571 |
+
"model.layers.14.self_attn.v_proj.weight": 524288,
|
| 572 |
+
"model.layers.14.self_attn.v_proj.bias": 256,
|
| 573 |
+
"model.layers.14.self_attn.o_proj.weight": 4194304,
|
| 574 |
+
"model.layers.14.mlp.gate_proj.weight": 22544384,
|
| 575 |
+
"model.layers.14.mlp.up_proj.weight": 22544384,
|
| 576 |
+
"model.layers.14.mlp.down_proj.weight": 22544384,
|
| 577 |
+
"model.layers.14.input_layernorm.weight": 2048,
|
| 578 |
+
"model.layers.14.post_attention_layernorm.weight": 2048,
|
| 579 |
+
"model.layers.15.self_attn.q_proj.weight": 4194304,
|
| 580 |
+
"model.layers.15.self_attn.q_proj.bias": 2048,
|
| 581 |
+
"model.layers.15.self_attn.k_proj.weight": 524288,
|
| 582 |
+
"model.layers.15.self_attn.k_proj.bias": 256,
|
| 583 |
+
"model.layers.15.self_attn.v_proj.weight": 524288,
|
| 584 |
+
"model.layers.15.self_attn.v_proj.bias": 256,
|
| 585 |
+
"model.layers.15.self_attn.o_proj.weight": 4194304,
|
| 586 |
+
"model.layers.15.mlp.gate_proj.weight": 22544384,
|
| 587 |
+
"model.layers.15.mlp.up_proj.weight": 22544384,
|
| 588 |
+
"model.layers.15.mlp.down_proj.weight": 22544384,
|
| 589 |
+
"model.layers.15.input_layernorm.weight": 2048,
|
| 590 |
+
"model.layers.15.post_attention_layernorm.weight": 2048,
|
| 591 |
+
"model.layers.16.self_attn.q_proj.weight": 4194304,
|
| 592 |
+
"model.layers.16.self_attn.q_proj.bias": 2048,
|
| 593 |
+
"model.layers.16.self_attn.k_proj.weight": 524288,
|
| 594 |
+
"model.layers.16.self_attn.k_proj.bias": 256,
|
| 595 |
+
"model.layers.16.self_attn.v_proj.weight": 524288,
|
| 596 |
+
"model.layers.16.self_attn.v_proj.bias": 256,
|
| 597 |
+
"model.layers.16.self_attn.o_proj.weight": 4194304,
|
| 598 |
+
"model.layers.16.mlp.gate_proj.weight": 22544384,
|
| 599 |
+
"model.layers.16.mlp.up_proj.weight": 22544384,
|
| 600 |
+
"model.layers.16.mlp.down_proj.weight": 22544384,
|
| 601 |
+
"model.layers.16.input_layernorm.weight": 2048,
|
| 602 |
+
"model.layers.16.post_attention_layernorm.weight": 2048,
|
| 603 |
+
"model.layers.17.self_attn.q_proj.weight": 4194304,
|
| 604 |
+
"model.layers.17.self_attn.q_proj.bias": 2048,
|
| 605 |
+
"model.layers.17.self_attn.k_proj.weight": 524288,
|
| 606 |
+
"model.layers.17.self_attn.k_proj.bias": 256,
|
| 607 |
+
"model.layers.17.self_attn.v_proj.weight": 524288,
|
| 608 |
+
"model.layers.17.self_attn.v_proj.bias": 256,
|
| 609 |
+
"model.layers.17.self_attn.o_proj.weight": 4194304,
|
| 610 |
+
"model.layers.17.mlp.gate_proj.weight": 22544384,
|
| 611 |
+
"model.layers.17.mlp.up_proj.weight": 22544384,
|
| 612 |
+
"model.layers.17.mlp.down_proj.weight": 22544384,
|
| 613 |
+
"model.layers.17.input_layernorm.weight": 2048,
|
| 614 |
+
"model.layers.17.post_attention_layernorm.weight": 2048,
|
| 615 |
+
"model.layers.18.self_attn.q_proj.weight": 4194304,
|
| 616 |
+
"model.layers.18.self_attn.q_proj.bias": 2048,
|
| 617 |
+
"model.layers.18.self_attn.k_proj.weight": 524288,
|
| 618 |
+
"model.layers.18.self_attn.k_proj.bias": 256,
|
| 619 |
+
"model.layers.18.self_attn.v_proj.weight": 524288,
|
| 620 |
+
"model.layers.18.self_attn.v_proj.bias": 256,
|
| 621 |
+
"model.layers.18.self_attn.o_proj.weight": 4194304,
|
| 622 |
+
"model.layers.18.mlp.gate_proj.weight": 22544384,
|
| 623 |
+
"model.layers.18.mlp.up_proj.weight": 22544384,
|
| 624 |
+
"model.layers.18.mlp.down_proj.weight": 22544384,
|
| 625 |
+
"model.layers.18.input_layernorm.weight": 2048,
|
| 626 |
+
"model.layers.18.post_attention_layernorm.weight": 2048,
|
| 627 |
+
"model.layers.19.self_attn.q_proj.weight": 4194304,
|
| 628 |
+
"model.layers.19.self_attn.q_proj.bias": 2048,
|
| 629 |
+
"model.layers.19.self_attn.k_proj.weight": 524288,
|
| 630 |
+
"model.layers.19.self_attn.k_proj.bias": 256,
|
| 631 |
+
"model.layers.19.self_attn.v_proj.weight": 524288,
|
| 632 |
+
"model.layers.19.self_attn.v_proj.bias": 256,
|
| 633 |
+
"model.layers.19.self_attn.o_proj.weight": 4194304,
|
| 634 |
+
"model.layers.19.mlp.gate_proj.weight": 22544384,
|
| 635 |
+
"model.layers.19.mlp.up_proj.weight": 22544384,
|
| 636 |
+
"model.layers.19.mlp.down_proj.weight": 22544384,
|
| 637 |
+
"model.layers.19.input_layernorm.weight": 2048,
|
| 638 |
+
"model.layers.19.post_attention_layernorm.weight": 2048,
|
| 639 |
+
"model.layers.20.self_attn.q_proj.weight": 4194304,
|
| 640 |
+
"model.layers.20.self_attn.q_proj.bias": 2048,
|
| 641 |
+
"model.layers.20.self_attn.k_proj.weight": 524288,
|
| 642 |
+
"model.layers.20.self_attn.k_proj.bias": 256,
|
| 643 |
+
"model.layers.20.self_attn.v_proj.weight": 524288,
|
| 644 |
+
"model.layers.20.self_attn.v_proj.bias": 256,
|
| 645 |
+
"model.layers.20.self_attn.o_proj.weight": 4194304,
|
| 646 |
+
"model.layers.20.mlp.gate_proj.weight": 22544384,
|
| 647 |
+
"model.layers.20.mlp.up_proj.weight": 22544384,
|
| 648 |
+
"model.layers.20.mlp.down_proj.weight": 22544384,
|
| 649 |
+
"model.layers.20.input_layernorm.weight": 2048,
|
| 650 |
+
"model.layers.20.post_attention_layernorm.weight": 2048,
|
| 651 |
+
"model.layers.21.self_attn.q_proj.weight": 4194304,
|
| 652 |
+
"model.layers.21.self_attn.q_proj.bias": 2048,
|
| 653 |
+
"model.layers.21.self_attn.k_proj.weight": 524288,
|
| 654 |
+
"model.layers.21.self_attn.k_proj.bias": 256,
|
| 655 |
+
"model.layers.21.self_attn.v_proj.weight": 524288,
|
| 656 |
+
"model.layers.21.self_attn.v_proj.bias": 256,
|
| 657 |
+
"model.layers.21.self_attn.o_proj.weight": 4194304,
|
| 658 |
+
"model.layers.21.mlp.gate_proj.weight": 22544384,
|
| 659 |
+
"model.layers.21.mlp.up_proj.weight": 22544384,
|
| 660 |
+
"model.layers.21.mlp.down_proj.weight": 22544384,
|
| 661 |
+
"model.layers.21.input_layernorm.weight": 2048,
|
| 662 |
+
"model.layers.21.post_attention_layernorm.weight": 2048,
|
| 663 |
+
"model.layers.22.self_attn.q_proj.weight": 4194304,
|
| 664 |
+
"model.layers.22.self_attn.q_proj.bias": 2048,
|
| 665 |
+
"model.layers.22.self_attn.k_proj.weight": 524288,
|
| 666 |
+
"model.layers.22.self_attn.k_proj.bias": 256,
|
| 667 |
+
"model.layers.22.self_attn.v_proj.weight": 524288,
|
| 668 |
+
"model.layers.22.self_attn.v_proj.bias": 256,
|
| 669 |
+
"model.layers.22.self_attn.o_proj.weight": 4194304,
|
| 670 |
+
"model.layers.22.mlp.gate_proj.weight": 22544384,
|
| 671 |
+
"model.layers.22.mlp.up_proj.weight": 22544384,
|
| 672 |
+
"model.layers.22.mlp.down_proj.weight": 22544384,
|
| 673 |
+
"model.layers.22.input_layernorm.weight": 2048,
|
| 674 |
+
"model.layers.22.post_attention_layernorm.weight": 2048,
|
| 675 |
+
"model.layers.23.self_attn.q_proj.weight": 4194304,
|
| 676 |
+
"model.layers.23.self_attn.q_proj.bias": 2048,
|
| 677 |
+
"model.layers.23.self_attn.k_proj.weight": 524288,
|
| 678 |
+
"model.layers.23.self_attn.k_proj.bias": 256,
|
| 679 |
+
"model.layers.23.self_attn.v_proj.weight": 524288,
|
| 680 |
+
"model.layers.23.self_attn.v_proj.bias": 256,
|
| 681 |
+
"model.layers.23.self_attn.o_proj.weight": 4194304,
|
| 682 |
+
"model.layers.23.mlp.gate_proj.weight": 22544384,
|
| 683 |
+
"model.layers.23.mlp.up_proj.weight": 22544384,
|
| 684 |
+
"model.layers.23.mlp.down_proj.weight": 22544384,
|
| 685 |
+
"model.layers.23.input_layernorm.weight": 2048,
|
| 686 |
+
"model.layers.23.post_attention_layernorm.weight": 2048,
|
| 687 |
+
"model.layers.24.self_attn.q_proj.weight": 4194304,
|
| 688 |
+
"model.layers.24.self_attn.q_proj.bias": 2048,
|
| 689 |
+
"model.layers.24.self_attn.k_proj.weight": 524288,
|
| 690 |
+
"model.layers.24.self_attn.k_proj.bias": 256,
|
| 691 |
+
"model.layers.24.self_attn.v_proj.weight": 524288,
|
| 692 |
+
"model.layers.24.self_attn.v_proj.bias": 256,
|
| 693 |
+
"model.layers.24.self_attn.o_proj.weight": 4194304,
|
| 694 |
+
"model.layers.24.mlp.gate_proj.weight": 22544384,
|
| 695 |
+
"model.layers.24.mlp.up_proj.weight": 22544384,
|
| 696 |
+
"model.layers.24.mlp.down_proj.weight": 22544384,
|
| 697 |
+
"model.layers.24.input_layernorm.weight": 2048,
|
| 698 |
+
"model.layers.24.post_attention_layernorm.weight": 2048,
|
| 699 |
+
"model.layers.25.self_attn.q_proj.weight": 4194304,
|
| 700 |
+
"model.layers.25.self_attn.q_proj.bias": 2048,
|
| 701 |
+
"model.layers.25.self_attn.k_proj.weight": 524288,
|
| 702 |
+
"model.layers.25.self_attn.k_proj.bias": 256,
|
| 703 |
+
"model.layers.25.self_attn.v_proj.weight": 524288,
|
| 704 |
+
"model.layers.25.self_attn.v_proj.bias": 256,
|
| 705 |
+
"model.layers.25.self_attn.o_proj.weight": 4194304,
|
| 706 |
+
"model.layers.25.mlp.gate_proj.weight": 22544384,
|
| 707 |
+
"model.layers.25.mlp.up_proj.weight": 22544384,
|
| 708 |
+
"model.layers.25.mlp.down_proj.weight": 22544384,
|
| 709 |
+
"model.layers.25.input_layernorm.weight": 2048,
|
| 710 |
+
"model.layers.25.post_attention_layernorm.weight": 2048,
|
| 711 |
+
"model.layers.26.self_attn.q_proj.weight": 4194304,
|
| 712 |
+
"model.layers.26.self_attn.q_proj.bias": 2048,
|
| 713 |
+
"model.layers.26.self_attn.k_proj.weight": 524288,
|
| 714 |
+
"model.layers.26.self_attn.k_proj.bias": 256,
|
| 715 |
+
"model.layers.26.self_attn.v_proj.weight": 524288,
|
| 716 |
+
"model.layers.26.self_attn.v_proj.bias": 256,
|
| 717 |
+
"model.layers.26.self_attn.o_proj.weight": 4194304,
|
| 718 |
+
"model.layers.26.mlp.gate_proj.weight": 22544384,
|
| 719 |
+
"model.layers.26.mlp.up_proj.weight": 22544384,
|
| 720 |
+
"model.layers.26.mlp.down_proj.weight": 22544384,
|
| 721 |
+
"model.layers.26.input_layernorm.weight": 2048,
|
| 722 |
+
"model.layers.26.post_attention_layernorm.weight": 2048,
|
| 723 |
+
"model.layers.27.self_attn.q_proj.weight": 4194304,
|
| 724 |
+
"model.layers.27.self_attn.q_proj.bias": 2048,
|
| 725 |
+
"model.layers.27.self_attn.k_proj.weight": 524288,
|
| 726 |
+
"model.layers.27.self_attn.k_proj.bias": 256,
|
| 727 |
+
"model.layers.27.self_attn.v_proj.weight": 524288,
|
| 728 |
+
"model.layers.27.self_attn.v_proj.bias": 256,
|
| 729 |
+
"model.layers.27.self_attn.o_proj.weight": 4194304,
|
| 730 |
+
"model.layers.27.mlp.gate_proj.weight": 22544384,
|
| 731 |
+
"model.layers.27.mlp.up_proj.weight": 22544384,
|
| 732 |
+
"model.layers.27.mlp.down_proj.weight": 22544384,
|
| 733 |
+
"model.layers.27.input_layernorm.weight": 2048,
|
| 734 |
+
"model.layers.27.post_attention_layernorm.weight": 2048,
|
| 735 |
+
"model.layers.28.self_attn.q_proj.weight": 4194304,
|
| 736 |
+
"model.layers.28.self_attn.q_proj.bias": 2048,
|
| 737 |
+
"model.layers.28.self_attn.k_proj.weight": 524288,
|
| 738 |
+
"model.layers.28.self_attn.k_proj.bias": 256,
|
| 739 |
+
"model.layers.28.self_attn.v_proj.weight": 524288,
|
| 740 |
+
"model.layers.28.self_attn.v_proj.bias": 256,
|
| 741 |
+
"model.layers.28.self_attn.o_proj.weight": 4194304,
|
| 742 |
+
"model.layers.28.mlp.gate_proj.weight": 22544384,
|
| 743 |
+
"model.layers.28.mlp.up_proj.weight": 22544384,
|
| 744 |
+
"model.layers.28.mlp.down_proj.weight": 22544384,
|
| 745 |
+
"model.layers.28.input_layernorm.weight": 2048,
|
| 746 |
+
"model.layers.28.post_attention_layernorm.weight": 2048,
|
| 747 |
+
"model.layers.29.self_attn.q_proj.weight": 4194304,
|
| 748 |
+
"model.layers.29.self_attn.q_proj.bias": 2048,
|
| 749 |
+
"model.layers.29.self_attn.k_proj.weight": 524288,
|
| 750 |
+
"model.layers.29.self_attn.k_proj.bias": 256,
|
| 751 |
+
"model.layers.29.self_attn.v_proj.weight": 524288,
|
| 752 |
+
"model.layers.29.self_attn.v_proj.bias": 256,
|
| 753 |
+
"model.layers.29.self_attn.o_proj.weight": 4194304,
|
| 754 |
+
"model.layers.29.mlp.gate_proj.weight": 22544384,
|
| 755 |
+
"model.layers.29.mlp.up_proj.weight": 22544384,
|
| 756 |
+
"model.layers.29.mlp.down_proj.weight": 22544384,
|
| 757 |
+
"model.layers.29.input_layernorm.weight": 2048,
|
| 758 |
+
"model.layers.29.post_attention_layernorm.weight": 2048,
|
| 759 |
+
"model.layers.30.self_attn.q_proj.weight": 4194304,
|
| 760 |
+
"model.layers.30.self_attn.q_proj.bias": 2048,
|
| 761 |
+
"model.layers.30.self_attn.k_proj.weight": 524288,
|
| 762 |
+
"model.layers.30.self_attn.k_proj.bias": 256,
|
| 763 |
+
"model.layers.30.self_attn.v_proj.weight": 524288,
|
| 764 |
+
"model.layers.30.self_attn.v_proj.bias": 256,
|
| 765 |
+
"model.layers.30.self_attn.o_proj.weight": 4194304,
|
| 766 |
+
"model.layers.30.mlp.gate_proj.weight": 22544384,
|
| 767 |
+
"model.layers.30.mlp.up_proj.weight": 22544384,
|
| 768 |
+
"model.layers.30.mlp.down_proj.weight": 22544384,
|
| 769 |
+
"model.layers.30.input_layernorm.weight": 2048,
|
| 770 |
+
"model.layers.30.post_attention_layernorm.weight": 2048,
|
| 771 |
+
"model.layers.31.self_attn.q_proj.weight": 4194304,
|
| 772 |
+
"model.layers.31.self_attn.q_proj.bias": 2048,
|
| 773 |
+
"model.layers.31.self_attn.k_proj.weight": 524288,
|
| 774 |
+
"model.layers.31.self_attn.k_proj.bias": 256,
|
| 775 |
+
"model.layers.31.self_attn.v_proj.weight": 524288,
|
| 776 |
+
"model.layers.31.self_attn.v_proj.bias": 256,
|
| 777 |
+
"model.layers.31.self_attn.o_proj.weight": 4194304,
|
| 778 |
+
"model.layers.31.mlp.gate_proj.weight": 22544384,
|
| 779 |
+
"model.layers.31.mlp.up_proj.weight": 22544384,
|
| 780 |
+
"model.layers.31.mlp.down_proj.weight": 22544384,
|
| 781 |
+
"model.layers.31.input_layernorm.weight": 2048,
|
| 782 |
+
"model.layers.31.post_attention_layernorm.weight": 2048,
|
| 783 |
+
"model.layers.32.self_attn.q_proj.weight": 4194304,
|
| 784 |
+
"model.layers.32.self_attn.q_proj.bias": 2048,
|
| 785 |
+
"model.layers.32.self_attn.k_proj.weight": 524288,
|
| 786 |
+
"model.layers.32.self_attn.k_proj.bias": 256,
|
| 787 |
+
"model.layers.32.self_attn.v_proj.weight": 524288,
|
| 788 |
+
"model.layers.32.self_attn.v_proj.bias": 256,
|
| 789 |
+
"model.layers.32.self_attn.o_proj.weight": 4194304,
|
| 790 |
+
"model.layers.32.mlp.gate_proj.weight": 22544384,
|
| 791 |
+
"model.layers.32.mlp.up_proj.weight": 22544384,
|
| 792 |
+
"model.layers.32.mlp.down_proj.weight": 22544384,
|
| 793 |
+
"model.layers.32.input_layernorm.weight": 2048,
|
| 794 |
+
"model.layers.32.post_attention_layernorm.weight": 2048,
|
| 795 |
+
"model.layers.33.self_attn.q_proj.weight": 4194304,
|
| 796 |
+
"model.layers.33.self_attn.q_proj.bias": 2048,
|
| 797 |
+
"model.layers.33.self_attn.k_proj.weight": 524288,
|
| 798 |
+
"model.layers.33.self_attn.k_proj.bias": 256,
|
| 799 |
+
"model.layers.33.self_attn.v_proj.weight": 524288,
|
| 800 |
+
"model.layers.33.self_attn.v_proj.bias": 256,
|
| 801 |
+
"model.layers.33.self_attn.o_proj.weight": 4194304,
|
| 802 |
+
"model.layers.33.mlp.gate_proj.weight": 22544384,
|
| 803 |
+
"model.layers.33.mlp.up_proj.weight": 22544384,
|
| 804 |
+
"model.layers.33.mlp.down_proj.weight": 22544384,
|
| 805 |
+
"model.layers.33.input_layernorm.weight": 2048,
|
| 806 |
+
"model.layers.33.post_attention_layernorm.weight": 2048,
|
| 807 |
+
"model.layers.34.self_attn.q_proj.weight": 4194304,
|
| 808 |
+
"model.layers.34.self_attn.q_proj.bias": 2048,
|
| 809 |
+
"model.layers.34.self_attn.k_proj.weight": 524288,
|
| 810 |
+
"model.layers.34.self_attn.k_proj.bias": 256,
|
| 811 |
+
"model.layers.34.self_attn.v_proj.weight": 524288,
|
| 812 |
+
"model.layers.34.self_attn.v_proj.bias": 256,
|
| 813 |
+
"model.layers.34.self_attn.o_proj.weight": 4194304,
|
| 814 |
+
"model.layers.34.mlp.gate_proj.weight": 22544384,
|
| 815 |
+
"model.layers.34.mlp.up_proj.weight": 22544384,
|
| 816 |
+
"model.layers.34.mlp.down_proj.weight": 22544384,
|
| 817 |
+
"model.layers.34.input_layernorm.weight": 2048,
|
| 818 |
+
"model.layers.34.post_attention_layernorm.weight": 2048,
|
| 819 |
+
"model.layers.35.self_attn.q_proj.weight": 4194304,
|
| 820 |
+
"model.layers.35.self_attn.q_proj.bias": 2048,
|
| 821 |
+
"model.layers.35.self_attn.k_proj.weight": 524288,
|
| 822 |
+
"model.layers.35.self_attn.k_proj.bias": 256,
|
| 823 |
+
"model.layers.35.self_attn.v_proj.weight": 524288,
|
| 824 |
+
"model.layers.35.self_attn.v_proj.bias": 256,
|
| 825 |
+
"model.layers.35.self_attn.o_proj.weight": 4194304,
|
| 826 |
+
"model.layers.35.mlp.gate_proj.weight": 22544384,
|
| 827 |
+
"model.layers.35.mlp.up_proj.weight": 22544384,
|
| 828 |
+
"model.layers.35.mlp.down_proj.weight": 22544384,
|
| 829 |
+
"model.layers.35.input_layernorm.weight": 2048,
|
| 830 |
+
"model.layers.35.post_attention_layernorm.weight": 2048,
|
| 831 |
+
"model.norm.weight": 2048
|
| 832 |
+
}
|
| 833 |
+
[02/15 15:32:01.046]: Model structure:
|
| 834 |
+
[02/15 15:32:01.047]: Qwen2_5_VLForConditionalGeneration(
|
| 835 |
+
(visual): Qwen2_5_VisionTransformerPretrainedModel(
|
| 836 |
+
(patch_embed): Qwen2_5_VisionPatchEmbed(
|
| 837 |
+
(proj): Conv3d(3, 1280, kernel_size=(2, 14, 14), stride=(2, 14, 14), bias=False)
|
| 838 |
+
)
|
| 839 |
+
(rotary_pos_emb): Qwen2_5_VisionRotaryEmbedding()
|
| 840 |
+
(blocks): ModuleList(
|
| 841 |
+
(0-31): 32 x Qwen2_5_VLVisionBlock(
|
| 842 |
+
(norm1): Qwen2RMSNorm((1280,), eps=1e-06)
|
| 843 |
+
(norm2): Qwen2RMSNorm((1280,), eps=1e-06)
|
| 844 |
+
(attn): Qwen2_5_VLVisionFlashAttention2(
|
| 845 |
+
(qkv): Linear(in_features=1280, out_features=3840, bias=True)
|
| 846 |
+
(proj): Linear(in_features=1280, out_features=1280, bias=True)
|
| 847 |
+
)
|
| 848 |
+
(mlp): Qwen2_5_VLMLP(
|
| 849 |
+
(gate_proj): Linear(in_features=1280, out_features=3420, bias=True)
|
| 850 |
+
(up_proj): Linear(in_features=1280, out_features=3420, bias=True)
|
| 851 |
+
(down_proj): Linear(in_features=3420, out_features=1280, bias=True)
|
| 852 |
+
(act_fn): SiLU()
|
| 853 |
+
)
|
| 854 |
+
)
|
| 855 |
+
)
|
| 856 |
+
(merger): Qwen2_5_VLPatchMerger(
|
| 857 |
+
(ln_q): Qwen2RMSNorm((1280,), eps=1e-06)
|
| 858 |
+
(mlp): Sequential(
|
| 859 |
+
(0): Linear(in_features=5120, out_features=5120, bias=True)
|
| 860 |
+
(1): GELU(approximate='none')
|
| 861 |
+
(2): Linear(in_features=5120, out_features=2048, bias=True)
|
| 862 |
+
)
|
| 863 |
+
)
|
| 864 |
+
)
|
| 865 |
+
(model): Qwen2_5_VLModel(
|
| 866 |
+
(embed_tokens): Embedding(151936, 2048, padding_idx=151643)
|
| 867 |
+
(layers): ModuleList(
|
| 868 |
+
(0-35): 36 x Qwen2_5_VLDecoderLayer(
|
| 869 |
+
(self_attn): Qwen2_5_VLFlashAttention2(
|
| 870 |
+
(q_proj): Linear(in_features=2048, out_features=2048, bias=True)
|
| 871 |
+
(k_proj): Linear(in_features=2048, out_features=256, bias=True)
|
| 872 |
+
(v_proj): Linear(in_features=2048, out_features=256, bias=True)
|
| 873 |
+
(o_proj): Linear(in_features=2048, out_features=2048, bias=False)
|
| 874 |
+
(rotary_emb): Qwen2_5_VLRotaryEmbedding()
|
| 875 |
+
)
|
| 876 |
+
(mlp): Qwen2MLP(
|
| 877 |
+
(gate_proj): Linear(in_features=2048, out_features=11008, bias=False)
|
| 878 |
+
(up_proj): Linear(in_features=2048, out_features=11008, bias=False)
|
| 879 |
+
(down_proj): Linear(in_features=11008, out_features=2048, bias=False)
|
| 880 |
+
(act_fn): SiLU()
|
| 881 |
+
)
|
| 882 |
+
(input_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
|
| 883 |
+
(post_attention_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
|
| 884 |
+
)
|
| 885 |
+
)
|
| 886 |
+
(norm): Qwen2RMSNorm((2048,), eps=1e-06)
|
| 887 |
+
(rotary_emb): Qwen2_5_VLRotaryEmbedding()
|
| 888 |
+
)
|
| 889 |
+
(lm_head): Linear(in_features=2048, out_features=151936, bias=False)
|
| 890 |
+
)
|
| 891 |
+
[02/15 15:32:01.073]: Training dataset size: 2385
|
merge_sft_o3/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
merge_sft_o3/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a0442c2b4de86186cfc5acf265a5f837d15a18c36388e08c81c1bb69cc5ab3d
|
| 3 |
+
size 4997750760
|
merge_sft_o3/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b792d26b50f844ea2d53facd8f790ba4a84e0609ef9be1c8116d53466898bae3
|
| 3 |
+
size 3133917248
|
merge_sft_o3/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8131575808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 726 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 732 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 738 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 744 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 750 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 756 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 762 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 763 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 768 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 774 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 775 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 780 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 786 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 792 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 798 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 799 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 804 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 810 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 811 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 816 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 822 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 823 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 825 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 827 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 829 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 830 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
| 831 |
+
}
|
| 832 |
+
}
|
merge_sft_o3/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 2007040,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 12544,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 2007040,
|
| 26 |
+
"shortest_edge": 12544
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
merge_sft_o3/special_tokens_map.json
ADDED
|
@@ -0,0 +1,1031 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<0>",
|
| 17 |
+
"<1>",
|
| 18 |
+
"<2>",
|
| 19 |
+
"<3>",
|
| 20 |
+
"<4>",
|
| 21 |
+
"<5>",
|
| 22 |
+
"<6>",
|
| 23 |
+
"<7>",
|
| 24 |
+
"<8>",
|
| 25 |
+
"<9>",
|
| 26 |
+
"<10>",
|
| 27 |
+
"<11>",
|
| 28 |
+
"<12>",
|
| 29 |
+
"<13>",
|
| 30 |
+
"<14>",
|
| 31 |
+
"<15>",
|
| 32 |
+
"<16>",
|
| 33 |
+
"<17>",
|
| 34 |
+
"<18>",
|
| 35 |
+
"<19>",
|
| 36 |
+
"<20>",
|
| 37 |
+
"<21>",
|
| 38 |
+
"<22>",
|
| 39 |
+
"<23>",
|
| 40 |
+
"<24>",
|
| 41 |
+
"<25>",
|
| 42 |
+
"<26>",
|
| 43 |
+
"<27>",
|
| 44 |
+
"<28>",
|
| 45 |
+
"<29>",
|
| 46 |
+
"<30>",
|
| 47 |
+
"<31>",
|
| 48 |
+
"<32>",
|
| 49 |
+
"<33>",
|
| 50 |
+
"<34>",
|
| 51 |
+
"<35>",
|
| 52 |
+
"<36>",
|
| 53 |
+
"<37>",
|
| 54 |
+
"<38>",
|
| 55 |
+
"<39>",
|
| 56 |
+
"<40>",
|
| 57 |
+
"<41>",
|
| 58 |
+
"<42>",
|
| 59 |
+
"<43>",
|
| 60 |
+
"<44>",
|
| 61 |
+
"<45>",
|
| 62 |
+
"<46>",
|
| 63 |
+
"<47>",
|
| 64 |
+
"<48>",
|
| 65 |
+
"<49>",
|
| 66 |
+
"<50>",
|
| 67 |
+
"<51>",
|
| 68 |
+
"<52>",
|
| 69 |
+
"<53>",
|
| 70 |
+
"<54>",
|
| 71 |
+
"<55>",
|
| 72 |
+
"<56>",
|
| 73 |
+
"<57>",
|
| 74 |
+
"<58>",
|
| 75 |
+
"<59>",
|
| 76 |
+
"<60>",
|
| 77 |
+
"<61>",
|
| 78 |
+
"<62>",
|
| 79 |
+
"<63>",
|
| 80 |
+
"<64>",
|
| 81 |
+
"<65>",
|
| 82 |
+
"<66>",
|
| 83 |
+
"<67>",
|
| 84 |
+
"<68>",
|
| 85 |
+
"<69>",
|
| 86 |
+
"<70>",
|
| 87 |
+
"<71>",
|
| 88 |
+
"<72>",
|
| 89 |
+
"<73>",
|
| 90 |
+
"<74>",
|
| 91 |
+
"<75>",
|
| 92 |
+
"<76>",
|
| 93 |
+
"<77>",
|
| 94 |
+
"<78>",
|
| 95 |
+
"<79>",
|
| 96 |
+
"<80>",
|
| 97 |
+
"<81>",
|
| 98 |
+
"<82>",
|
| 99 |
+
"<83>",
|
| 100 |
+
"<84>",
|
| 101 |
+
"<85>",
|
| 102 |
+
"<86>",
|
| 103 |
+
"<87>",
|
| 104 |
+
"<88>",
|
| 105 |
+
"<89>",
|
| 106 |
+
"<90>",
|
| 107 |
+
"<91>",
|
| 108 |
+
"<92>",
|
| 109 |
+
"<93>",
|
| 110 |
+
"<94>",
|
| 111 |
+
"<95>",
|
| 112 |
+
"<96>",
|
| 113 |
+
"<97>",
|
| 114 |
+
"<98>",
|
| 115 |
+
"<99>",
|
| 116 |
+
"<100>",
|
| 117 |
+
"<101>",
|
| 118 |
+
"<102>",
|
| 119 |
+
"<103>",
|
| 120 |
+
"<104>",
|
| 121 |
+
"<105>",
|
| 122 |
+
"<106>",
|
| 123 |
+
"<107>",
|
| 124 |
+
"<108>",
|
| 125 |
+
"<109>",
|
| 126 |
+
"<110>",
|
| 127 |
+
"<111>",
|
| 128 |
+
"<112>",
|
| 129 |
+
"<113>",
|
| 130 |
+
"<114>",
|
| 131 |
+
"<115>",
|
| 132 |
+
"<116>",
|
| 133 |
+
"<117>",
|
| 134 |
+
"<118>",
|
| 135 |
+
"<119>",
|
| 136 |
+
"<120>",
|
| 137 |
+
"<121>",
|
| 138 |
+
"<122>",
|
| 139 |
+
"<123>",
|
| 140 |
+
"<124>",
|
| 141 |
+
"<125>",
|
| 142 |
+
"<126>",
|
| 143 |
+
"<127>",
|
| 144 |
+
"<128>",
|
| 145 |
+
"<129>",
|
| 146 |
+
"<130>",
|
| 147 |
+
"<131>",
|
| 148 |
+
"<132>",
|
| 149 |
+
"<133>",
|
| 150 |
+
"<134>",
|
| 151 |
+
"<135>",
|
| 152 |
+
"<136>",
|
| 153 |
+
"<137>",
|
| 154 |
+
"<138>",
|
| 155 |
+
"<139>",
|
| 156 |
+
"<140>",
|
| 157 |
+
"<141>",
|
| 158 |
+
"<142>",
|
| 159 |
+
"<143>",
|
| 160 |
+
"<144>",
|
| 161 |
+
"<145>",
|
| 162 |
+
"<146>",
|
| 163 |
+
"<147>",
|
| 164 |
+
"<148>",
|
| 165 |
+
"<149>",
|
| 166 |
+
"<150>",
|
| 167 |
+
"<151>",
|
| 168 |
+
"<152>",
|
| 169 |
+
"<153>",
|
| 170 |
+
"<154>",
|
| 171 |
+
"<155>",
|
| 172 |
+
"<156>",
|
| 173 |
+
"<157>",
|
| 174 |
+
"<158>",
|
| 175 |
+
"<159>",
|
| 176 |
+
"<160>",
|
| 177 |
+
"<161>",
|
| 178 |
+
"<162>",
|
| 179 |
+
"<163>",
|
| 180 |
+
"<164>",
|
| 181 |
+
"<165>",
|
| 182 |
+
"<166>",
|
| 183 |
+
"<167>",
|
| 184 |
+
"<168>",
|
| 185 |
+
"<169>",
|
| 186 |
+
"<170>",
|
| 187 |
+
"<171>",
|
| 188 |
+
"<172>",
|
| 189 |
+
"<173>",
|
| 190 |
+
"<174>",
|
| 191 |
+
"<175>",
|
| 192 |
+
"<176>",
|
| 193 |
+
"<177>",
|
| 194 |
+
"<178>",
|
| 195 |
+
"<179>",
|
| 196 |
+
"<180>",
|
| 197 |
+
"<181>",
|
| 198 |
+
"<182>",
|
| 199 |
+
"<183>",
|
| 200 |
+
"<184>",
|
| 201 |
+
"<185>",
|
| 202 |
+
"<186>",
|
| 203 |
+
"<187>",
|
| 204 |
+
"<188>",
|
| 205 |
+
"<189>",
|
| 206 |
+
"<190>",
|
| 207 |
+
"<191>",
|
| 208 |
+
"<192>",
|
| 209 |
+
"<193>",
|
| 210 |
+
"<194>",
|
| 211 |
+
"<195>",
|
| 212 |
+
"<196>",
|
| 213 |
+
"<197>",
|
| 214 |
+
"<198>",
|
| 215 |
+
"<199>",
|
| 216 |
+
"<200>",
|
| 217 |
+
"<201>",
|
| 218 |
+
"<202>",
|
| 219 |
+
"<203>",
|
| 220 |
+
"<204>",
|
| 221 |
+
"<205>",
|
| 222 |
+
"<206>",
|
| 223 |
+
"<207>",
|
| 224 |
+
"<208>",
|
| 225 |
+
"<209>",
|
| 226 |
+
"<210>",
|
| 227 |
+
"<211>",
|
| 228 |
+
"<212>",
|
| 229 |
+
"<213>",
|
| 230 |
+
"<214>",
|
| 231 |
+
"<215>",
|
| 232 |
+
"<216>",
|
| 233 |
+
"<217>",
|
| 234 |
+
"<218>",
|
| 235 |
+
"<219>",
|
| 236 |
+
"<220>",
|
| 237 |
+
"<221>",
|
| 238 |
+
"<222>",
|
| 239 |
+
"<223>",
|
| 240 |
+
"<224>",
|
| 241 |
+
"<225>",
|
| 242 |
+
"<226>",
|
| 243 |
+
"<227>",
|
| 244 |
+
"<228>",
|
| 245 |
+
"<229>",
|
| 246 |
+
"<230>",
|
| 247 |
+
"<231>",
|
| 248 |
+
"<232>",
|
| 249 |
+
"<233>",
|
| 250 |
+
"<234>",
|
| 251 |
+
"<235>",
|
| 252 |
+
"<236>",
|
| 253 |
+
"<237>",
|
| 254 |
+
"<238>",
|
| 255 |
+
"<239>",
|
| 256 |
+
"<240>",
|
| 257 |
+
"<241>",
|
| 258 |
+
"<242>",
|
| 259 |
+
"<243>",
|
| 260 |
+
"<244>",
|
| 261 |
+
"<245>",
|
| 262 |
+
"<246>",
|
| 263 |
+
"<247>",
|
| 264 |
+
"<248>",
|
| 265 |
+
"<249>",
|
| 266 |
+
"<250>",
|
| 267 |
+
"<251>",
|
| 268 |
+
"<252>",
|
| 269 |
+
"<253>",
|
| 270 |
+
"<254>",
|
| 271 |
+
"<255>",
|
| 272 |
+
"<256>",
|
| 273 |
+
"<257>",
|
| 274 |
+
"<258>",
|
| 275 |
+
"<259>",
|
| 276 |
+
"<260>",
|
| 277 |
+
"<261>",
|
| 278 |
+
"<262>",
|
| 279 |
+
"<263>",
|
| 280 |
+
"<264>",
|
| 281 |
+
"<265>",
|
| 282 |
+
"<266>",
|
| 283 |
+
"<267>",
|
| 284 |
+
"<268>",
|
| 285 |
+
"<269>",
|
| 286 |
+
"<270>",
|
| 287 |
+
"<271>",
|
| 288 |
+
"<272>",
|
| 289 |
+
"<273>",
|
| 290 |
+
"<274>",
|
| 291 |
+
"<275>",
|
| 292 |
+
"<276>",
|
| 293 |
+
"<277>",
|
| 294 |
+
"<278>",
|
| 295 |
+
"<279>",
|
| 296 |
+
"<280>",
|
| 297 |
+
"<281>",
|
| 298 |
+
"<282>",
|
| 299 |
+
"<283>",
|
| 300 |
+
"<284>",
|
| 301 |
+
"<285>",
|
| 302 |
+
"<286>",
|
| 303 |
+
"<287>",
|
| 304 |
+
"<288>",
|
| 305 |
+
"<289>",
|
| 306 |
+
"<290>",
|
| 307 |
+
"<291>",
|
| 308 |
+
"<292>",
|
| 309 |
+
"<293>",
|
| 310 |
+
"<294>",
|
| 311 |
+
"<295>",
|
| 312 |
+
"<296>",
|
| 313 |
+
"<297>",
|
| 314 |
+
"<298>",
|
| 315 |
+
"<299>",
|
| 316 |
+
"<300>",
|
| 317 |
+
"<301>",
|
| 318 |
+
"<302>",
|
| 319 |
+
"<303>",
|
| 320 |
+
"<304>",
|
| 321 |
+
"<305>",
|
| 322 |
+
"<306>",
|
| 323 |
+
"<307>",
|
| 324 |
+
"<308>",
|
| 325 |
+
"<309>",
|
| 326 |
+
"<310>",
|
| 327 |
+
"<311>",
|
| 328 |
+
"<312>",
|
| 329 |
+
"<313>",
|
| 330 |
+
"<314>",
|
| 331 |
+
"<315>",
|
| 332 |
+
"<316>",
|
| 333 |
+
"<317>",
|
| 334 |
+
"<318>",
|
| 335 |
+
"<319>",
|
| 336 |
+
"<320>",
|
| 337 |
+
"<321>",
|
| 338 |
+
"<322>",
|
| 339 |
+
"<323>",
|
| 340 |
+
"<324>",
|
| 341 |
+
"<325>",
|
| 342 |
+
"<326>",
|
| 343 |
+
"<327>",
|
| 344 |
+
"<328>",
|
| 345 |
+
"<329>",
|
| 346 |
+
"<330>",
|
| 347 |
+
"<331>",
|
| 348 |
+
"<332>",
|
| 349 |
+
"<333>",
|
| 350 |
+
"<334>",
|
| 351 |
+
"<335>",
|
| 352 |
+
"<336>",
|
| 353 |
+
"<337>",
|
| 354 |
+
"<338>",
|
| 355 |
+
"<339>",
|
| 356 |
+
"<340>",
|
| 357 |
+
"<341>",
|
| 358 |
+
"<342>",
|
| 359 |
+
"<343>",
|
| 360 |
+
"<344>",
|
| 361 |
+
"<345>",
|
| 362 |
+
"<346>",
|
| 363 |
+
"<347>",
|
| 364 |
+
"<348>",
|
| 365 |
+
"<349>",
|
| 366 |
+
"<350>",
|
| 367 |
+
"<351>",
|
| 368 |
+
"<352>",
|
| 369 |
+
"<353>",
|
| 370 |
+
"<354>",
|
| 371 |
+
"<355>",
|
| 372 |
+
"<356>",
|
| 373 |
+
"<357>",
|
| 374 |
+
"<358>",
|
| 375 |
+
"<359>",
|
| 376 |
+
"<360>",
|
| 377 |
+
"<361>",
|
| 378 |
+
"<362>",
|
| 379 |
+
"<363>",
|
| 380 |
+
"<364>",
|
| 381 |
+
"<365>",
|
| 382 |
+
"<366>",
|
| 383 |
+
"<367>",
|
| 384 |
+
"<368>",
|
| 385 |
+
"<369>",
|
| 386 |
+
"<370>",
|
| 387 |
+
"<371>",
|
| 388 |
+
"<372>",
|
| 389 |
+
"<373>",
|
| 390 |
+
"<374>",
|
| 391 |
+
"<375>",
|
| 392 |
+
"<376>",
|
| 393 |
+
"<377>",
|
| 394 |
+
"<378>",
|
| 395 |
+
"<379>",
|
| 396 |
+
"<380>",
|
| 397 |
+
"<381>",
|
| 398 |
+
"<382>",
|
| 399 |
+
"<383>",
|
| 400 |
+
"<384>",
|
| 401 |
+
"<385>",
|
| 402 |
+
"<386>",
|
| 403 |
+
"<387>",
|
| 404 |
+
"<388>",
|
| 405 |
+
"<389>",
|
| 406 |
+
"<390>",
|
| 407 |
+
"<391>",
|
| 408 |
+
"<392>",
|
| 409 |
+
"<393>",
|
| 410 |
+
"<394>",
|
| 411 |
+
"<395>",
|
| 412 |
+
"<396>",
|
| 413 |
+
"<397>",
|
| 414 |
+
"<398>",
|
| 415 |
+
"<399>",
|
| 416 |
+
"<400>",
|
| 417 |
+
"<401>",
|
| 418 |
+
"<402>",
|
| 419 |
+
"<403>",
|
| 420 |
+
"<404>",
|
| 421 |
+
"<405>",
|
| 422 |
+
"<406>",
|
| 423 |
+
"<407>",
|
| 424 |
+
"<408>",
|
| 425 |
+
"<409>",
|
| 426 |
+
"<410>",
|
| 427 |
+
"<411>",
|
| 428 |
+
"<412>",
|
| 429 |
+
"<413>",
|
| 430 |
+
"<414>",
|
| 431 |
+
"<415>",
|
| 432 |
+
"<416>",
|
| 433 |
+
"<417>",
|
| 434 |
+
"<418>",
|
| 435 |
+
"<419>",
|
| 436 |
+
"<420>",
|
| 437 |
+
"<421>",
|
| 438 |
+
"<422>",
|
| 439 |
+
"<423>",
|
| 440 |
+
"<424>",
|
| 441 |
+
"<425>",
|
| 442 |
+
"<426>",
|
| 443 |
+
"<427>",
|
| 444 |
+
"<428>",
|
| 445 |
+
"<429>",
|
| 446 |
+
"<430>",
|
| 447 |
+
"<431>",
|
| 448 |
+
"<432>",
|
| 449 |
+
"<433>",
|
| 450 |
+
"<434>",
|
| 451 |
+
"<435>",
|
| 452 |
+
"<436>",
|
| 453 |
+
"<437>",
|
| 454 |
+
"<438>",
|
| 455 |
+
"<439>",
|
| 456 |
+
"<440>",
|
| 457 |
+
"<441>",
|
| 458 |
+
"<442>",
|
| 459 |
+
"<443>",
|
| 460 |
+
"<444>",
|
| 461 |
+
"<445>",
|
| 462 |
+
"<446>",
|
| 463 |
+
"<447>",
|
| 464 |
+
"<448>",
|
| 465 |
+
"<449>",
|
| 466 |
+
"<450>",
|
| 467 |
+
"<451>",
|
| 468 |
+
"<452>",
|
| 469 |
+
"<453>",
|
| 470 |
+
"<454>",
|
| 471 |
+
"<455>",
|
| 472 |
+
"<456>",
|
| 473 |
+
"<457>",
|
| 474 |
+
"<458>",
|
| 475 |
+
"<459>",
|
| 476 |
+
"<460>",
|
| 477 |
+
"<461>",
|
| 478 |
+
"<462>",
|
| 479 |
+
"<463>",
|
| 480 |
+
"<464>",
|
| 481 |
+
"<465>",
|
| 482 |
+
"<466>",
|
| 483 |
+
"<467>",
|
| 484 |
+
"<468>",
|
| 485 |
+
"<469>",
|
| 486 |
+
"<470>",
|
| 487 |
+
"<471>",
|
| 488 |
+
"<472>",
|
| 489 |
+
"<473>",
|
| 490 |
+
"<474>",
|
| 491 |
+
"<475>",
|
| 492 |
+
"<476>",
|
| 493 |
+
"<477>",
|
| 494 |
+
"<478>",
|
| 495 |
+
"<479>",
|
| 496 |
+
"<480>",
|
| 497 |
+
"<481>",
|
| 498 |
+
"<482>",
|
| 499 |
+
"<483>",
|
| 500 |
+
"<484>",
|
| 501 |
+
"<485>",
|
| 502 |
+
"<486>",
|
| 503 |
+
"<487>",
|
| 504 |
+
"<488>",
|
| 505 |
+
"<489>",
|
| 506 |
+
"<490>",
|
| 507 |
+
"<491>",
|
| 508 |
+
"<492>",
|
| 509 |
+
"<493>",
|
| 510 |
+
"<494>",
|
| 511 |
+
"<495>",
|
| 512 |
+
"<496>",
|
| 513 |
+
"<497>",
|
| 514 |
+
"<498>",
|
| 515 |
+
"<499>",
|
| 516 |
+
"<500>",
|
| 517 |
+
"<501>",
|
| 518 |
+
"<502>",
|
| 519 |
+
"<503>",
|
| 520 |
+
"<504>",
|
| 521 |
+
"<505>",
|
| 522 |
+
"<506>",
|
| 523 |
+
"<507>",
|
| 524 |
+
"<508>",
|
| 525 |
+
"<509>",
|
| 526 |
+
"<510>",
|
| 527 |
+
"<511>",
|
| 528 |
+
"<512>",
|
| 529 |
+
"<513>",
|
| 530 |
+
"<514>",
|
| 531 |
+
"<515>",
|
| 532 |
+
"<516>",
|
| 533 |
+
"<517>",
|
| 534 |
+
"<518>",
|
| 535 |
+
"<519>",
|
| 536 |
+
"<520>",
|
| 537 |
+
"<521>",
|
| 538 |
+
"<522>",
|
| 539 |
+
"<523>",
|
| 540 |
+
"<524>",
|
| 541 |
+
"<525>",
|
| 542 |
+
"<526>",
|
| 543 |
+
"<527>",
|
| 544 |
+
"<528>",
|
| 545 |
+
"<529>",
|
| 546 |
+
"<530>",
|
| 547 |
+
"<531>",
|
| 548 |
+
"<532>",
|
| 549 |
+
"<533>",
|
| 550 |
+
"<534>",
|
| 551 |
+
"<535>",
|
| 552 |
+
"<536>",
|
| 553 |
+
"<537>",
|
| 554 |
+
"<538>",
|
| 555 |
+
"<539>",
|
| 556 |
+
"<540>",
|
| 557 |
+
"<541>",
|
| 558 |
+
"<542>",
|
| 559 |
+
"<543>",
|
| 560 |
+
"<544>",
|
| 561 |
+
"<545>",
|
| 562 |
+
"<546>",
|
| 563 |
+
"<547>",
|
| 564 |
+
"<548>",
|
| 565 |
+
"<549>",
|
| 566 |
+
"<550>",
|
| 567 |
+
"<551>",
|
| 568 |
+
"<552>",
|
| 569 |
+
"<553>",
|
| 570 |
+
"<554>",
|
| 571 |
+
"<555>",
|
| 572 |
+
"<556>",
|
| 573 |
+
"<557>",
|
| 574 |
+
"<558>",
|
| 575 |
+
"<559>",
|
| 576 |
+
"<560>",
|
| 577 |
+
"<561>",
|
| 578 |
+
"<562>",
|
| 579 |
+
"<563>",
|
| 580 |
+
"<564>",
|
| 581 |
+
"<565>",
|
| 582 |
+
"<566>",
|
| 583 |
+
"<567>",
|
| 584 |
+
"<568>",
|
| 585 |
+
"<569>",
|
| 586 |
+
"<570>",
|
| 587 |
+
"<571>",
|
| 588 |
+
"<572>",
|
| 589 |
+
"<573>",
|
| 590 |
+
"<574>",
|
| 591 |
+
"<575>",
|
| 592 |
+
"<576>",
|
| 593 |
+
"<577>",
|
| 594 |
+
"<578>",
|
| 595 |
+
"<579>",
|
| 596 |
+
"<580>",
|
| 597 |
+
"<581>",
|
| 598 |
+
"<582>",
|
| 599 |
+
"<583>",
|
| 600 |
+
"<584>",
|
| 601 |
+
"<585>",
|
| 602 |
+
"<586>",
|
| 603 |
+
"<587>",
|
| 604 |
+
"<588>",
|
| 605 |
+
"<589>",
|
| 606 |
+
"<590>",
|
| 607 |
+
"<591>",
|
| 608 |
+
"<592>",
|
| 609 |
+
"<593>",
|
| 610 |
+
"<594>",
|
| 611 |
+
"<595>",
|
| 612 |
+
"<596>",
|
| 613 |
+
"<597>",
|
| 614 |
+
"<598>",
|
| 615 |
+
"<599>",
|
| 616 |
+
"<600>",
|
| 617 |
+
"<601>",
|
| 618 |
+
"<602>",
|
| 619 |
+
"<603>",
|
| 620 |
+
"<604>",
|
| 621 |
+
"<605>",
|
| 622 |
+
"<606>",
|
| 623 |
+
"<607>",
|
| 624 |
+
"<608>",
|
| 625 |
+
"<609>",
|
| 626 |
+
"<610>",
|
| 627 |
+
"<611>",
|
| 628 |
+
"<612>",
|
| 629 |
+
"<613>",
|
| 630 |
+
"<614>",
|
| 631 |
+
"<615>",
|
| 632 |
+
"<616>",
|
| 633 |
+
"<617>",
|
| 634 |
+
"<618>",
|
| 635 |
+
"<619>",
|
| 636 |
+
"<620>",
|
| 637 |
+
"<621>",
|
| 638 |
+
"<622>",
|
| 639 |
+
"<623>",
|
| 640 |
+
"<624>",
|
| 641 |
+
"<625>",
|
| 642 |
+
"<626>",
|
| 643 |
+
"<627>",
|
| 644 |
+
"<628>",
|
| 645 |
+
"<629>",
|
| 646 |
+
"<630>",
|
| 647 |
+
"<631>",
|
| 648 |
+
"<632>",
|
| 649 |
+
"<633>",
|
| 650 |
+
"<634>",
|
| 651 |
+
"<635>",
|
| 652 |
+
"<636>",
|
| 653 |
+
"<637>",
|
| 654 |
+
"<638>",
|
| 655 |
+
"<639>",
|
| 656 |
+
"<640>",
|
| 657 |
+
"<641>",
|
| 658 |
+
"<642>",
|
| 659 |
+
"<643>",
|
| 660 |
+
"<644>",
|
| 661 |
+
"<645>",
|
| 662 |
+
"<646>",
|
| 663 |
+
"<647>",
|
| 664 |
+
"<648>",
|
| 665 |
+
"<649>",
|
| 666 |
+
"<650>",
|
| 667 |
+
"<651>",
|
| 668 |
+
"<652>",
|
| 669 |
+
"<653>",
|
| 670 |
+
"<654>",
|
| 671 |
+
"<655>",
|
| 672 |
+
"<656>",
|
| 673 |
+
"<657>",
|
| 674 |
+
"<658>",
|
| 675 |
+
"<659>",
|
| 676 |
+
"<660>",
|
| 677 |
+
"<661>",
|
| 678 |
+
"<662>",
|
| 679 |
+
"<663>",
|
| 680 |
+
"<664>",
|
| 681 |
+
"<665>",
|
| 682 |
+
"<666>",
|
| 683 |
+
"<667>",
|
| 684 |
+
"<668>",
|
| 685 |
+
"<669>",
|
| 686 |
+
"<670>",
|
| 687 |
+
"<671>",
|
| 688 |
+
"<672>",
|
| 689 |
+
"<673>",
|
| 690 |
+
"<674>",
|
| 691 |
+
"<675>",
|
| 692 |
+
"<676>",
|
| 693 |
+
"<677>",
|
| 694 |
+
"<678>",
|
| 695 |
+
"<679>",
|
| 696 |
+
"<680>",
|
| 697 |
+
"<681>",
|
| 698 |
+
"<682>",
|
| 699 |
+
"<683>",
|
| 700 |
+
"<684>",
|
| 701 |
+
"<685>",
|
| 702 |
+
"<686>",
|
| 703 |
+
"<687>",
|
| 704 |
+
"<688>",
|
| 705 |
+
"<689>",
|
| 706 |
+
"<690>",
|
| 707 |
+
"<691>",
|
| 708 |
+
"<692>",
|
| 709 |
+
"<693>",
|
| 710 |
+
"<694>",
|
| 711 |
+
"<695>",
|
| 712 |
+
"<696>",
|
| 713 |
+
"<697>",
|
| 714 |
+
"<698>",
|
| 715 |
+
"<699>",
|
| 716 |
+
"<700>",
|
| 717 |
+
"<701>",
|
| 718 |
+
"<702>",
|
| 719 |
+
"<703>",
|
| 720 |
+
"<704>",
|
| 721 |
+
"<705>",
|
| 722 |
+
"<706>",
|
| 723 |
+
"<707>",
|
| 724 |
+
"<708>",
|
| 725 |
+
"<709>",
|
| 726 |
+
"<710>",
|
| 727 |
+
"<711>",
|
| 728 |
+
"<712>",
|
| 729 |
+
"<713>",
|
| 730 |
+
"<714>",
|
| 731 |
+
"<715>",
|
| 732 |
+
"<716>",
|
| 733 |
+
"<717>",
|
| 734 |
+
"<718>",
|
| 735 |
+
"<719>",
|
| 736 |
+
"<720>",
|
| 737 |
+
"<721>",
|
| 738 |
+
"<722>",
|
| 739 |
+
"<723>",
|
| 740 |
+
"<724>",
|
| 741 |
+
"<725>",
|
| 742 |
+
"<726>",
|
| 743 |
+
"<727>",
|
| 744 |
+
"<728>",
|
| 745 |
+
"<729>",
|
| 746 |
+
"<730>",
|
| 747 |
+
"<731>",
|
| 748 |
+
"<732>",
|
| 749 |
+
"<733>",
|
| 750 |
+
"<734>",
|
| 751 |
+
"<735>",
|
| 752 |
+
"<736>",
|
| 753 |
+
"<737>",
|
| 754 |
+
"<738>",
|
| 755 |
+
"<739>",
|
| 756 |
+
"<740>",
|
| 757 |
+
"<741>",
|
| 758 |
+
"<742>",
|
| 759 |
+
"<743>",
|
| 760 |
+
"<744>",
|
| 761 |
+
"<745>",
|
| 762 |
+
"<746>",
|
| 763 |
+
"<747>",
|
| 764 |
+
"<748>",
|
| 765 |
+
"<749>",
|
| 766 |
+
"<750>",
|
| 767 |
+
"<751>",
|
| 768 |
+
"<752>",
|
| 769 |
+
"<753>",
|
| 770 |
+
"<754>",
|
| 771 |
+
"<755>",
|
| 772 |
+
"<756>",
|
| 773 |
+
"<757>",
|
| 774 |
+
"<758>",
|
| 775 |
+
"<759>",
|
| 776 |
+
"<760>",
|
| 777 |
+
"<761>",
|
| 778 |
+
"<762>",
|
| 779 |
+
"<763>",
|
| 780 |
+
"<764>",
|
| 781 |
+
"<765>",
|
| 782 |
+
"<766>",
|
| 783 |
+
"<767>",
|
| 784 |
+
"<768>",
|
| 785 |
+
"<769>",
|
| 786 |
+
"<770>",
|
| 787 |
+
"<771>",
|
| 788 |
+
"<772>",
|
| 789 |
+
"<773>",
|
| 790 |
+
"<774>",
|
| 791 |
+
"<775>",
|
| 792 |
+
"<776>",
|
| 793 |
+
"<777>",
|
| 794 |
+
"<778>",
|
| 795 |
+
"<779>",
|
| 796 |
+
"<780>",
|
| 797 |
+
"<781>",
|
| 798 |
+
"<782>",
|
| 799 |
+
"<783>",
|
| 800 |
+
"<784>",
|
| 801 |
+
"<785>",
|
| 802 |
+
"<786>",
|
| 803 |
+
"<787>",
|
| 804 |
+
"<788>",
|
| 805 |
+
"<789>",
|
| 806 |
+
"<790>",
|
| 807 |
+
"<791>",
|
| 808 |
+
"<792>",
|
| 809 |
+
"<793>",
|
| 810 |
+
"<794>",
|
| 811 |
+
"<795>",
|
| 812 |
+
"<796>",
|
| 813 |
+
"<797>",
|
| 814 |
+
"<798>",
|
| 815 |
+
"<799>",
|
| 816 |
+
"<800>",
|
| 817 |
+
"<801>",
|
| 818 |
+
"<802>",
|
| 819 |
+
"<803>",
|
| 820 |
+
"<804>",
|
| 821 |
+
"<805>",
|
| 822 |
+
"<806>",
|
| 823 |
+
"<807>",
|
| 824 |
+
"<808>",
|
| 825 |
+
"<809>",
|
| 826 |
+
"<810>",
|
| 827 |
+
"<811>",
|
| 828 |
+
"<812>",
|
| 829 |
+
"<813>",
|
| 830 |
+
"<814>",
|
| 831 |
+
"<815>",
|
| 832 |
+
"<816>",
|
| 833 |
+
"<817>",
|
| 834 |
+
"<818>",
|
| 835 |
+
"<819>",
|
| 836 |
+
"<820>",
|
| 837 |
+
"<821>",
|
| 838 |
+
"<822>",
|
| 839 |
+
"<823>",
|
| 840 |
+
"<824>",
|
| 841 |
+
"<825>",
|
| 842 |
+
"<826>",
|
| 843 |
+
"<827>",
|
| 844 |
+
"<828>",
|
| 845 |
+
"<829>",
|
| 846 |
+
"<830>",
|
| 847 |
+
"<831>",
|
| 848 |
+
"<832>",
|
| 849 |
+
"<833>",
|
| 850 |
+
"<834>",
|
| 851 |
+
"<835>",
|
| 852 |
+
"<836>",
|
| 853 |
+
"<837>",
|
| 854 |
+
"<838>",
|
| 855 |
+
"<839>",
|
| 856 |
+
"<840>",
|
| 857 |
+
"<841>",
|
| 858 |
+
"<842>",
|
| 859 |
+
"<843>",
|
| 860 |
+
"<844>",
|
| 861 |
+
"<845>",
|
| 862 |
+
"<846>",
|
| 863 |
+
"<847>",
|
| 864 |
+
"<848>",
|
| 865 |
+
"<849>",
|
| 866 |
+
"<850>",
|
| 867 |
+
"<851>",
|
| 868 |
+
"<852>",
|
| 869 |
+
"<853>",
|
| 870 |
+
"<854>",
|
| 871 |
+
"<855>",
|
| 872 |
+
"<856>",
|
| 873 |
+
"<857>",
|
| 874 |
+
"<858>",
|
| 875 |
+
"<859>",
|
| 876 |
+
"<860>",
|
| 877 |
+
"<861>",
|
| 878 |
+
"<862>",
|
| 879 |
+
"<863>",
|
| 880 |
+
"<864>",
|
| 881 |
+
"<865>",
|
| 882 |
+
"<866>",
|
| 883 |
+
"<867>",
|
| 884 |
+
"<868>",
|
| 885 |
+
"<869>",
|
| 886 |
+
"<870>",
|
| 887 |
+
"<871>",
|
| 888 |
+
"<872>",
|
| 889 |
+
"<873>",
|
| 890 |
+
"<874>",
|
| 891 |
+
"<875>",
|
| 892 |
+
"<876>",
|
| 893 |
+
"<877>",
|
| 894 |
+
"<878>",
|
| 895 |
+
"<879>",
|
| 896 |
+
"<880>",
|
| 897 |
+
"<881>",
|
| 898 |
+
"<882>",
|
| 899 |
+
"<883>",
|
| 900 |
+
"<884>",
|
| 901 |
+
"<885>",
|
| 902 |
+
"<886>",
|
| 903 |
+
"<887>",
|
| 904 |
+
"<888>",
|
| 905 |
+
"<889>",
|
| 906 |
+
"<890>",
|
| 907 |
+
"<891>",
|
| 908 |
+
"<892>",
|
| 909 |
+
"<893>",
|
| 910 |
+
"<894>",
|
| 911 |
+
"<895>",
|
| 912 |
+
"<896>",
|
| 913 |
+
"<897>",
|
| 914 |
+
"<898>",
|
| 915 |
+
"<899>",
|
| 916 |
+
"<900>",
|
| 917 |
+
"<901>",
|
| 918 |
+
"<902>",
|
| 919 |
+
"<903>",
|
| 920 |
+
"<904>",
|
| 921 |
+
"<905>",
|
| 922 |
+
"<906>",
|
| 923 |
+
"<907>",
|
| 924 |
+
"<908>",
|
| 925 |
+
"<909>",
|
| 926 |
+
"<910>",
|
| 927 |
+
"<911>",
|
| 928 |
+
"<912>",
|
| 929 |
+
"<913>",
|
| 930 |
+
"<914>",
|
| 931 |
+
"<915>",
|
| 932 |
+
"<916>",
|
| 933 |
+
"<917>",
|
| 934 |
+
"<918>",
|
| 935 |
+
"<919>",
|
| 936 |
+
"<920>",
|
| 937 |
+
"<921>",
|
| 938 |
+
"<922>",
|
| 939 |
+
"<923>",
|
| 940 |
+
"<924>",
|
| 941 |
+
"<925>",
|
| 942 |
+
"<926>",
|
| 943 |
+
"<927>",
|
| 944 |
+
"<928>",
|
| 945 |
+
"<929>",
|
| 946 |
+
"<930>",
|
| 947 |
+
"<931>",
|
| 948 |
+
"<932>",
|
| 949 |
+
"<933>",
|
| 950 |
+
"<934>",
|
| 951 |
+
"<935>",
|
| 952 |
+
"<936>",
|
| 953 |
+
"<937>",
|
| 954 |
+
"<938>",
|
| 955 |
+
"<939>",
|
| 956 |
+
"<940>",
|
| 957 |
+
"<941>",
|
| 958 |
+
"<942>",
|
| 959 |
+
"<943>",
|
| 960 |
+
"<944>",
|
| 961 |
+
"<945>",
|
| 962 |
+
"<946>",
|
| 963 |
+
"<947>",
|
| 964 |
+
"<948>",
|
| 965 |
+
"<949>",
|
| 966 |
+
"<950>",
|
| 967 |
+
"<951>",
|
| 968 |
+
"<952>",
|
| 969 |
+
"<953>",
|
| 970 |
+
"<954>",
|
| 971 |
+
"<955>",
|
| 972 |
+
"<956>",
|
| 973 |
+
"<957>",
|
| 974 |
+
"<958>",
|
| 975 |
+
"<959>",
|
| 976 |
+
"<960>",
|
| 977 |
+
"<961>",
|
| 978 |
+
"<962>",
|
| 979 |
+
"<963>",
|
| 980 |
+
"<964>",
|
| 981 |
+
"<965>",
|
| 982 |
+
"<966>",
|
| 983 |
+
"<967>",
|
| 984 |
+
"<968>",
|
| 985 |
+
"<969>",
|
| 986 |
+
"<970>",
|
| 987 |
+
"<971>",
|
| 988 |
+
"<972>",
|
| 989 |
+
"<973>",
|
| 990 |
+
"<974>",
|
| 991 |
+
"<975>",
|
| 992 |
+
"<976>",
|
| 993 |
+
"<977>",
|
| 994 |
+
"<978>",
|
| 995 |
+
"<979>",
|
| 996 |
+
"<980>",
|
| 997 |
+
"<981>",
|
| 998 |
+
"<982>",
|
| 999 |
+
"<983>",
|
| 1000 |
+
"<984>",
|
| 1001 |
+
"<985>",
|
| 1002 |
+
"<986>",
|
| 1003 |
+
"<987>",
|
| 1004 |
+
"<988>",
|
| 1005 |
+
"<989>",
|
| 1006 |
+
"<990>",
|
| 1007 |
+
"<991>",
|
| 1008 |
+
"<992>",
|
| 1009 |
+
"<993>",
|
| 1010 |
+
"<994>",
|
| 1011 |
+
"<995>",
|
| 1012 |
+
"<996>",
|
| 1013 |
+
"<997>",
|
| 1014 |
+
"<998>",
|
| 1015 |
+
"<999>"
|
| 1016 |
+
],
|
| 1017 |
+
"eos_token": {
|
| 1018 |
+
"content": "<|im_end|>",
|
| 1019 |
+
"lstrip": false,
|
| 1020 |
+
"normalized": false,
|
| 1021 |
+
"rstrip": false,
|
| 1022 |
+
"single_word": false
|
| 1023 |
+
},
|
| 1024 |
+
"pad_token": {
|
| 1025 |
+
"content": "<|endoftext|>",
|
| 1026 |
+
"lstrip": false,
|
| 1027 |
+
"normalized": false,
|
| 1028 |
+
"rstrip": false,
|
| 1029 |
+
"single_word": false
|
| 1030 |
+
}
|
| 1031 |
+
}
|
merge_sft_o3/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
merge_sft_o3/trainer_state.json
ADDED
|
@@ -0,0 +1,2136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5008375209380235,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 299,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0016750418760469012,
|
| 14 |
+
"grad_norm": 184.61497497558594,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 6.3458,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0033500837520938024,
|
| 21 |
+
"grad_norm": 152.375732421875,
|
| 22 |
+
"learning_rate": 1.111111111111111e-06,
|
| 23 |
+
"loss": 5.4643,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.005025125628140704,
|
| 28 |
+
"grad_norm": 356.3520202636719,
|
| 29 |
+
"learning_rate": 2.222222222222222e-06,
|
| 30 |
+
"loss": 6.1129,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.006700167504187605,
|
| 35 |
+
"grad_norm": 613.0651245117188,
|
| 36 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 37 |
+
"loss": 4.4944,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.008375209380234505,
|
| 42 |
+
"grad_norm": 132.7268829345703,
|
| 43 |
+
"learning_rate": 4.444444444444444e-06,
|
| 44 |
+
"loss": 5.6694,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.010050251256281407,
|
| 49 |
+
"grad_norm": 258.3136901855469,
|
| 50 |
+
"learning_rate": 5.555555555555557e-06,
|
| 51 |
+
"loss": 4.4102,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.011725293132328308,
|
| 56 |
+
"grad_norm": 144.93475341796875,
|
| 57 |
+
"learning_rate": 6.666666666666667e-06,
|
| 58 |
+
"loss": 3.7698,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.01340033500837521,
|
| 63 |
+
"grad_norm": 243.77890014648438,
|
| 64 |
+
"learning_rate": 7.77777777777778e-06,
|
| 65 |
+
"loss": 3.2521,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.01507537688442211,
|
| 70 |
+
"grad_norm": 59.826744079589844,
|
| 71 |
+
"learning_rate": 8.888888888888888e-06,
|
| 72 |
+
"loss": 2.7316,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01675041876046901,
|
| 77 |
+
"grad_norm": 29.094650268554688,
|
| 78 |
+
"learning_rate": 1e-05,
|
| 79 |
+
"loss": 2.62,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.018425460636515914,
|
| 84 |
+
"grad_norm": 41.548927307128906,
|
| 85 |
+
"learning_rate": 9.999706613915567e-06,
|
| 86 |
+
"loss": 2.4787,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.020100502512562814,
|
| 91 |
+
"grad_norm": 32.94384765625,
|
| 92 |
+
"learning_rate": 9.99882649009242e-06,
|
| 93 |
+
"loss": 2.302,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.021775544388609715,
|
| 98 |
+
"grad_norm": 16.03069305419922,
|
| 99 |
+
"learning_rate": 9.997359731816998e-06,
|
| 100 |
+
"loss": 1.7278,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.023450586264656615,
|
| 105 |
+
"grad_norm": 37.94606399536133,
|
| 106 |
+
"learning_rate": 9.995306511219885e-06,
|
| 107 |
+
"loss": 1.5484,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.02512562814070352,
|
| 112 |
+
"grad_norm": 21.531919479370117,
|
| 113 |
+
"learning_rate": 9.99266706925562e-06,
|
| 114 |
+
"loss": 1.3825,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.02680067001675042,
|
| 119 |
+
"grad_norm": 24.522897720336914,
|
| 120 |
+
"learning_rate": 9.989441715674422e-06,
|
| 121 |
+
"loss": 1.2853,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.02847571189279732,
|
| 126 |
+
"grad_norm": 15.005258560180664,
|
| 127 |
+
"learning_rate": 9.985630828985835e-06,
|
| 128 |
+
"loss": 1.2812,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03015075376884422,
|
| 133 |
+
"grad_norm": 10.962531089782715,
|
| 134 |
+
"learning_rate": 9.981234856414306e-06,
|
| 135 |
+
"loss": 1.1479,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.031825795644891124,
|
| 140 |
+
"grad_norm": 19.95958709716797,
|
| 141 |
+
"learning_rate": 9.97625431384671e-06,
|
| 142 |
+
"loss": 1.3123,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.03350083752093802,
|
| 147 |
+
"grad_norm": 15.907459259033203,
|
| 148 |
+
"learning_rate": 9.970689785771798e-06,
|
| 149 |
+
"loss": 1.1219,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.035175879396984924,
|
| 154 |
+
"grad_norm": 12.068412780761719,
|
| 155 |
+
"learning_rate": 9.964541925211613e-06,
|
| 156 |
+
"loss": 1.2989,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.03685092127303183,
|
| 161 |
+
"grad_norm": 13.935729026794434,
|
| 162 |
+
"learning_rate": 9.957811453644848e-06,
|
| 163 |
+
"loss": 1.0826,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.038525963149078725,
|
| 168 |
+
"grad_norm": 20.98143768310547,
|
| 169 |
+
"learning_rate": 9.950499160922184e-06,
|
| 170 |
+
"loss": 0.8362,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04020100502512563,
|
| 175 |
+
"grad_norm": 15.402368545532227,
|
| 176 |
+
"learning_rate": 9.942605905173593e-06,
|
| 177 |
+
"loss": 0.9655,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.04187604690117253,
|
| 182 |
+
"grad_norm": 16.108549118041992,
|
| 183 |
+
"learning_rate": 9.934132612707631e-06,
|
| 184 |
+
"loss": 0.7919,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.04355108877721943,
|
| 189 |
+
"grad_norm": 8.706860542297363,
|
| 190 |
+
"learning_rate": 9.925080277902743e-06,
|
| 191 |
+
"loss": 0.8685,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.04522613065326633,
|
| 196 |
+
"grad_norm": 6.408807277679443,
|
| 197 |
+
"learning_rate": 9.915449963090551e-06,
|
| 198 |
+
"loss": 0.9193,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.04690117252931323,
|
| 203 |
+
"grad_norm": 22.336645126342773,
|
| 204 |
+
"learning_rate": 9.905242798431196e-06,
|
| 205 |
+
"loss": 0.808,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.048576214405360134,
|
| 210 |
+
"grad_norm": 13.571297645568848,
|
| 211 |
+
"learning_rate": 9.894459981780711e-06,
|
| 212 |
+
"loss": 0.8239,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.05025125628140704,
|
| 217 |
+
"grad_norm": 13.84472370147705,
|
| 218 |
+
"learning_rate": 9.883102778550434e-06,
|
| 219 |
+
"loss": 0.8468,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.051926298157453935,
|
| 224 |
+
"grad_norm": 12.625249862670898,
|
| 225 |
+
"learning_rate": 9.871172521558523e-06,
|
| 226 |
+
"loss": 0.8541,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.05360134003350084,
|
| 231 |
+
"grad_norm": 9.949478149414062,
|
| 232 |
+
"learning_rate": 9.858670610873528e-06,
|
| 233 |
+
"loss": 0.8863,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.05527638190954774,
|
| 238 |
+
"grad_norm": 8.322579383850098,
|
| 239 |
+
"learning_rate": 9.845598513650104e-06,
|
| 240 |
+
"loss": 0.8315,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.05695142378559464,
|
| 245 |
+
"grad_norm": 9.097247123718262,
|
| 246 |
+
"learning_rate": 9.831957763956814e-06,
|
| 247 |
+
"loss": 0.7842,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.05862646566164154,
|
| 252 |
+
"grad_norm": 14.322467803955078,
|
| 253 |
+
"learning_rate": 9.817749962596115e-06,
|
| 254 |
+
"loss": 0.7906,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06030150753768844,
|
| 259 |
+
"grad_norm": 7.565073490142822,
|
| 260 |
+
"learning_rate": 9.802976776916493e-06,
|
| 261 |
+
"loss": 0.7968,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.06197654941373534,
|
| 266 |
+
"grad_norm": 17.257848739624023,
|
| 267 |
+
"learning_rate": 9.787639940616789e-06,
|
| 268 |
+
"loss": 0.6602,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.06365159128978225,
|
| 273 |
+
"grad_norm": 7.198502540588379,
|
| 274 |
+
"learning_rate": 9.771741253542742e-06,
|
| 275 |
+
"loss": 0.6571,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.06532663316582915,
|
| 280 |
+
"grad_norm": 15.588485717773438,
|
| 281 |
+
"learning_rate": 9.755282581475769e-06,
|
| 282 |
+
"loss": 0.9697,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.06700167504187604,
|
| 287 |
+
"grad_norm": 9.76461124420166,
|
| 288 |
+
"learning_rate": 9.738265855914014e-06,
|
| 289 |
+
"loss": 0.8673,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.06867671691792294,
|
| 294 |
+
"grad_norm": 12.12215805053711,
|
| 295 |
+
"learning_rate": 9.720693073845668e-06,
|
| 296 |
+
"loss": 0.909,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07035175879396985,
|
| 301 |
+
"grad_norm": 6.311887264251709,
|
| 302 |
+
"learning_rate": 9.70256629751462e-06,
|
| 303 |
+
"loss": 0.5544,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.07202680067001675,
|
| 308 |
+
"grad_norm": 14.915327072143555,
|
| 309 |
+
"learning_rate": 9.683887654178446e-06,
|
| 310 |
+
"loss": 0.708,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.07370184254606366,
|
| 315 |
+
"grad_norm": 8.040735244750977,
|
| 316 |
+
"learning_rate": 9.664659335858755e-06,
|
| 317 |
+
"loss": 0.6549,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.07537688442211055,
|
| 322 |
+
"grad_norm": 216.47198486328125,
|
| 323 |
+
"learning_rate": 9.644883599083959e-06,
|
| 324 |
+
"loss": 0.5904,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.07705192629815745,
|
| 329 |
+
"grad_norm": 15.451247215270996,
|
| 330 |
+
"learning_rate": 9.624562764624445e-06,
|
| 331 |
+
"loss": 0.6873,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.07872696817420435,
|
| 336 |
+
"grad_norm": 22.482295989990234,
|
| 337 |
+
"learning_rate": 9.603699217220239e-06,
|
| 338 |
+
"loss": 0.6076,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.08040201005025126,
|
| 343 |
+
"grad_norm": 8.874513626098633,
|
| 344 |
+
"learning_rate": 9.582295405301131e-06,
|
| 345 |
+
"loss": 0.638,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.08207705192629816,
|
| 350 |
+
"grad_norm": 6.470407962799072,
|
| 351 |
+
"learning_rate": 9.56035384069935e-06,
|
| 352 |
+
"loss": 0.5414,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.08375209380234507,
|
| 357 |
+
"grad_norm": 10.324779510498047,
|
| 358 |
+
"learning_rate": 9.537877098354787e-06,
|
| 359 |
+
"loss": 0.4528,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08542713567839195,
|
| 364 |
+
"grad_norm": 37.99070358276367,
|
| 365 |
+
"learning_rate": 9.514867816012809e-06,
|
| 366 |
+
"loss": 0.6703,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.08710217755443886,
|
| 371 |
+
"grad_norm": 7.273169994354248,
|
| 372 |
+
"learning_rate": 9.491328693914723e-06,
|
| 373 |
+
"loss": 0.6366,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.08877721943048576,
|
| 378 |
+
"grad_norm": 8.475452423095703,
|
| 379 |
+
"learning_rate": 9.46726249448087e-06,
|
| 380 |
+
"loss": 0.6846,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.09045226130653267,
|
| 385 |
+
"grad_norm": 9.614311218261719,
|
| 386 |
+
"learning_rate": 9.442672041986456e-06,
|
| 387 |
+
"loss": 0.7953,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.09212730318257957,
|
| 392 |
+
"grad_norm": 14.27919864654541,
|
| 393 |
+
"learning_rate": 9.417560222230115e-06,
|
| 394 |
+
"loss": 0.6215,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.09380234505862646,
|
| 399 |
+
"grad_norm": 12.88886547088623,
|
| 400 |
+
"learning_rate": 9.391929982195233e-06,
|
| 401 |
+
"loss": 0.7193,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.09547738693467336,
|
| 406 |
+
"grad_norm": 8.559778213500977,
|
| 407 |
+
"learning_rate": 9.365784329704114e-06,
|
| 408 |
+
"loss": 0.5583,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.09715242881072027,
|
| 413 |
+
"grad_norm": 56.14809799194336,
|
| 414 |
+
"learning_rate": 9.339126333065008e-06,
|
| 415 |
+
"loss": 0.7828,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.09882747068676717,
|
| 420 |
+
"grad_norm": 61.46057891845703,
|
| 421 |
+
"learning_rate": 9.311959120712012e-06,
|
| 422 |
+
"loss": 0.7155,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.10050251256281408,
|
| 427 |
+
"grad_norm": 17.28756332397461,
|
| 428 |
+
"learning_rate": 9.284285880837947e-06,
|
| 429 |
+
"loss": 0.5593,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.10217755443886097,
|
| 434 |
+
"grad_norm": 8.185969352722168,
|
| 435 |
+
"learning_rate": 9.256109861020213e-06,
|
| 436 |
+
"loss": 0.76,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.10385259631490787,
|
| 441 |
+
"grad_norm": 11.113842964172363,
|
| 442 |
+
"learning_rate": 9.22743436783966e-06,
|
| 443 |
+
"loss": 0.5493,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.10552763819095477,
|
| 448 |
+
"grad_norm": 16.599327087402344,
|
| 449 |
+
"learning_rate": 9.198262766492554e-06,
|
| 450 |
+
"loss": 0.6696,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.10720268006700168,
|
| 455 |
+
"grad_norm": 10.840875625610352,
|
| 456 |
+
"learning_rate": 9.168598480395653e-06,
|
| 457 |
+
"loss": 0.4487,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.10887772194304858,
|
| 462 |
+
"grad_norm": 6.5747904777526855,
|
| 463 |
+
"learning_rate": 9.138444990784455e-06,
|
| 464 |
+
"loss": 0.5742,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.11055276381909548,
|
| 469 |
+
"grad_norm": 9.715214729309082,
|
| 470 |
+
"learning_rate": 9.107805836304658e-06,
|
| 471 |
+
"loss": 0.4517,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.11222780569514237,
|
| 476 |
+
"grad_norm": 8.065790176391602,
|
| 477 |
+
"learning_rate": 9.076684612596891e-06,
|
| 478 |
+
"loss": 0.632,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.11390284757118928,
|
| 483 |
+
"grad_norm": 6.31274938583374,
|
| 484 |
+
"learning_rate": 9.045084971874738e-06,
|
| 485 |
+
"loss": 0.6249,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.11557788944723618,
|
| 490 |
+
"grad_norm": 6.64466667175293,
|
| 491 |
+
"learning_rate": 9.013010622496145e-06,
|
| 492 |
+
"loss": 0.6312,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.11725293132328309,
|
| 497 |
+
"grad_norm": 5.58828592300415,
|
| 498 |
+
"learning_rate": 8.98046532852822e-06,
|
| 499 |
+
"loss": 0.6025,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.11892797319932999,
|
| 504 |
+
"grad_norm": 16.6801815032959,
|
| 505 |
+
"learning_rate": 8.94745290930551e-06,
|
| 506 |
+
"loss": 0.6504,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.12060301507537688,
|
| 511 |
+
"grad_norm": 8.754212379455566,
|
| 512 |
+
"learning_rate": 8.91397723898178e-06,
|
| 513 |
+
"loss": 0.5521,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.12227805695142378,
|
| 518 |
+
"grad_norm": 17.730134963989258,
|
| 519 |
+
"learning_rate": 8.880042246075366e-06,
|
| 520 |
+
"loss": 0.5011,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.12395309882747069,
|
| 525 |
+
"grad_norm": 62.947059631347656,
|
| 526 |
+
"learning_rate": 8.845651913008145e-06,
|
| 527 |
+
"loss": 0.4938,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.12562814070351758,
|
| 532 |
+
"grad_norm": 7.203149795532227,
|
| 533 |
+
"learning_rate": 8.810810275638183e-06,
|
| 534 |
+
"loss": 0.6011,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.1273031825795645,
|
| 539 |
+
"grad_norm": 14.420639991760254,
|
| 540 |
+
"learning_rate": 8.775521422786104e-06,
|
| 541 |
+
"loss": 0.4677,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.12897822445561138,
|
| 546 |
+
"grad_norm": 15.807499885559082,
|
| 547 |
+
"learning_rate": 8.739789495755254e-06,
|
| 548 |
+
"loss": 0.4981,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.1306532663316583,
|
| 553 |
+
"grad_norm": 11.188671112060547,
|
| 554 |
+
"learning_rate": 8.703618687845697e-06,
|
| 555 |
+
"loss": 0.7101,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.1323283082077052,
|
| 560 |
+
"grad_norm": 8.056306838989258,
|
| 561 |
+
"learning_rate": 8.667013243862113e-06,
|
| 562 |
+
"loss": 0.4939,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.13400335008375208,
|
| 567 |
+
"grad_norm": 19.15292739868164,
|
| 568 |
+
"learning_rate": 8.629977459615655e-06,
|
| 569 |
+
"loss": 0.4609,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.135678391959799,
|
| 574 |
+
"grad_norm": 17.06001853942871,
|
| 575 |
+
"learning_rate": 8.592515681419812e-06,
|
| 576 |
+
"loss": 0.5927,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.1373534338358459,
|
| 581 |
+
"grad_norm": 45.06548309326172,
|
| 582 |
+
"learning_rate": 8.554632305580355e-06,
|
| 583 |
+
"loss": 0.3981,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.1390284757118928,
|
| 588 |
+
"grad_norm": 7.85860013961792,
|
| 589 |
+
"learning_rate": 8.5163317778794e-06,
|
| 590 |
+
"loss": 0.5786,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.1407035175879397,
|
| 595 |
+
"grad_norm": 6.724557876586914,
|
| 596 |
+
"learning_rate": 8.477618593053693e-06,
|
| 597 |
+
"loss": 0.6885,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.1423785594639866,
|
| 602 |
+
"grad_norm": 10.746766090393066,
|
| 603 |
+
"learning_rate": 8.438497294267117e-06,
|
| 604 |
+
"loss": 0.6679,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.1440536013400335,
|
| 609 |
+
"grad_norm": 7.629374980926514,
|
| 610 |
+
"learning_rate": 8.39897247257754e-06,
|
| 611 |
+
"loss": 0.4738,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.1457286432160804,
|
| 616 |
+
"grad_norm": 9.05395221710205,
|
| 617 |
+
"learning_rate": 8.359048766398032e-06,
|
| 618 |
+
"loss": 0.477,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.1474036850921273,
|
| 623 |
+
"grad_norm": 5.074159622192383,
|
| 624 |
+
"learning_rate": 8.318730860952523e-06,
|
| 625 |
+
"loss": 0.2511,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.1490787269681742,
|
| 630 |
+
"grad_norm": 9.573104858398438,
|
| 631 |
+
"learning_rate": 8.278023487725981e-06,
|
| 632 |
+
"loss": 0.6567,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.1507537688442211,
|
| 637 |
+
"grad_norm": 8.720430374145508,
|
| 638 |
+
"learning_rate": 8.23693142390914e-06,
|
| 639 |
+
"loss": 0.6146,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.152428810720268,
|
| 644 |
+
"grad_norm": 14.700223922729492,
|
| 645 |
+
"learning_rate": 8.195459491837881e-06,
|
| 646 |
+
"loss": 0.5902,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.1541038525963149,
|
| 651 |
+
"grad_norm": 4.695188522338867,
|
| 652 |
+
"learning_rate": 8.153612558427311e-06,
|
| 653 |
+
"loss": 0.4277,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.15577889447236182,
|
| 658 |
+
"grad_norm": 10.933897972106934,
|
| 659 |
+
"learning_rate": 8.111395534600604e-06,
|
| 660 |
+
"loss": 0.6181,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.1574539363484087,
|
| 665 |
+
"grad_norm": 11.810751914978027,
|
| 666 |
+
"learning_rate": 8.068813374712689e-06,
|
| 667 |
+
"loss": 0.5727,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.15912897822445563,
|
| 672 |
+
"grad_norm": 7.552143573760986,
|
| 673 |
+
"learning_rate": 8.025871075968828e-06,
|
| 674 |
+
"loss": 0.49,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.16080402010050251,
|
| 679 |
+
"grad_norm": 5.579692363739014,
|
| 680 |
+
"learning_rate": 7.982573677838172e-06,
|
| 681 |
+
"loss": 0.4109,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.1624790619765494,
|
| 686 |
+
"grad_norm": 26.893417358398438,
|
| 687 |
+
"learning_rate": 7.938926261462366e-06,
|
| 688 |
+
"loss": 0.4731,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.16415410385259632,
|
| 693 |
+
"grad_norm": 9.309822082519531,
|
| 694 |
+
"learning_rate": 7.894933949059245e-06,
|
| 695 |
+
"loss": 0.4118,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.1658291457286432,
|
| 700 |
+
"grad_norm": 11.836834907531738,
|
| 701 |
+
"learning_rate": 7.850601903321717e-06,
|
| 702 |
+
"loss": 0.52,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.16750418760469013,
|
| 707 |
+
"grad_norm": 5.299133777618408,
|
| 708 |
+
"learning_rate": 7.805935326811913e-06,
|
| 709 |
+
"loss": 0.5764,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.16917922948073702,
|
| 714 |
+
"grad_norm": 5.415176868438721,
|
| 715 |
+
"learning_rate": 7.760939461350622e-06,
|
| 716 |
+
"loss": 0.4241,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.1708542713567839,
|
| 721 |
+
"grad_norm": 6.854716777801514,
|
| 722 |
+
"learning_rate": 7.715619587402165e-06,
|
| 723 |
+
"loss": 0.5104,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.17252931323283083,
|
| 728 |
+
"grad_norm": 14.379980087280273,
|
| 729 |
+
"learning_rate": 7.669981023454682e-06,
|
| 730 |
+
"loss": 0.5983,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.17420435510887772,
|
| 735 |
+
"grad_norm": 5.8609089851379395,
|
| 736 |
+
"learning_rate": 7.624029125396004e-06,
|
| 737 |
+
"loss": 0.5859,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.17587939698492464,
|
| 742 |
+
"grad_norm": 12.067666053771973,
|
| 743 |
+
"learning_rate": 7.57776928588511e-06,
|
| 744 |
+
"loss": 0.3405,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.17755443886097153,
|
| 749 |
+
"grad_norm": 7.230931282043457,
|
| 750 |
+
"learning_rate": 7.53120693371927e-06,
|
| 751 |
+
"loss": 0.5964,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.17922948073701842,
|
| 756 |
+
"grad_norm": 15.658750534057617,
|
| 757 |
+
"learning_rate": 7.4843475331969614e-06,
|
| 758 |
+
"loss": 0.5566,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.18090452261306533,
|
| 763 |
+
"grad_norm": 11.907587051391602,
|
| 764 |
+
"learning_rate": 7.437196583476597e-06,
|
| 765 |
+
"loss": 0.5354,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.18257956448911222,
|
| 770 |
+
"grad_norm": 19.394973754882812,
|
| 771 |
+
"learning_rate": 7.389759617931183e-06,
|
| 772 |
+
"loss": 0.6029,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.18425460636515914,
|
| 777 |
+
"grad_norm": 19.29716682434082,
|
| 778 |
+
"learning_rate": 7.342042203498952e-06,
|
| 779 |
+
"loss": 0.5322,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.18592964824120603,
|
| 784 |
+
"grad_norm": 25.739967346191406,
|
| 785 |
+
"learning_rate": 7.294049940030055e-06,
|
| 786 |
+
"loss": 0.5994,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.18760469011725292,
|
| 791 |
+
"grad_norm": 5.602751731872559,
|
| 792 |
+
"learning_rate": 7.245788459629397e-06,
|
| 793 |
+
"loss": 0.2659,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.18927973199329984,
|
| 798 |
+
"grad_norm": 18.118988037109375,
|
| 799 |
+
"learning_rate": 7.197263425995682e-06,
|
| 800 |
+
"loss": 0.5351,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.19095477386934673,
|
| 805 |
+
"grad_norm": 15.692747116088867,
|
| 806 |
+
"learning_rate": 7.148480533756759e-06,
|
| 807 |
+
"loss": 0.5777,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.19262981574539365,
|
| 812 |
+
"grad_norm": 11.225866317749023,
|
| 813 |
+
"learning_rate": 7.099445507801324e-06,
|
| 814 |
+
"loss": 0.5669,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.19430485762144054,
|
| 819 |
+
"grad_norm": 10.936521530151367,
|
| 820 |
+
"learning_rate": 7.050164102607081e-06,
|
| 821 |
+
"loss": 0.6746,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.19597989949748743,
|
| 826 |
+
"grad_norm": 14.266733169555664,
|
| 827 |
+
"learning_rate": 7.000642101565434e-06,
|
| 828 |
+
"loss": 0.6428,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.19765494137353434,
|
| 833 |
+
"grad_norm": 11.925481796264648,
|
| 834 |
+
"learning_rate": 6.950885316302773e-06,
|
| 835 |
+
"loss": 0.7126,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.19932998324958123,
|
| 840 |
+
"grad_norm": 6.662454605102539,
|
| 841 |
+
"learning_rate": 6.90089958599846e-06,
|
| 842 |
+
"loss": 0.6021,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.20100502512562815,
|
| 847 |
+
"grad_norm": 9.899117469787598,
|
| 848 |
+
"learning_rate": 6.850690776699574e-06,
|
| 849 |
+
"loss": 0.6556,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.20268006700167504,
|
| 854 |
+
"grad_norm": 13.664289474487305,
|
| 855 |
+
"learning_rate": 6.800264780632495e-06,
|
| 856 |
+
"loss": 0.5943,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.20435510887772193,
|
| 861 |
+
"grad_norm": 7.985660552978516,
|
| 862 |
+
"learning_rate": 6.749627515511443e-06,
|
| 863 |
+
"loss": 0.5525,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.20603015075376885,
|
| 868 |
+
"grad_norm": 11.558802604675293,
|
| 869 |
+
"learning_rate": 6.698784923843993e-06,
|
| 870 |
+
"loss": 0.4728,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.20770519262981574,
|
| 875 |
+
"grad_norm": 7.4603962898254395,
|
| 876 |
+
"learning_rate": 6.647742972233703e-06,
|
| 877 |
+
"loss": 0.4323,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.20938023450586266,
|
| 882 |
+
"grad_norm": 36.05428695678711,
|
| 883 |
+
"learning_rate": 6.5965076506799e-06,
|
| 884 |
+
"loss": 0.6249,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.21105527638190955,
|
| 889 |
+
"grad_norm": 16.956544876098633,
|
| 890 |
+
"learning_rate": 6.545084971874738e-06,
|
| 891 |
+
"loss": 0.3934,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.21273031825795644,
|
| 896 |
+
"grad_norm": 11.381563186645508,
|
| 897 |
+
"learning_rate": 6.493480970497569e-06,
|
| 898 |
+
"loss": 0.6617,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.21440536013400335,
|
| 903 |
+
"grad_norm": 217.95272827148438,
|
| 904 |
+
"learning_rate": 6.441701702506755e-06,
|
| 905 |
+
"loss": 0.5256,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.21608040201005024,
|
| 910 |
+
"grad_norm": 9.412247657775879,
|
| 911 |
+
"learning_rate": 6.389753244428973e-06,
|
| 912 |
+
"loss": 0.4618,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.21775544388609716,
|
| 917 |
+
"grad_norm": 17.076452255249023,
|
| 918 |
+
"learning_rate": 6.337641692646106e-06,
|
| 919 |
+
"loss": 0.593,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.21943048576214405,
|
| 924 |
+
"grad_norm": 13.418828010559082,
|
| 925 |
+
"learning_rate": 6.285373162679804e-06,
|
| 926 |
+
"loss": 0.5148,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.22110552763819097,
|
| 931 |
+
"grad_norm": 7.642491340637207,
|
| 932 |
+
"learning_rate": 6.2329537884738115e-06,
|
| 933 |
+
"loss": 0.4513,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.22278056951423786,
|
| 938 |
+
"grad_norm": 11.128157615661621,
|
| 939 |
+
"learning_rate": 6.180389721674101e-06,
|
| 940 |
+
"loss": 0.5543,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.22445561139028475,
|
| 945 |
+
"grad_norm": 15.602160453796387,
|
| 946 |
+
"learning_rate": 6.127687130906972e-06,
|
| 947 |
+
"loss": 0.517,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.22613065326633167,
|
| 952 |
+
"grad_norm": 9.082503318786621,
|
| 953 |
+
"learning_rate": 6.074852201055121e-06,
|
| 954 |
+
"loss": 0.4042,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.22780569514237856,
|
| 959 |
+
"grad_norm": 13.633258819580078,
|
| 960 |
+
"learning_rate": 6.021891132531825e-06,
|
| 961 |
+
"loss": 0.4797,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.22948073701842547,
|
| 966 |
+
"grad_norm": 21.258358001708984,
|
| 967 |
+
"learning_rate": 5.968810140553292e-06,
|
| 968 |
+
"loss": 0.3428,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.23115577889447236,
|
| 973 |
+
"grad_norm": 8.031540870666504,
|
| 974 |
+
"learning_rate": 5.915615454409281e-06,
|
| 975 |
+
"loss": 0.5858,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.23283082077051925,
|
| 980 |
+
"grad_norm": 12.13369369506836,
|
| 981 |
+
"learning_rate": 5.862313316732064e-06,
|
| 982 |
+
"loss": 0.6293,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.23450586264656617,
|
| 987 |
+
"grad_norm": 11.311995506286621,
|
| 988 |
+
"learning_rate": 5.808909982763825e-06,
|
| 989 |
+
"loss": 0.5867,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.23618090452261306,
|
| 994 |
+
"grad_norm": 8.858957290649414,
|
| 995 |
+
"learning_rate": 5.755411719622584e-06,
|
| 996 |
+
"loss": 0.5254,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.23785594639865998,
|
| 1001 |
+
"grad_norm": 8.272749900817871,
|
| 1002 |
+
"learning_rate": 5.701824805566722e-06,
|
| 1003 |
+
"loss": 0.619,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.23953098827470687,
|
| 1008 |
+
"grad_norm": 19.47360610961914,
|
| 1009 |
+
"learning_rate": 5.648155529258195e-06,
|
| 1010 |
+
"loss": 0.5212,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.24120603015075376,
|
| 1015 |
+
"grad_norm": 54.815223693847656,
|
| 1016 |
+
"learning_rate": 5.594410189024533e-06,
|
| 1017 |
+
"loss": 0.417,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.24288107202680068,
|
| 1022 |
+
"grad_norm": 5.4333415031433105,
|
| 1023 |
+
"learning_rate": 5.540595092119709e-06,
|
| 1024 |
+
"loss": 0.5524,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.24455611390284757,
|
| 1029 |
+
"grad_norm": 12.186278343200684,
|
| 1030 |
+
"learning_rate": 5.4867165539839505e-06,
|
| 1031 |
+
"loss": 0.588,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.24623115577889448,
|
| 1036 |
+
"grad_norm": 6.177221775054932,
|
| 1037 |
+
"learning_rate": 5.432780897502588e-06,
|
| 1038 |
+
"loss": 0.4526,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.24790619765494137,
|
| 1043 |
+
"grad_norm": 4.464267253875732,
|
| 1044 |
+
"learning_rate": 5.378794452264053e-06,
|
| 1045 |
+
"loss": 0.183,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.24958123953098826,
|
| 1050 |
+
"grad_norm": 11.388463020324707,
|
| 1051 |
+
"learning_rate": 5.3247635538170536e-06,
|
| 1052 |
+
"loss": 0.4689,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.25125628140703515,
|
| 1057 |
+
"grad_norm": 8.842340469360352,
|
| 1058 |
+
"learning_rate": 5.270694542927089e-06,
|
| 1059 |
+
"loss": 0.4768,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.2529313232830821,
|
| 1064 |
+
"grad_norm": 10.527604103088379,
|
| 1065 |
+
"learning_rate": 5.2165937648323115e-06,
|
| 1066 |
+
"loss": 0.5544,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.254606365159129,
|
| 1071 |
+
"grad_norm": 6.122803211212158,
|
| 1072 |
+
"learning_rate": 5.1624675684989035e-06,
|
| 1073 |
+
"loss": 0.4713,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.2562814070351759,
|
| 1078 |
+
"grad_norm": 12.654393196105957,
|
| 1079 |
+
"learning_rate": 5.108322305875988e-06,
|
| 1080 |
+
"loss": 0.4106,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.25795644891122277,
|
| 1085 |
+
"grad_norm": 9.802145004272461,
|
| 1086 |
+
"learning_rate": 5.054164331150199e-06,
|
| 1087 |
+
"loss": 0.3948,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.25963149078726966,
|
| 1092 |
+
"grad_norm": 12.221999168395996,
|
| 1093 |
+
"learning_rate": 5e-06,
|
| 1094 |
+
"loss": 0.3965,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.2613065326633166,
|
| 1099 |
+
"grad_norm": 38.88837814331055,
|
| 1100 |
+
"learning_rate": 4.945835668849801e-06,
|
| 1101 |
+
"loss": 0.4963,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.2629815745393635,
|
| 1106 |
+
"grad_norm": 8.302274703979492,
|
| 1107 |
+
"learning_rate": 4.891677694124013e-06,
|
| 1108 |
+
"loss": 0.5769,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.2646566164154104,
|
| 1113 |
+
"grad_norm": 12.677837371826172,
|
| 1114 |
+
"learning_rate": 4.837532431501098e-06,
|
| 1115 |
+
"loss": 0.5523,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.2663316582914573,
|
| 1120 |
+
"grad_norm": 30.812339782714844,
|
| 1121 |
+
"learning_rate": 4.783406235167689e-06,
|
| 1122 |
+
"loss": 0.5633,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.26800670016750416,
|
| 1127 |
+
"grad_norm": 11.15478229522705,
|
| 1128 |
+
"learning_rate": 4.729305457072913e-06,
|
| 1129 |
+
"loss": 0.5249,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.2696817420435511,
|
| 1134 |
+
"grad_norm": 12.282779693603516,
|
| 1135 |
+
"learning_rate": 4.6752364461829456e-06,
|
| 1136 |
+
"loss": 0.5661,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.271356783919598,
|
| 1141 |
+
"grad_norm": 7.128274440765381,
|
| 1142 |
+
"learning_rate": 4.621205547735949e-06,
|
| 1143 |
+
"loss": 0.5326,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.2730318257956449,
|
| 1148 |
+
"grad_norm": 7.350680828094482,
|
| 1149 |
+
"learning_rate": 4.567219102497413e-06,
|
| 1150 |
+
"loss": 0.6519,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.2747068676716918,
|
| 1155 |
+
"grad_norm": 8.06054973602295,
|
| 1156 |
+
"learning_rate": 4.513283446016052e-06,
|
| 1157 |
+
"loss": 0.4751,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.27638190954773867,
|
| 1162 |
+
"grad_norm": 12.172195434570312,
|
| 1163 |
+
"learning_rate": 4.459404907880293e-06,
|
| 1164 |
+
"loss": 0.7911,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.2780569514237856,
|
| 1169 |
+
"grad_norm": 20.65127944946289,
|
| 1170 |
+
"learning_rate": 4.4055898109754684e-06,
|
| 1171 |
+
"loss": 0.4739,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.2797319932998325,
|
| 1176 |
+
"grad_norm": 13.884875297546387,
|
| 1177 |
+
"learning_rate": 4.351844470741808e-06,
|
| 1178 |
+
"loss": 0.4879,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.2814070351758794,
|
| 1183 |
+
"grad_norm": 9.510852813720703,
|
| 1184 |
+
"learning_rate": 4.298175194433279e-06,
|
| 1185 |
+
"loss": 0.5028,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.2830820770519263,
|
| 1190 |
+
"grad_norm": 48.42875671386719,
|
| 1191 |
+
"learning_rate": 4.244588280377417e-06,
|
| 1192 |
+
"loss": 0.6133,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.2847571189279732,
|
| 1197 |
+
"grad_norm": 7.53723669052124,
|
| 1198 |
+
"learning_rate": 4.191090017236177e-06,
|
| 1199 |
+
"loss": 0.5408,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.2864321608040201,
|
| 1204 |
+
"grad_norm": 26.799591064453125,
|
| 1205 |
+
"learning_rate": 4.137686683267939e-06,
|
| 1206 |
+
"loss": 0.4197,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.288107202680067,
|
| 1211 |
+
"grad_norm": 6.606400966644287,
|
| 1212 |
+
"learning_rate": 4.0843845455907195e-06,
|
| 1213 |
+
"loss": 0.541,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.2897822445561139,
|
| 1218 |
+
"grad_norm": 23.75130271911621,
|
| 1219 |
+
"learning_rate": 4.0311898594467084e-06,
|
| 1220 |
+
"loss": 0.7346,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.2914572864321608,
|
| 1225 |
+
"grad_norm": 13.880631446838379,
|
| 1226 |
+
"learning_rate": 3.9781088674681764e-06,
|
| 1227 |
+
"loss": 0.2598,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.2931323283082077,
|
| 1232 |
+
"grad_norm": 6.773393154144287,
|
| 1233 |
+
"learning_rate": 3.92514779894488e-06,
|
| 1234 |
+
"loss": 0.6391,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.2948073701842546,
|
| 1239 |
+
"grad_norm": 26.008617401123047,
|
| 1240 |
+
"learning_rate": 3.87231286909303e-06,
|
| 1241 |
+
"loss": 0.5113,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.2964824120603015,
|
| 1246 |
+
"grad_norm": 24.8104190826416,
|
| 1247 |
+
"learning_rate": 3.8196102783259e-06,
|
| 1248 |
+
"loss": 0.4022,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.2981574539363484,
|
| 1253 |
+
"grad_norm": 15.53122329711914,
|
| 1254 |
+
"learning_rate": 3.767046211526191e-06,
|
| 1255 |
+
"loss": 0.5938,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.2998324958123953,
|
| 1260 |
+
"grad_norm": 11.584595680236816,
|
| 1261 |
+
"learning_rate": 3.7146268373201956e-06,
|
| 1262 |
+
"loss": 0.6259,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.3015075376884422,
|
| 1267 |
+
"grad_norm": 88.4962387084961,
|
| 1268 |
+
"learning_rate": 3.662358307353897e-06,
|
| 1269 |
+
"loss": 0.4355,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.30318257956448913,
|
| 1274 |
+
"grad_norm": 8.964816093444824,
|
| 1275 |
+
"learning_rate": 3.61024675557103e-06,
|
| 1276 |
+
"loss": 0.414,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.304857621440536,
|
| 1281 |
+
"grad_norm": 7.981844902038574,
|
| 1282 |
+
"learning_rate": 3.5582982974932467e-06,
|
| 1283 |
+
"loss": 0.7115,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.3065326633165829,
|
| 1288 |
+
"grad_norm": 10.597481727600098,
|
| 1289 |
+
"learning_rate": 3.5065190295024334e-06,
|
| 1290 |
+
"loss": 0.6133,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.3082077051926298,
|
| 1295 |
+
"grad_norm": 16.402362823486328,
|
| 1296 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 1297 |
+
"loss": 0.5979,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.3098827470686767,
|
| 1302 |
+
"grad_norm": 14.621550559997559,
|
| 1303 |
+
"learning_rate": 3.403492349320101e-06,
|
| 1304 |
+
"loss": 0.5506,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.31155778894472363,
|
| 1309 |
+
"grad_norm": 9.449843406677246,
|
| 1310 |
+
"learning_rate": 3.3522570277662986e-06,
|
| 1311 |
+
"loss": 0.7524,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.3132328308207705,
|
| 1316 |
+
"grad_norm": 24.799516677856445,
|
| 1317 |
+
"learning_rate": 3.3012150761560085e-06,
|
| 1318 |
+
"loss": 0.7117,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.3149078726968174,
|
| 1323 |
+
"grad_norm": 8.362727165222168,
|
| 1324 |
+
"learning_rate": 3.250372484488558e-06,
|
| 1325 |
+
"loss": 0.4724,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.3165829145728643,
|
| 1330 |
+
"grad_norm": 11.293312072753906,
|
| 1331 |
+
"learning_rate": 3.199735219367507e-06,
|
| 1332 |
+
"loss": 0.5159,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.31825795644891125,
|
| 1337 |
+
"grad_norm": 44.262168884277344,
|
| 1338 |
+
"learning_rate": 3.149309223300428e-06,
|
| 1339 |
+
"loss": 0.3814,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.31993299832495814,
|
| 1344 |
+
"grad_norm": 7.846794128417969,
|
| 1345 |
+
"learning_rate": 3.09910041400154e-06,
|
| 1346 |
+
"loss": 0.4224,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.32160804020100503,
|
| 1351 |
+
"grad_norm": 5.657670974731445,
|
| 1352 |
+
"learning_rate": 3.0491146836972273e-06,
|
| 1353 |
+
"loss": 0.5493,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.3232830820770519,
|
| 1358 |
+
"grad_norm": 7.904693126678467,
|
| 1359 |
+
"learning_rate": 2.9993578984345673e-06,
|
| 1360 |
+
"loss": 0.5352,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.3249581239530988,
|
| 1365 |
+
"grad_norm": 39.29635238647461,
|
| 1366 |
+
"learning_rate": 2.9498358973929197e-06,
|
| 1367 |
+
"loss": 0.4895,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.32663316582914576,
|
| 1372 |
+
"grad_norm": 13.3257417678833,
|
| 1373 |
+
"learning_rate": 2.9005544921986774e-06,
|
| 1374 |
+
"loss": 0.6642,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.32830820770519265,
|
| 1379 |
+
"grad_norm": 15.072986602783203,
|
| 1380 |
+
"learning_rate": 2.8515194662432423e-06,
|
| 1381 |
+
"loss": 0.5708,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.32998324958123953,
|
| 1386 |
+
"grad_norm": 9.44666576385498,
|
| 1387 |
+
"learning_rate": 2.8027365740043188e-06,
|
| 1388 |
+
"loss": 0.5566,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.3316582914572864,
|
| 1393 |
+
"grad_norm": 6.700301170349121,
|
| 1394 |
+
"learning_rate": 2.7542115403706067e-06,
|
| 1395 |
+
"loss": 0.5716,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.3333333333333333,
|
| 1400 |
+
"grad_norm": 11.697546005249023,
|
| 1401 |
+
"learning_rate": 2.705950059969948e-06,
|
| 1402 |
+
"loss": 0.7045,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.33500837520938026,
|
| 1407 |
+
"grad_norm": 22.737268447875977,
|
| 1408 |
+
"learning_rate": 2.65795779650105e-06,
|
| 1409 |
+
"loss": 0.5387,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.33668341708542715,
|
| 1414 |
+
"grad_norm": 18.21468162536621,
|
| 1415 |
+
"learning_rate": 2.610240382068818e-06,
|
| 1416 |
+
"loss": 0.6045,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.33835845896147404,
|
| 1421 |
+
"grad_norm": 12.064650535583496,
|
| 1422 |
+
"learning_rate": 2.562803416523405e-06,
|
| 1423 |
+
"loss": 0.459,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.34003350083752093,
|
| 1428 |
+
"grad_norm": 6.445646286010742,
|
| 1429 |
+
"learning_rate": 2.5156524668030402e-06,
|
| 1430 |
+
"loss": 0.4602,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.3417085427135678,
|
| 1435 |
+
"grad_norm": 11.140998840332031,
|
| 1436 |
+
"learning_rate": 2.46879306628073e-06,
|
| 1437 |
+
"loss": 0.6812,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.34338358458961477,
|
| 1442 |
+
"grad_norm": 10.476651191711426,
|
| 1443 |
+
"learning_rate": 2.422230714114891e-06,
|
| 1444 |
+
"loss": 0.6035,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.34505862646566166,
|
| 1449 |
+
"grad_norm": 8.941152572631836,
|
| 1450 |
+
"learning_rate": 2.375970874603998e-06,
|
| 1451 |
+
"loss": 0.5796,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.34673366834170855,
|
| 1456 |
+
"grad_norm": 16.08871841430664,
|
| 1457 |
+
"learning_rate": 2.3300189765453198e-06,
|
| 1458 |
+
"loss": 0.493,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.34840871021775544,
|
| 1463 |
+
"grad_norm": 7.066103935241699,
|
| 1464 |
+
"learning_rate": 2.2843804125978356e-06,
|
| 1465 |
+
"loss": 0.502,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.3500837520938023,
|
| 1470 |
+
"grad_norm": 6.593835353851318,
|
| 1471 |
+
"learning_rate": 2.2390605386493758e-06,
|
| 1472 |
+
"loss": 0.4092,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.35175879396984927,
|
| 1477 |
+
"grad_norm": 32.884464263916016,
|
| 1478 |
+
"learning_rate": 2.1940646731880887e-06,
|
| 1479 |
+
"loss": 0.7114,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.35343383584589616,
|
| 1484 |
+
"grad_norm": 13.246516227722168,
|
| 1485 |
+
"learning_rate": 2.149398096678283e-06,
|
| 1486 |
+
"loss": 0.4562,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.35510887772194305,
|
| 1491 |
+
"grad_norm": 7.112019062042236,
|
| 1492 |
+
"learning_rate": 2.105066050940758e-06,
|
| 1493 |
+
"loss": 0.6352,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.35678391959798994,
|
| 1498 |
+
"grad_norm": 8.236289978027344,
|
| 1499 |
+
"learning_rate": 2.061073738537635e-06,
|
| 1500 |
+
"loss": 0.4265,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.35845896147403683,
|
| 1505 |
+
"grad_norm": 29.113269805908203,
|
| 1506 |
+
"learning_rate": 2.0174263221618307e-06,
|
| 1507 |
+
"loss": 0.6073,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.3601340033500838,
|
| 1512 |
+
"grad_norm": 9.382705688476562,
|
| 1513 |
+
"learning_rate": 1.9741289240311757e-06,
|
| 1514 |
+
"loss": 0.4926,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.36180904522613067,
|
| 1519 |
+
"grad_norm": 14.245380401611328,
|
| 1520 |
+
"learning_rate": 1.931186625287313e-06,
|
| 1521 |
+
"loss": 0.3995,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.36348408710217756,
|
| 1526 |
+
"grad_norm": 10.581442832946777,
|
| 1527 |
+
"learning_rate": 1.8886044653993968e-06,
|
| 1528 |
+
"loss": 0.6254,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.36515912897822445,
|
| 1533 |
+
"grad_norm": 6.930440902709961,
|
| 1534 |
+
"learning_rate": 1.8463874415726918e-06,
|
| 1535 |
+
"loss": 0.4251,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.36683417085427134,
|
| 1540 |
+
"grad_norm": 19.613649368286133,
|
| 1541 |
+
"learning_rate": 1.8045405081621215e-06,
|
| 1542 |
+
"loss": 0.553,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.3685092127303183,
|
| 1547 |
+
"grad_norm": 9.161355972290039,
|
| 1548 |
+
"learning_rate": 1.7630685760908623e-06,
|
| 1549 |
+
"loss": 0.536,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.37018425460636517,
|
| 1554 |
+
"grad_norm": 9.995697975158691,
|
| 1555 |
+
"learning_rate": 1.7219765122740202e-06,
|
| 1556 |
+
"loss": 0.5082,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.37185929648241206,
|
| 1561 |
+
"grad_norm": 8.794468879699707,
|
| 1562 |
+
"learning_rate": 1.6812691390474788e-06,
|
| 1563 |
+
"loss": 0.8881,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.37353433835845895,
|
| 1568 |
+
"grad_norm": 6.503959655761719,
|
| 1569 |
+
"learning_rate": 1.64095123360197e-06,
|
| 1570 |
+
"loss": 0.3433,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.37520938023450584,
|
| 1575 |
+
"grad_norm": 57.5499153137207,
|
| 1576 |
+
"learning_rate": 1.6010275274224607e-06,
|
| 1577 |
+
"loss": 0.4246,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.3768844221105528,
|
| 1582 |
+
"grad_norm": 17.57508659362793,
|
| 1583 |
+
"learning_rate": 1.561502705732883e-06,
|
| 1584 |
+
"loss": 0.3944,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.3785594639865997,
|
| 1589 |
+
"grad_norm": 9.493674278259277,
|
| 1590 |
+
"learning_rate": 1.5223814069463077e-06,
|
| 1591 |
+
"loss": 0.588,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.38023450586264657,
|
| 1596 |
+
"grad_norm": 8.24322509765625,
|
| 1597 |
+
"learning_rate": 1.4836682221206e-06,
|
| 1598 |
+
"loss": 0.4862,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.38190954773869346,
|
| 1603 |
+
"grad_norm": 50.324214935302734,
|
| 1604 |
+
"learning_rate": 1.4453676944196477e-06,
|
| 1605 |
+
"loss": 0.4875,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.38358458961474035,
|
| 1610 |
+
"grad_norm": 7.776052951812744,
|
| 1611 |
+
"learning_rate": 1.4074843185801885e-06,
|
| 1612 |
+
"loss": 0.6423,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.3852596314907873,
|
| 1617 |
+
"grad_norm": 8.240702629089355,
|
| 1618 |
+
"learning_rate": 1.370022540384347e-06,
|
| 1619 |
+
"loss": 0.4907,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.3869346733668342,
|
| 1624 |
+
"grad_norm": 13.278138160705566,
|
| 1625 |
+
"learning_rate": 1.332986756137889e-06,
|
| 1626 |
+
"loss": 0.5323,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.38860971524288107,
|
| 1631 |
+
"grad_norm": 8.120410919189453,
|
| 1632 |
+
"learning_rate": 1.296381312154305e-06,
|
| 1633 |
+
"loss": 0.5162,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.39028475711892796,
|
| 1638 |
+
"grad_norm": 21.758024215698242,
|
| 1639 |
+
"learning_rate": 1.2602105042447472e-06,
|
| 1640 |
+
"loss": 0.5555,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.39195979899497485,
|
| 1645 |
+
"grad_norm": 7.469094276428223,
|
| 1646 |
+
"learning_rate": 1.2244785772138972e-06,
|
| 1647 |
+
"loss": 0.5623,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.3936348408710218,
|
| 1652 |
+
"grad_norm": 49.71147155761719,
|
| 1653 |
+
"learning_rate": 1.1891897243618184e-06,
|
| 1654 |
+
"loss": 0.4722,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.3953098827470687,
|
| 1659 |
+
"grad_norm": 11.76391315460205,
|
| 1660 |
+
"learning_rate": 1.1543480869918555e-06,
|
| 1661 |
+
"loss": 0.6332,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.3969849246231156,
|
| 1666 |
+
"grad_norm": 11.209744453430176,
|
| 1667 |
+
"learning_rate": 1.1199577539246348e-06,
|
| 1668 |
+
"loss": 0.6735,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.39865996649916247,
|
| 1673 |
+
"grad_norm": 5.120416641235352,
|
| 1674 |
+
"learning_rate": 1.0860227610182222e-06,
|
| 1675 |
+
"loss": 0.3694,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.40033500837520936,
|
| 1680 |
+
"grad_norm": 16.753280639648438,
|
| 1681 |
+
"learning_rate": 1.0525470906944919e-06,
|
| 1682 |
+
"loss": 0.4364,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.4020100502512563,
|
| 1687 |
+
"grad_norm": 6.704367637634277,
|
| 1688 |
+
"learning_rate": 1.0195346714717813e-06,
|
| 1689 |
+
"loss": 0.6302,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.4036850921273032,
|
| 1694 |
+
"grad_norm": 4.85359001159668,
|
| 1695 |
+
"learning_rate": 9.869893775038558e-07,
|
| 1696 |
+
"loss": 0.598,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.4053601340033501,
|
| 1701 |
+
"grad_norm": 7.249150276184082,
|
| 1702 |
+
"learning_rate": 9.549150281252633e-07,
|
| 1703 |
+
"loss": 0.4393,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.40703517587939697,
|
| 1708 |
+
"grad_norm": 7.743532180786133,
|
| 1709 |
+
"learning_rate": 9.233153874031103e-07,
|
| 1710 |
+
"loss": 0.4066,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.40871021775544386,
|
| 1715 |
+
"grad_norm": 7.766452312469482,
|
| 1716 |
+
"learning_rate": 8.921941636953435e-07,
|
| 1717 |
+
"loss": 0.5213,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.4103852596314908,
|
| 1722 |
+
"grad_norm": 6.406693458557129,
|
| 1723 |
+
"learning_rate": 8.615550092155478e-07,
|
| 1724 |
+
"loss": 0.4888,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.4120603015075377,
|
| 1729 |
+
"grad_norm": 22.529430389404297,
|
| 1730 |
+
"learning_rate": 8.314015196043501e-07,
|
| 1731 |
+
"loss": 0.5954,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.4137353433835846,
|
| 1736 |
+
"grad_norm": 13.165040016174316,
|
| 1737 |
+
"learning_rate": 8.017372335074486e-07,
|
| 1738 |
+
"loss": 0.5477,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.4154103852596315,
|
| 1743 |
+
"grad_norm": 6.576857089996338,
|
| 1744 |
+
"learning_rate": 7.725656321603414e-07,
|
| 1745 |
+
"loss": 0.5417,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.41708542713567837,
|
| 1750 |
+
"grad_norm": 22.716075897216797,
|
| 1751 |
+
"learning_rate": 7.438901389797881e-07,
|
| 1752 |
+
"loss": 0.594,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.4187604690117253,
|
| 1757 |
+
"grad_norm": 9.823974609375,
|
| 1758 |
+
"learning_rate": 7.157141191620548e-07,
|
| 1759 |
+
"loss": 0.3765,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.4204355108877722,
|
| 1764 |
+
"grad_norm": 9.209877967834473,
|
| 1765 |
+
"learning_rate": 6.880408792879905e-07,
|
| 1766 |
+
"loss": 0.4761,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.4221105527638191,
|
| 1771 |
+
"grad_norm": 9.016582489013672,
|
| 1772 |
+
"learning_rate": 6.60873666934993e-07,
|
| 1773 |
+
"loss": 0.6334,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.423785594639866,
|
| 1778 |
+
"grad_norm": 6.272766590118408,
|
| 1779 |
+
"learning_rate": 6.342156702958851e-07,
|
| 1780 |
+
"loss": 0.4594,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.42546063651591287,
|
| 1785 |
+
"grad_norm": 7.893350124359131,
|
| 1786 |
+
"learning_rate": 6.080700178047688e-07,
|
| 1787 |
+
"loss": 0.3005,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.4271356783919598,
|
| 1792 |
+
"grad_norm": 12.034364700317383,
|
| 1793 |
+
"learning_rate": 5.824397777698859e-07,
|
| 1794 |
+
"loss": 0.4884,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.4288107202680067,
|
| 1799 |
+
"grad_norm": 11.671263694763184,
|
| 1800 |
+
"learning_rate": 5.573279580135438e-07,
|
| 1801 |
+
"loss": 0.4399,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.4304857621440536,
|
| 1806 |
+
"grad_norm": 5.5128021240234375,
|
| 1807 |
+
"learning_rate": 5.327375055191313e-07,
|
| 1808 |
+
"loss": 0.4798,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.4321608040201005,
|
| 1813 |
+
"grad_norm": 13.470276832580566,
|
| 1814 |
+
"learning_rate": 5.086713060852788e-07,
|
| 1815 |
+
"loss": 0.5985,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.4338358458961474,
|
| 1820 |
+
"grad_norm": 10.267711639404297,
|
| 1821 |
+
"learning_rate": 4.851321839871908e-07,
|
| 1822 |
+
"loss": 0.5087,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.4355108877721943,
|
| 1827 |
+
"grad_norm": 9.08798599243164,
|
| 1828 |
+
"learning_rate": 4.6212290164521554e-07,
|
| 1829 |
+
"loss": 0.5305,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.4371859296482412,
|
| 1834 |
+
"grad_norm": 12.159041404724121,
|
| 1835 |
+
"learning_rate": 4.3964615930065126e-07,
|
| 1836 |
+
"loss": 0.4978,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.4388609715242881,
|
| 1841 |
+
"grad_norm": 9.033683776855469,
|
| 1842 |
+
"learning_rate": 4.1770459469887003e-07,
|
| 1843 |
+
"loss": 0.4951,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.440536013400335,
|
| 1848 |
+
"grad_norm": 14.07659912109375,
|
| 1849 |
+
"learning_rate": 3.963007827797627e-07,
|
| 1850 |
+
"loss": 0.5756,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.44221105527638194,
|
| 1855 |
+
"grad_norm": 19.38117027282715,
|
| 1856 |
+
"learning_rate": 3.754372353755559e-07,
|
| 1857 |
+
"loss": 0.6105,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.4438860971524288,
|
| 1862 |
+
"grad_norm": 17.42119789123535,
|
| 1863 |
+
"learning_rate": 3.5511640091604293e-07,
|
| 1864 |
+
"loss": 0.4331,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.4455611390284757,
|
| 1869 |
+
"grad_norm": 29.625110626220703,
|
| 1870 |
+
"learning_rate": 3.35340664141246e-07,
|
| 1871 |
+
"loss": 0.4794,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.4472361809045226,
|
| 1876 |
+
"grad_norm": 15.121739387512207,
|
| 1877 |
+
"learning_rate": 3.161123458215554e-07,
|
| 1878 |
+
"loss": 0.4272,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.4489112227805695,
|
| 1883 |
+
"grad_norm": 10.418220520019531,
|
| 1884 |
+
"learning_rate": 2.974337024853802e-07,
|
| 1885 |
+
"loss": 0.5001,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.45058626465661644,
|
| 1890 |
+
"grad_norm": 54.28071212768555,
|
| 1891 |
+
"learning_rate": 2.7930692615433353e-07,
|
| 1892 |
+
"loss": 0.3813,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.45226130653266333,
|
| 1897 |
+
"grad_norm": 36.43853759765625,
|
| 1898 |
+
"learning_rate": 2.617341440859883e-07,
|
| 1899 |
+
"loss": 0.4241,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.4539363484087102,
|
| 1904 |
+
"grad_norm": 5.519733428955078,
|
| 1905 |
+
"learning_rate": 2.447174185242324e-07,
|
| 1906 |
+
"loss": 0.3407,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.4556113902847571,
|
| 1911 |
+
"grad_norm": 14.556188583374023,
|
| 1912 |
+
"learning_rate": 2.2825874645725942e-07,
|
| 1913 |
+
"loss": 0.6346,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.457286432160804,
|
| 1918 |
+
"grad_norm": 6.780929088592529,
|
| 1919 |
+
"learning_rate": 2.1236005938321092e-07,
|
| 1920 |
+
"loss": 0.4018,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.45896147403685095,
|
| 1925 |
+
"grad_norm": 5.3348236083984375,
|
| 1926 |
+
"learning_rate": 1.9702322308350675e-07,
|
| 1927 |
+
"loss": 0.4059,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.46063651591289784,
|
| 1932 |
+
"grad_norm": 28.80681037902832,
|
| 1933 |
+
"learning_rate": 1.8225003740388546e-07,
|
| 1934 |
+
"loss": 0.5874,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.4623115577889447,
|
| 1939 |
+
"grad_norm": 25.336196899414062,
|
| 1940 |
+
"learning_rate": 1.6804223604318825e-07,
|
| 1941 |
+
"loss": 0.4397,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.4639865996649916,
|
| 1946 |
+
"grad_norm": 18.95155906677246,
|
| 1947 |
+
"learning_rate": 1.5440148634989827e-07,
|
| 1948 |
+
"loss": 0.6041,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.4656616415410385,
|
| 1953 |
+
"grad_norm": 31.836097717285156,
|
| 1954 |
+
"learning_rate": 1.413293891264722e-07,
|
| 1955 |
+
"loss": 0.5253,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.46733668341708545,
|
| 1960 |
+
"grad_norm": 9.865562438964844,
|
| 1961 |
+
"learning_rate": 1.2882747844147893e-07,
|
| 1962 |
+
"loss": 0.4289,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.46901172529313234,
|
| 1967 |
+
"grad_norm": 9.91409683227539,
|
| 1968 |
+
"learning_rate": 1.1689722144956672e-07,
|
| 1969 |
+
"loss": 0.3261,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.47068676716917923,
|
| 1974 |
+
"grad_norm": 6.046374320983887,
|
| 1975 |
+
"learning_rate": 1.0554001821929061e-07,
|
| 1976 |
+
"loss": 0.4735,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.4723618090452261,
|
| 1981 |
+
"grad_norm": 19.15390968322754,
|
| 1982 |
+
"learning_rate": 9.475720156880419e-08,
|
| 1983 |
+
"loss": 0.3544,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.474036850921273,
|
| 1988 |
+
"grad_norm": 21.648508071899414,
|
| 1989 |
+
"learning_rate": 8.45500369094504e-08,
|
| 1990 |
+
"loss": 0.5075,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.47571189279731996,
|
| 1995 |
+
"grad_norm": 5.8988800048828125,
|
| 1996 |
+
"learning_rate": 7.491972209725807e-08,
|
| 1997 |
+
"loss": 0.4676,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.47738693467336685,
|
| 2002 |
+
"grad_norm": 6.347811698913574,
|
| 2003 |
+
"learning_rate": 6.58673872923693e-08,
|
| 2004 |
+
"loss": 0.4129,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.47906197654941374,
|
| 2009 |
+
"grad_norm": 11.679835319519043,
|
| 2010 |
+
"learning_rate": 5.739409482640956e-08,
|
| 2011 |
+
"loss": 0.4807,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.4807370184254606,
|
| 2016 |
+
"grad_norm": 11.485947608947754,
|
| 2017 |
+
"learning_rate": 4.950083907781733e-08,
|
| 2018 |
+
"loss": 0.4375,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.4824120603015075,
|
| 2023 |
+
"grad_norm": 10.619180679321289,
|
| 2024 |
+
"learning_rate": 4.2188546355153016e-08,
|
| 2025 |
+
"loss": 0.5927,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.48408710217755446,
|
| 2030 |
+
"grad_norm": 20.557666778564453,
|
| 2031 |
+
"learning_rate": 3.5458074788387585e-08,
|
| 2032 |
+
"loss": 0.4438,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.48576214405360135,
|
| 2037 |
+
"grad_norm": 9.889961242675781,
|
| 2038 |
+
"learning_rate": 2.9310214228202016e-08,
|
| 2039 |
+
"loss": 0.4449,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.48743718592964824,
|
| 2044 |
+
"grad_norm": 14.826864242553711,
|
| 2045 |
+
"learning_rate": 2.3745686153290314e-08,
|
| 2046 |
+
"loss": 0.6031,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.48911222780569513,
|
| 2051 |
+
"grad_norm": 8.660721778869629,
|
| 2052 |
+
"learning_rate": 1.8765143585693924e-08,
|
| 2053 |
+
"loss": 0.2636,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.490787269681742,
|
| 2058 |
+
"grad_norm": 36.333221435546875,
|
| 2059 |
+
"learning_rate": 1.4369171014165795e-08,
|
| 2060 |
+
"loss": 0.4975,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.49246231155778897,
|
| 2065 |
+
"grad_norm": 5.76406192779541,
|
| 2066 |
+
"learning_rate": 1.0558284325578038e-08,
|
| 2067 |
+
"loss": 0.435,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.49413735343383586,
|
| 2072 |
+
"grad_norm": 7.007124900817871,
|
| 2073 |
+
"learning_rate": 7.332930744380906e-09,
|
| 2074 |
+
"loss": 0.5393,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.49581239530988275,
|
| 2079 |
+
"grad_norm": 8.597932815551758,
|
| 2080 |
+
"learning_rate": 4.69348878011644e-09,
|
| 2081 |
+
"loss": 0.445,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.49748743718592964,
|
| 2086 |
+
"grad_norm": 6.45357084274292,
|
| 2087 |
+
"learning_rate": 2.640268183002337e-09,
|
| 2088 |
+
"loss": 0.4827,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.4991624790619765,
|
| 2093 |
+
"grad_norm": 10.597525596618652,
|
| 2094 |
+
"learning_rate": 1.173509907579362e-09,
|
| 2095 |
+
"loss": 0.5845,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.5008375209380235,
|
| 2100 |
+
"grad_norm": 35.76505661010742,
|
| 2101 |
+
"learning_rate": 2.9338608443452154e-10,
|
| 2102 |
+
"loss": 0.4823,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.5008375209380235,
|
| 2107 |
+
"step": 299,
|
| 2108 |
+
"total_flos": 7.518564054676275e+16,
|
| 2109 |
+
"train_loss": 0.7220620686892283,
|
| 2110 |
+
"train_runtime": 621.1923,
|
| 2111 |
+
"train_samples_per_second": 1.92,
|
| 2112 |
+
"train_steps_per_second": 0.481
|
| 2113 |
+
}
|
| 2114 |
+
],
|
| 2115 |
+
"logging_steps": 1.0,
|
| 2116 |
+
"max_steps": 299,
|
| 2117 |
+
"num_input_tokens_seen": 0,
|
| 2118 |
+
"num_train_epochs": 1,
|
| 2119 |
+
"save_steps": 100,
|
| 2120 |
+
"stateful_callbacks": {
|
| 2121 |
+
"TrainerControl": {
|
| 2122 |
+
"args": {
|
| 2123 |
+
"should_epoch_stop": false,
|
| 2124 |
+
"should_evaluate": false,
|
| 2125 |
+
"should_log": false,
|
| 2126 |
+
"should_save": true,
|
| 2127 |
+
"should_training_stop": true
|
| 2128 |
+
},
|
| 2129 |
+
"attributes": {}
|
| 2130 |
+
}
|
| 2131 |
+
},
|
| 2132 |
+
"total_flos": 7.518564054676275e+16,
|
| 2133 |
+
"train_batch_size": 1,
|
| 2134 |
+
"trial_name": null,
|
| 2135 |
+
"trial_params": null
|
| 2136 |
+
}
|
merge_sft_o3/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97df8d883ecaae4d490b3388e60624a12421f4839806268c80e0328e288a1387
|
| 3 |
+
size 6904
|
merge_sft_o3/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 2048,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
+
"max_window_layers": 70,
|
| 14 |
+
"model_type": "qwen2_5_vl",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_hidden_layers": 36,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"depth": 32,
|
| 39 |
+
"fullatt_block_indexes": [
|
| 40 |
+
7,
|
| 41 |
+
15,
|
| 42 |
+
23,
|
| 43 |
+
31
|
| 44 |
+
],
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 1280,
|
| 47 |
+
"in_channels": 3,
|
| 48 |
+
"in_chans": 3,
|
| 49 |
+
"intermediate_size": 3420,
|
| 50 |
+
"model_type": "qwen2_5_vl",
|
| 51 |
+
"num_heads": 16,
|
| 52 |
+
"out_hidden_size": 2048,
|
| 53 |
+
"patch_size": 14,
|
| 54 |
+
"spatial_merge_size": 2,
|
| 55 |
+
"spatial_patch_size": 14,
|
| 56 |
+
"temporal_patch_size": 2,
|
| 57 |
+
"tokens_per_second": 2,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"window_size": 112
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652,
|
| 63 |
+
"vision_token_id": 151654,
|
| 64 |
+
"vocab_size": 151936
|
| 65 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.51.3",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:510e292ada906584c2c57e93d06606f6da608da6f71b28abae4510e6d8114b8b
|
| 3 |
+
size 4955009048
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24827ae5bddfc35276c1537e908bfaca1146d8596e4ea942633769c7753678cc
|
| 3 |
+
size 3176658952
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8131575808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 380 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.norm.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.27.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.28.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.28.norm1.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 726 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 732 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 738 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 744 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 750 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"visual.blocks.31.norm1.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 756 |
+
"visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 762 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 763 |
+
"visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 768 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 774 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 775 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 780 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 786 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 792 |
+
"visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 798 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 799 |
+
"visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 804 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 810 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 811 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 816 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 822 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 823 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 825 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.bias": "model-00002-of-00002.safetensors",
|
| 827 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.bias": "model-00002-of-00002.safetensors",
|
| 829 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 830 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
| 831 |
+
}
|
| 832 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 2007040,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 12544,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 2007040,
|
| 26 |
+
"shortest_edge": 12544
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/special_tokens_map.json
ADDED
|
@@ -0,0 +1,1031 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<0>",
|
| 17 |
+
"<1>",
|
| 18 |
+
"<2>",
|
| 19 |
+
"<3>",
|
| 20 |
+
"<4>",
|
| 21 |
+
"<5>",
|
| 22 |
+
"<6>",
|
| 23 |
+
"<7>",
|
| 24 |
+
"<8>",
|
| 25 |
+
"<9>",
|
| 26 |
+
"<10>",
|
| 27 |
+
"<11>",
|
| 28 |
+
"<12>",
|
| 29 |
+
"<13>",
|
| 30 |
+
"<14>",
|
| 31 |
+
"<15>",
|
| 32 |
+
"<16>",
|
| 33 |
+
"<17>",
|
| 34 |
+
"<18>",
|
| 35 |
+
"<19>",
|
| 36 |
+
"<20>",
|
| 37 |
+
"<21>",
|
| 38 |
+
"<22>",
|
| 39 |
+
"<23>",
|
| 40 |
+
"<24>",
|
| 41 |
+
"<25>",
|
| 42 |
+
"<26>",
|
| 43 |
+
"<27>",
|
| 44 |
+
"<28>",
|
| 45 |
+
"<29>",
|
| 46 |
+
"<30>",
|
| 47 |
+
"<31>",
|
| 48 |
+
"<32>",
|
| 49 |
+
"<33>",
|
| 50 |
+
"<34>",
|
| 51 |
+
"<35>",
|
| 52 |
+
"<36>",
|
| 53 |
+
"<37>",
|
| 54 |
+
"<38>",
|
| 55 |
+
"<39>",
|
| 56 |
+
"<40>",
|
| 57 |
+
"<41>",
|
| 58 |
+
"<42>",
|
| 59 |
+
"<43>",
|
| 60 |
+
"<44>",
|
| 61 |
+
"<45>",
|
| 62 |
+
"<46>",
|
| 63 |
+
"<47>",
|
| 64 |
+
"<48>",
|
| 65 |
+
"<49>",
|
| 66 |
+
"<50>",
|
| 67 |
+
"<51>",
|
| 68 |
+
"<52>",
|
| 69 |
+
"<53>",
|
| 70 |
+
"<54>",
|
| 71 |
+
"<55>",
|
| 72 |
+
"<56>",
|
| 73 |
+
"<57>",
|
| 74 |
+
"<58>",
|
| 75 |
+
"<59>",
|
| 76 |
+
"<60>",
|
| 77 |
+
"<61>",
|
| 78 |
+
"<62>",
|
| 79 |
+
"<63>",
|
| 80 |
+
"<64>",
|
| 81 |
+
"<65>",
|
| 82 |
+
"<66>",
|
| 83 |
+
"<67>",
|
| 84 |
+
"<68>",
|
| 85 |
+
"<69>",
|
| 86 |
+
"<70>",
|
| 87 |
+
"<71>",
|
| 88 |
+
"<72>",
|
| 89 |
+
"<73>",
|
| 90 |
+
"<74>",
|
| 91 |
+
"<75>",
|
| 92 |
+
"<76>",
|
| 93 |
+
"<77>",
|
| 94 |
+
"<78>",
|
| 95 |
+
"<79>",
|
| 96 |
+
"<80>",
|
| 97 |
+
"<81>",
|
| 98 |
+
"<82>",
|
| 99 |
+
"<83>",
|
| 100 |
+
"<84>",
|
| 101 |
+
"<85>",
|
| 102 |
+
"<86>",
|
| 103 |
+
"<87>",
|
| 104 |
+
"<88>",
|
| 105 |
+
"<89>",
|
| 106 |
+
"<90>",
|
| 107 |
+
"<91>",
|
| 108 |
+
"<92>",
|
| 109 |
+
"<93>",
|
| 110 |
+
"<94>",
|
| 111 |
+
"<95>",
|
| 112 |
+
"<96>",
|
| 113 |
+
"<97>",
|
| 114 |
+
"<98>",
|
| 115 |
+
"<99>",
|
| 116 |
+
"<100>",
|
| 117 |
+
"<101>",
|
| 118 |
+
"<102>",
|
| 119 |
+
"<103>",
|
| 120 |
+
"<104>",
|
| 121 |
+
"<105>",
|
| 122 |
+
"<106>",
|
| 123 |
+
"<107>",
|
| 124 |
+
"<108>",
|
| 125 |
+
"<109>",
|
| 126 |
+
"<110>",
|
| 127 |
+
"<111>",
|
| 128 |
+
"<112>",
|
| 129 |
+
"<113>",
|
| 130 |
+
"<114>",
|
| 131 |
+
"<115>",
|
| 132 |
+
"<116>",
|
| 133 |
+
"<117>",
|
| 134 |
+
"<118>",
|
| 135 |
+
"<119>",
|
| 136 |
+
"<120>",
|
| 137 |
+
"<121>",
|
| 138 |
+
"<122>",
|
| 139 |
+
"<123>",
|
| 140 |
+
"<124>",
|
| 141 |
+
"<125>",
|
| 142 |
+
"<126>",
|
| 143 |
+
"<127>",
|
| 144 |
+
"<128>",
|
| 145 |
+
"<129>",
|
| 146 |
+
"<130>",
|
| 147 |
+
"<131>",
|
| 148 |
+
"<132>",
|
| 149 |
+
"<133>",
|
| 150 |
+
"<134>",
|
| 151 |
+
"<135>",
|
| 152 |
+
"<136>",
|
| 153 |
+
"<137>",
|
| 154 |
+
"<138>",
|
| 155 |
+
"<139>",
|
| 156 |
+
"<140>",
|
| 157 |
+
"<141>",
|
| 158 |
+
"<142>",
|
| 159 |
+
"<143>",
|
| 160 |
+
"<144>",
|
| 161 |
+
"<145>",
|
| 162 |
+
"<146>",
|
| 163 |
+
"<147>",
|
| 164 |
+
"<148>",
|
| 165 |
+
"<149>",
|
| 166 |
+
"<150>",
|
| 167 |
+
"<151>",
|
| 168 |
+
"<152>",
|
| 169 |
+
"<153>",
|
| 170 |
+
"<154>",
|
| 171 |
+
"<155>",
|
| 172 |
+
"<156>",
|
| 173 |
+
"<157>",
|
| 174 |
+
"<158>",
|
| 175 |
+
"<159>",
|
| 176 |
+
"<160>",
|
| 177 |
+
"<161>",
|
| 178 |
+
"<162>",
|
| 179 |
+
"<163>",
|
| 180 |
+
"<164>",
|
| 181 |
+
"<165>",
|
| 182 |
+
"<166>",
|
| 183 |
+
"<167>",
|
| 184 |
+
"<168>",
|
| 185 |
+
"<169>",
|
| 186 |
+
"<170>",
|
| 187 |
+
"<171>",
|
| 188 |
+
"<172>",
|
| 189 |
+
"<173>",
|
| 190 |
+
"<174>",
|
| 191 |
+
"<175>",
|
| 192 |
+
"<176>",
|
| 193 |
+
"<177>",
|
| 194 |
+
"<178>",
|
| 195 |
+
"<179>",
|
| 196 |
+
"<180>",
|
| 197 |
+
"<181>",
|
| 198 |
+
"<182>",
|
| 199 |
+
"<183>",
|
| 200 |
+
"<184>",
|
| 201 |
+
"<185>",
|
| 202 |
+
"<186>",
|
| 203 |
+
"<187>",
|
| 204 |
+
"<188>",
|
| 205 |
+
"<189>",
|
| 206 |
+
"<190>",
|
| 207 |
+
"<191>",
|
| 208 |
+
"<192>",
|
| 209 |
+
"<193>",
|
| 210 |
+
"<194>",
|
| 211 |
+
"<195>",
|
| 212 |
+
"<196>",
|
| 213 |
+
"<197>",
|
| 214 |
+
"<198>",
|
| 215 |
+
"<199>",
|
| 216 |
+
"<200>",
|
| 217 |
+
"<201>",
|
| 218 |
+
"<202>",
|
| 219 |
+
"<203>",
|
| 220 |
+
"<204>",
|
| 221 |
+
"<205>",
|
| 222 |
+
"<206>",
|
| 223 |
+
"<207>",
|
| 224 |
+
"<208>",
|
| 225 |
+
"<209>",
|
| 226 |
+
"<210>",
|
| 227 |
+
"<211>",
|
| 228 |
+
"<212>",
|
| 229 |
+
"<213>",
|
| 230 |
+
"<214>",
|
| 231 |
+
"<215>",
|
| 232 |
+
"<216>",
|
| 233 |
+
"<217>",
|
| 234 |
+
"<218>",
|
| 235 |
+
"<219>",
|
| 236 |
+
"<220>",
|
| 237 |
+
"<221>",
|
| 238 |
+
"<222>",
|
| 239 |
+
"<223>",
|
| 240 |
+
"<224>",
|
| 241 |
+
"<225>",
|
| 242 |
+
"<226>",
|
| 243 |
+
"<227>",
|
| 244 |
+
"<228>",
|
| 245 |
+
"<229>",
|
| 246 |
+
"<230>",
|
| 247 |
+
"<231>",
|
| 248 |
+
"<232>",
|
| 249 |
+
"<233>",
|
| 250 |
+
"<234>",
|
| 251 |
+
"<235>",
|
| 252 |
+
"<236>",
|
| 253 |
+
"<237>",
|
| 254 |
+
"<238>",
|
| 255 |
+
"<239>",
|
| 256 |
+
"<240>",
|
| 257 |
+
"<241>",
|
| 258 |
+
"<242>",
|
| 259 |
+
"<243>",
|
| 260 |
+
"<244>",
|
| 261 |
+
"<245>",
|
| 262 |
+
"<246>",
|
| 263 |
+
"<247>",
|
| 264 |
+
"<248>",
|
| 265 |
+
"<249>",
|
| 266 |
+
"<250>",
|
| 267 |
+
"<251>",
|
| 268 |
+
"<252>",
|
| 269 |
+
"<253>",
|
| 270 |
+
"<254>",
|
| 271 |
+
"<255>",
|
| 272 |
+
"<256>",
|
| 273 |
+
"<257>",
|
| 274 |
+
"<258>",
|
| 275 |
+
"<259>",
|
| 276 |
+
"<260>",
|
| 277 |
+
"<261>",
|
| 278 |
+
"<262>",
|
| 279 |
+
"<263>",
|
| 280 |
+
"<264>",
|
| 281 |
+
"<265>",
|
| 282 |
+
"<266>",
|
| 283 |
+
"<267>",
|
| 284 |
+
"<268>",
|
| 285 |
+
"<269>",
|
| 286 |
+
"<270>",
|
| 287 |
+
"<271>",
|
| 288 |
+
"<272>",
|
| 289 |
+
"<273>",
|
| 290 |
+
"<274>",
|
| 291 |
+
"<275>",
|
| 292 |
+
"<276>",
|
| 293 |
+
"<277>",
|
| 294 |
+
"<278>",
|
| 295 |
+
"<279>",
|
| 296 |
+
"<280>",
|
| 297 |
+
"<281>",
|
| 298 |
+
"<282>",
|
| 299 |
+
"<283>",
|
| 300 |
+
"<284>",
|
| 301 |
+
"<285>",
|
| 302 |
+
"<286>",
|
| 303 |
+
"<287>",
|
| 304 |
+
"<288>",
|
| 305 |
+
"<289>",
|
| 306 |
+
"<290>",
|
| 307 |
+
"<291>",
|
| 308 |
+
"<292>",
|
| 309 |
+
"<293>",
|
| 310 |
+
"<294>",
|
| 311 |
+
"<295>",
|
| 312 |
+
"<296>",
|
| 313 |
+
"<297>",
|
| 314 |
+
"<298>",
|
| 315 |
+
"<299>",
|
| 316 |
+
"<300>",
|
| 317 |
+
"<301>",
|
| 318 |
+
"<302>",
|
| 319 |
+
"<303>",
|
| 320 |
+
"<304>",
|
| 321 |
+
"<305>",
|
| 322 |
+
"<306>",
|
| 323 |
+
"<307>",
|
| 324 |
+
"<308>",
|
| 325 |
+
"<309>",
|
| 326 |
+
"<310>",
|
| 327 |
+
"<311>",
|
| 328 |
+
"<312>",
|
| 329 |
+
"<313>",
|
| 330 |
+
"<314>",
|
| 331 |
+
"<315>",
|
| 332 |
+
"<316>",
|
| 333 |
+
"<317>",
|
| 334 |
+
"<318>",
|
| 335 |
+
"<319>",
|
| 336 |
+
"<320>",
|
| 337 |
+
"<321>",
|
| 338 |
+
"<322>",
|
| 339 |
+
"<323>",
|
| 340 |
+
"<324>",
|
| 341 |
+
"<325>",
|
| 342 |
+
"<326>",
|
| 343 |
+
"<327>",
|
| 344 |
+
"<328>",
|
| 345 |
+
"<329>",
|
| 346 |
+
"<330>",
|
| 347 |
+
"<331>",
|
| 348 |
+
"<332>",
|
| 349 |
+
"<333>",
|
| 350 |
+
"<334>",
|
| 351 |
+
"<335>",
|
| 352 |
+
"<336>",
|
| 353 |
+
"<337>",
|
| 354 |
+
"<338>",
|
| 355 |
+
"<339>",
|
| 356 |
+
"<340>",
|
| 357 |
+
"<341>",
|
| 358 |
+
"<342>",
|
| 359 |
+
"<343>",
|
| 360 |
+
"<344>",
|
| 361 |
+
"<345>",
|
| 362 |
+
"<346>",
|
| 363 |
+
"<347>",
|
| 364 |
+
"<348>",
|
| 365 |
+
"<349>",
|
| 366 |
+
"<350>",
|
| 367 |
+
"<351>",
|
| 368 |
+
"<352>",
|
| 369 |
+
"<353>",
|
| 370 |
+
"<354>",
|
| 371 |
+
"<355>",
|
| 372 |
+
"<356>",
|
| 373 |
+
"<357>",
|
| 374 |
+
"<358>",
|
| 375 |
+
"<359>",
|
| 376 |
+
"<360>",
|
| 377 |
+
"<361>",
|
| 378 |
+
"<362>",
|
| 379 |
+
"<363>",
|
| 380 |
+
"<364>",
|
| 381 |
+
"<365>",
|
| 382 |
+
"<366>",
|
| 383 |
+
"<367>",
|
| 384 |
+
"<368>",
|
| 385 |
+
"<369>",
|
| 386 |
+
"<370>",
|
| 387 |
+
"<371>",
|
| 388 |
+
"<372>",
|
| 389 |
+
"<373>",
|
| 390 |
+
"<374>",
|
| 391 |
+
"<375>",
|
| 392 |
+
"<376>",
|
| 393 |
+
"<377>",
|
| 394 |
+
"<378>",
|
| 395 |
+
"<379>",
|
| 396 |
+
"<380>",
|
| 397 |
+
"<381>",
|
| 398 |
+
"<382>",
|
| 399 |
+
"<383>",
|
| 400 |
+
"<384>",
|
| 401 |
+
"<385>",
|
| 402 |
+
"<386>",
|
| 403 |
+
"<387>",
|
| 404 |
+
"<388>",
|
| 405 |
+
"<389>",
|
| 406 |
+
"<390>",
|
| 407 |
+
"<391>",
|
| 408 |
+
"<392>",
|
| 409 |
+
"<393>",
|
| 410 |
+
"<394>",
|
| 411 |
+
"<395>",
|
| 412 |
+
"<396>",
|
| 413 |
+
"<397>",
|
| 414 |
+
"<398>",
|
| 415 |
+
"<399>",
|
| 416 |
+
"<400>",
|
| 417 |
+
"<401>",
|
| 418 |
+
"<402>",
|
| 419 |
+
"<403>",
|
| 420 |
+
"<404>",
|
| 421 |
+
"<405>",
|
| 422 |
+
"<406>",
|
| 423 |
+
"<407>",
|
| 424 |
+
"<408>",
|
| 425 |
+
"<409>",
|
| 426 |
+
"<410>",
|
| 427 |
+
"<411>",
|
| 428 |
+
"<412>",
|
| 429 |
+
"<413>",
|
| 430 |
+
"<414>",
|
| 431 |
+
"<415>",
|
| 432 |
+
"<416>",
|
| 433 |
+
"<417>",
|
| 434 |
+
"<418>",
|
| 435 |
+
"<419>",
|
| 436 |
+
"<420>",
|
| 437 |
+
"<421>",
|
| 438 |
+
"<422>",
|
| 439 |
+
"<423>",
|
| 440 |
+
"<424>",
|
| 441 |
+
"<425>",
|
| 442 |
+
"<426>",
|
| 443 |
+
"<427>",
|
| 444 |
+
"<428>",
|
| 445 |
+
"<429>",
|
| 446 |
+
"<430>",
|
| 447 |
+
"<431>",
|
| 448 |
+
"<432>",
|
| 449 |
+
"<433>",
|
| 450 |
+
"<434>",
|
| 451 |
+
"<435>",
|
| 452 |
+
"<436>",
|
| 453 |
+
"<437>",
|
| 454 |
+
"<438>",
|
| 455 |
+
"<439>",
|
| 456 |
+
"<440>",
|
| 457 |
+
"<441>",
|
| 458 |
+
"<442>",
|
| 459 |
+
"<443>",
|
| 460 |
+
"<444>",
|
| 461 |
+
"<445>",
|
| 462 |
+
"<446>",
|
| 463 |
+
"<447>",
|
| 464 |
+
"<448>",
|
| 465 |
+
"<449>",
|
| 466 |
+
"<450>",
|
| 467 |
+
"<451>",
|
| 468 |
+
"<452>",
|
| 469 |
+
"<453>",
|
| 470 |
+
"<454>",
|
| 471 |
+
"<455>",
|
| 472 |
+
"<456>",
|
| 473 |
+
"<457>",
|
| 474 |
+
"<458>",
|
| 475 |
+
"<459>",
|
| 476 |
+
"<460>",
|
| 477 |
+
"<461>",
|
| 478 |
+
"<462>",
|
| 479 |
+
"<463>",
|
| 480 |
+
"<464>",
|
| 481 |
+
"<465>",
|
| 482 |
+
"<466>",
|
| 483 |
+
"<467>",
|
| 484 |
+
"<468>",
|
| 485 |
+
"<469>",
|
| 486 |
+
"<470>",
|
| 487 |
+
"<471>",
|
| 488 |
+
"<472>",
|
| 489 |
+
"<473>",
|
| 490 |
+
"<474>",
|
| 491 |
+
"<475>",
|
| 492 |
+
"<476>",
|
| 493 |
+
"<477>",
|
| 494 |
+
"<478>",
|
| 495 |
+
"<479>",
|
| 496 |
+
"<480>",
|
| 497 |
+
"<481>",
|
| 498 |
+
"<482>",
|
| 499 |
+
"<483>",
|
| 500 |
+
"<484>",
|
| 501 |
+
"<485>",
|
| 502 |
+
"<486>",
|
| 503 |
+
"<487>",
|
| 504 |
+
"<488>",
|
| 505 |
+
"<489>",
|
| 506 |
+
"<490>",
|
| 507 |
+
"<491>",
|
| 508 |
+
"<492>",
|
| 509 |
+
"<493>",
|
| 510 |
+
"<494>",
|
| 511 |
+
"<495>",
|
| 512 |
+
"<496>",
|
| 513 |
+
"<497>",
|
| 514 |
+
"<498>",
|
| 515 |
+
"<499>",
|
| 516 |
+
"<500>",
|
| 517 |
+
"<501>",
|
| 518 |
+
"<502>",
|
| 519 |
+
"<503>",
|
| 520 |
+
"<504>",
|
| 521 |
+
"<505>",
|
| 522 |
+
"<506>",
|
| 523 |
+
"<507>",
|
| 524 |
+
"<508>",
|
| 525 |
+
"<509>",
|
| 526 |
+
"<510>",
|
| 527 |
+
"<511>",
|
| 528 |
+
"<512>",
|
| 529 |
+
"<513>",
|
| 530 |
+
"<514>",
|
| 531 |
+
"<515>",
|
| 532 |
+
"<516>",
|
| 533 |
+
"<517>",
|
| 534 |
+
"<518>",
|
| 535 |
+
"<519>",
|
| 536 |
+
"<520>",
|
| 537 |
+
"<521>",
|
| 538 |
+
"<522>",
|
| 539 |
+
"<523>",
|
| 540 |
+
"<524>",
|
| 541 |
+
"<525>",
|
| 542 |
+
"<526>",
|
| 543 |
+
"<527>",
|
| 544 |
+
"<528>",
|
| 545 |
+
"<529>",
|
| 546 |
+
"<530>",
|
| 547 |
+
"<531>",
|
| 548 |
+
"<532>",
|
| 549 |
+
"<533>",
|
| 550 |
+
"<534>",
|
| 551 |
+
"<535>",
|
| 552 |
+
"<536>",
|
| 553 |
+
"<537>",
|
| 554 |
+
"<538>",
|
| 555 |
+
"<539>",
|
| 556 |
+
"<540>",
|
| 557 |
+
"<541>",
|
| 558 |
+
"<542>",
|
| 559 |
+
"<543>",
|
| 560 |
+
"<544>",
|
| 561 |
+
"<545>",
|
| 562 |
+
"<546>",
|
| 563 |
+
"<547>",
|
| 564 |
+
"<548>",
|
| 565 |
+
"<549>",
|
| 566 |
+
"<550>",
|
| 567 |
+
"<551>",
|
| 568 |
+
"<552>",
|
| 569 |
+
"<553>",
|
| 570 |
+
"<554>",
|
| 571 |
+
"<555>",
|
| 572 |
+
"<556>",
|
| 573 |
+
"<557>",
|
| 574 |
+
"<558>",
|
| 575 |
+
"<559>",
|
| 576 |
+
"<560>",
|
| 577 |
+
"<561>",
|
| 578 |
+
"<562>",
|
| 579 |
+
"<563>",
|
| 580 |
+
"<564>",
|
| 581 |
+
"<565>",
|
| 582 |
+
"<566>",
|
| 583 |
+
"<567>",
|
| 584 |
+
"<568>",
|
| 585 |
+
"<569>",
|
| 586 |
+
"<570>",
|
| 587 |
+
"<571>",
|
| 588 |
+
"<572>",
|
| 589 |
+
"<573>",
|
| 590 |
+
"<574>",
|
| 591 |
+
"<575>",
|
| 592 |
+
"<576>",
|
| 593 |
+
"<577>",
|
| 594 |
+
"<578>",
|
| 595 |
+
"<579>",
|
| 596 |
+
"<580>",
|
| 597 |
+
"<581>",
|
| 598 |
+
"<582>",
|
| 599 |
+
"<583>",
|
| 600 |
+
"<584>",
|
| 601 |
+
"<585>",
|
| 602 |
+
"<586>",
|
| 603 |
+
"<587>",
|
| 604 |
+
"<588>",
|
| 605 |
+
"<589>",
|
| 606 |
+
"<590>",
|
| 607 |
+
"<591>",
|
| 608 |
+
"<592>",
|
| 609 |
+
"<593>",
|
| 610 |
+
"<594>",
|
| 611 |
+
"<595>",
|
| 612 |
+
"<596>",
|
| 613 |
+
"<597>",
|
| 614 |
+
"<598>",
|
| 615 |
+
"<599>",
|
| 616 |
+
"<600>",
|
| 617 |
+
"<601>",
|
| 618 |
+
"<602>",
|
| 619 |
+
"<603>",
|
| 620 |
+
"<604>",
|
| 621 |
+
"<605>",
|
| 622 |
+
"<606>",
|
| 623 |
+
"<607>",
|
| 624 |
+
"<608>",
|
| 625 |
+
"<609>",
|
| 626 |
+
"<610>",
|
| 627 |
+
"<611>",
|
| 628 |
+
"<612>",
|
| 629 |
+
"<613>",
|
| 630 |
+
"<614>",
|
| 631 |
+
"<615>",
|
| 632 |
+
"<616>",
|
| 633 |
+
"<617>",
|
| 634 |
+
"<618>",
|
| 635 |
+
"<619>",
|
| 636 |
+
"<620>",
|
| 637 |
+
"<621>",
|
| 638 |
+
"<622>",
|
| 639 |
+
"<623>",
|
| 640 |
+
"<624>",
|
| 641 |
+
"<625>",
|
| 642 |
+
"<626>",
|
| 643 |
+
"<627>",
|
| 644 |
+
"<628>",
|
| 645 |
+
"<629>",
|
| 646 |
+
"<630>",
|
| 647 |
+
"<631>",
|
| 648 |
+
"<632>",
|
| 649 |
+
"<633>",
|
| 650 |
+
"<634>",
|
| 651 |
+
"<635>",
|
| 652 |
+
"<636>",
|
| 653 |
+
"<637>",
|
| 654 |
+
"<638>",
|
| 655 |
+
"<639>",
|
| 656 |
+
"<640>",
|
| 657 |
+
"<641>",
|
| 658 |
+
"<642>",
|
| 659 |
+
"<643>",
|
| 660 |
+
"<644>",
|
| 661 |
+
"<645>",
|
| 662 |
+
"<646>",
|
| 663 |
+
"<647>",
|
| 664 |
+
"<648>",
|
| 665 |
+
"<649>",
|
| 666 |
+
"<650>",
|
| 667 |
+
"<651>",
|
| 668 |
+
"<652>",
|
| 669 |
+
"<653>",
|
| 670 |
+
"<654>",
|
| 671 |
+
"<655>",
|
| 672 |
+
"<656>",
|
| 673 |
+
"<657>",
|
| 674 |
+
"<658>",
|
| 675 |
+
"<659>",
|
| 676 |
+
"<660>",
|
| 677 |
+
"<661>",
|
| 678 |
+
"<662>",
|
| 679 |
+
"<663>",
|
| 680 |
+
"<664>",
|
| 681 |
+
"<665>",
|
| 682 |
+
"<666>",
|
| 683 |
+
"<667>",
|
| 684 |
+
"<668>",
|
| 685 |
+
"<669>",
|
| 686 |
+
"<670>",
|
| 687 |
+
"<671>",
|
| 688 |
+
"<672>",
|
| 689 |
+
"<673>",
|
| 690 |
+
"<674>",
|
| 691 |
+
"<675>",
|
| 692 |
+
"<676>",
|
| 693 |
+
"<677>",
|
| 694 |
+
"<678>",
|
| 695 |
+
"<679>",
|
| 696 |
+
"<680>",
|
| 697 |
+
"<681>",
|
| 698 |
+
"<682>",
|
| 699 |
+
"<683>",
|
| 700 |
+
"<684>",
|
| 701 |
+
"<685>",
|
| 702 |
+
"<686>",
|
| 703 |
+
"<687>",
|
| 704 |
+
"<688>",
|
| 705 |
+
"<689>",
|
| 706 |
+
"<690>",
|
| 707 |
+
"<691>",
|
| 708 |
+
"<692>",
|
| 709 |
+
"<693>",
|
| 710 |
+
"<694>",
|
| 711 |
+
"<695>",
|
| 712 |
+
"<696>",
|
| 713 |
+
"<697>",
|
| 714 |
+
"<698>",
|
| 715 |
+
"<699>",
|
| 716 |
+
"<700>",
|
| 717 |
+
"<701>",
|
| 718 |
+
"<702>",
|
| 719 |
+
"<703>",
|
| 720 |
+
"<704>",
|
| 721 |
+
"<705>",
|
| 722 |
+
"<706>",
|
| 723 |
+
"<707>",
|
| 724 |
+
"<708>",
|
| 725 |
+
"<709>",
|
| 726 |
+
"<710>",
|
| 727 |
+
"<711>",
|
| 728 |
+
"<712>",
|
| 729 |
+
"<713>",
|
| 730 |
+
"<714>",
|
| 731 |
+
"<715>",
|
| 732 |
+
"<716>",
|
| 733 |
+
"<717>",
|
| 734 |
+
"<718>",
|
| 735 |
+
"<719>",
|
| 736 |
+
"<720>",
|
| 737 |
+
"<721>",
|
| 738 |
+
"<722>",
|
| 739 |
+
"<723>",
|
| 740 |
+
"<724>",
|
| 741 |
+
"<725>",
|
| 742 |
+
"<726>",
|
| 743 |
+
"<727>",
|
| 744 |
+
"<728>",
|
| 745 |
+
"<729>",
|
| 746 |
+
"<730>",
|
| 747 |
+
"<731>",
|
| 748 |
+
"<732>",
|
| 749 |
+
"<733>",
|
| 750 |
+
"<734>",
|
| 751 |
+
"<735>",
|
| 752 |
+
"<736>",
|
| 753 |
+
"<737>",
|
| 754 |
+
"<738>",
|
| 755 |
+
"<739>",
|
| 756 |
+
"<740>",
|
| 757 |
+
"<741>",
|
| 758 |
+
"<742>",
|
| 759 |
+
"<743>",
|
| 760 |
+
"<744>",
|
| 761 |
+
"<745>",
|
| 762 |
+
"<746>",
|
| 763 |
+
"<747>",
|
| 764 |
+
"<748>",
|
| 765 |
+
"<749>",
|
| 766 |
+
"<750>",
|
| 767 |
+
"<751>",
|
| 768 |
+
"<752>",
|
| 769 |
+
"<753>",
|
| 770 |
+
"<754>",
|
| 771 |
+
"<755>",
|
| 772 |
+
"<756>",
|
| 773 |
+
"<757>",
|
| 774 |
+
"<758>",
|
| 775 |
+
"<759>",
|
| 776 |
+
"<760>",
|
| 777 |
+
"<761>",
|
| 778 |
+
"<762>",
|
| 779 |
+
"<763>",
|
| 780 |
+
"<764>",
|
| 781 |
+
"<765>",
|
| 782 |
+
"<766>",
|
| 783 |
+
"<767>",
|
| 784 |
+
"<768>",
|
| 785 |
+
"<769>",
|
| 786 |
+
"<770>",
|
| 787 |
+
"<771>",
|
| 788 |
+
"<772>",
|
| 789 |
+
"<773>",
|
| 790 |
+
"<774>",
|
| 791 |
+
"<775>",
|
| 792 |
+
"<776>",
|
| 793 |
+
"<777>",
|
| 794 |
+
"<778>",
|
| 795 |
+
"<779>",
|
| 796 |
+
"<780>",
|
| 797 |
+
"<781>",
|
| 798 |
+
"<782>",
|
| 799 |
+
"<783>",
|
| 800 |
+
"<784>",
|
| 801 |
+
"<785>",
|
| 802 |
+
"<786>",
|
| 803 |
+
"<787>",
|
| 804 |
+
"<788>",
|
| 805 |
+
"<789>",
|
| 806 |
+
"<790>",
|
| 807 |
+
"<791>",
|
| 808 |
+
"<792>",
|
| 809 |
+
"<793>",
|
| 810 |
+
"<794>",
|
| 811 |
+
"<795>",
|
| 812 |
+
"<796>",
|
| 813 |
+
"<797>",
|
| 814 |
+
"<798>",
|
| 815 |
+
"<799>",
|
| 816 |
+
"<800>",
|
| 817 |
+
"<801>",
|
| 818 |
+
"<802>",
|
| 819 |
+
"<803>",
|
| 820 |
+
"<804>",
|
| 821 |
+
"<805>",
|
| 822 |
+
"<806>",
|
| 823 |
+
"<807>",
|
| 824 |
+
"<808>",
|
| 825 |
+
"<809>",
|
| 826 |
+
"<810>",
|
| 827 |
+
"<811>",
|
| 828 |
+
"<812>",
|
| 829 |
+
"<813>",
|
| 830 |
+
"<814>",
|
| 831 |
+
"<815>",
|
| 832 |
+
"<816>",
|
| 833 |
+
"<817>",
|
| 834 |
+
"<818>",
|
| 835 |
+
"<819>",
|
| 836 |
+
"<820>",
|
| 837 |
+
"<821>",
|
| 838 |
+
"<822>",
|
| 839 |
+
"<823>",
|
| 840 |
+
"<824>",
|
| 841 |
+
"<825>",
|
| 842 |
+
"<826>",
|
| 843 |
+
"<827>",
|
| 844 |
+
"<828>",
|
| 845 |
+
"<829>",
|
| 846 |
+
"<830>",
|
| 847 |
+
"<831>",
|
| 848 |
+
"<832>",
|
| 849 |
+
"<833>",
|
| 850 |
+
"<834>",
|
| 851 |
+
"<835>",
|
| 852 |
+
"<836>",
|
| 853 |
+
"<837>",
|
| 854 |
+
"<838>",
|
| 855 |
+
"<839>",
|
| 856 |
+
"<840>",
|
| 857 |
+
"<841>",
|
| 858 |
+
"<842>",
|
| 859 |
+
"<843>",
|
| 860 |
+
"<844>",
|
| 861 |
+
"<845>",
|
| 862 |
+
"<846>",
|
| 863 |
+
"<847>",
|
| 864 |
+
"<848>",
|
| 865 |
+
"<849>",
|
| 866 |
+
"<850>",
|
| 867 |
+
"<851>",
|
| 868 |
+
"<852>",
|
| 869 |
+
"<853>",
|
| 870 |
+
"<854>",
|
| 871 |
+
"<855>",
|
| 872 |
+
"<856>",
|
| 873 |
+
"<857>",
|
| 874 |
+
"<858>",
|
| 875 |
+
"<859>",
|
| 876 |
+
"<860>",
|
| 877 |
+
"<861>",
|
| 878 |
+
"<862>",
|
| 879 |
+
"<863>",
|
| 880 |
+
"<864>",
|
| 881 |
+
"<865>",
|
| 882 |
+
"<866>",
|
| 883 |
+
"<867>",
|
| 884 |
+
"<868>",
|
| 885 |
+
"<869>",
|
| 886 |
+
"<870>",
|
| 887 |
+
"<871>",
|
| 888 |
+
"<872>",
|
| 889 |
+
"<873>",
|
| 890 |
+
"<874>",
|
| 891 |
+
"<875>",
|
| 892 |
+
"<876>",
|
| 893 |
+
"<877>",
|
| 894 |
+
"<878>",
|
| 895 |
+
"<879>",
|
| 896 |
+
"<880>",
|
| 897 |
+
"<881>",
|
| 898 |
+
"<882>",
|
| 899 |
+
"<883>",
|
| 900 |
+
"<884>",
|
| 901 |
+
"<885>",
|
| 902 |
+
"<886>",
|
| 903 |
+
"<887>",
|
| 904 |
+
"<888>",
|
| 905 |
+
"<889>",
|
| 906 |
+
"<890>",
|
| 907 |
+
"<891>",
|
| 908 |
+
"<892>",
|
| 909 |
+
"<893>",
|
| 910 |
+
"<894>",
|
| 911 |
+
"<895>",
|
| 912 |
+
"<896>",
|
| 913 |
+
"<897>",
|
| 914 |
+
"<898>",
|
| 915 |
+
"<899>",
|
| 916 |
+
"<900>",
|
| 917 |
+
"<901>",
|
| 918 |
+
"<902>",
|
| 919 |
+
"<903>",
|
| 920 |
+
"<904>",
|
| 921 |
+
"<905>",
|
| 922 |
+
"<906>",
|
| 923 |
+
"<907>",
|
| 924 |
+
"<908>",
|
| 925 |
+
"<909>",
|
| 926 |
+
"<910>",
|
| 927 |
+
"<911>",
|
| 928 |
+
"<912>",
|
| 929 |
+
"<913>",
|
| 930 |
+
"<914>",
|
| 931 |
+
"<915>",
|
| 932 |
+
"<916>",
|
| 933 |
+
"<917>",
|
| 934 |
+
"<918>",
|
| 935 |
+
"<919>",
|
| 936 |
+
"<920>",
|
| 937 |
+
"<921>",
|
| 938 |
+
"<922>",
|
| 939 |
+
"<923>",
|
| 940 |
+
"<924>",
|
| 941 |
+
"<925>",
|
| 942 |
+
"<926>",
|
| 943 |
+
"<927>",
|
| 944 |
+
"<928>",
|
| 945 |
+
"<929>",
|
| 946 |
+
"<930>",
|
| 947 |
+
"<931>",
|
| 948 |
+
"<932>",
|
| 949 |
+
"<933>",
|
| 950 |
+
"<934>",
|
| 951 |
+
"<935>",
|
| 952 |
+
"<936>",
|
| 953 |
+
"<937>",
|
| 954 |
+
"<938>",
|
| 955 |
+
"<939>",
|
| 956 |
+
"<940>",
|
| 957 |
+
"<941>",
|
| 958 |
+
"<942>",
|
| 959 |
+
"<943>",
|
| 960 |
+
"<944>",
|
| 961 |
+
"<945>",
|
| 962 |
+
"<946>",
|
| 963 |
+
"<947>",
|
| 964 |
+
"<948>",
|
| 965 |
+
"<949>",
|
| 966 |
+
"<950>",
|
| 967 |
+
"<951>",
|
| 968 |
+
"<952>",
|
| 969 |
+
"<953>",
|
| 970 |
+
"<954>",
|
| 971 |
+
"<955>",
|
| 972 |
+
"<956>",
|
| 973 |
+
"<957>",
|
| 974 |
+
"<958>",
|
| 975 |
+
"<959>",
|
| 976 |
+
"<960>",
|
| 977 |
+
"<961>",
|
| 978 |
+
"<962>",
|
| 979 |
+
"<963>",
|
| 980 |
+
"<964>",
|
| 981 |
+
"<965>",
|
| 982 |
+
"<966>",
|
| 983 |
+
"<967>",
|
| 984 |
+
"<968>",
|
| 985 |
+
"<969>",
|
| 986 |
+
"<970>",
|
| 987 |
+
"<971>",
|
| 988 |
+
"<972>",
|
| 989 |
+
"<973>",
|
| 990 |
+
"<974>",
|
| 991 |
+
"<975>",
|
| 992 |
+
"<976>",
|
| 993 |
+
"<977>",
|
| 994 |
+
"<978>",
|
| 995 |
+
"<979>",
|
| 996 |
+
"<980>",
|
| 997 |
+
"<981>",
|
| 998 |
+
"<982>",
|
| 999 |
+
"<983>",
|
| 1000 |
+
"<984>",
|
| 1001 |
+
"<985>",
|
| 1002 |
+
"<986>",
|
| 1003 |
+
"<987>",
|
| 1004 |
+
"<988>",
|
| 1005 |
+
"<989>",
|
| 1006 |
+
"<990>",
|
| 1007 |
+
"<991>",
|
| 1008 |
+
"<992>",
|
| 1009 |
+
"<993>",
|
| 1010 |
+
"<994>",
|
| 1011 |
+
"<995>",
|
| 1012 |
+
"<996>",
|
| 1013 |
+
"<997>",
|
| 1014 |
+
"<998>",
|
| 1015 |
+
"<999>"
|
| 1016 |
+
],
|
| 1017 |
+
"eos_token": {
|
| 1018 |
+
"content": "<|im_end|>",
|
| 1019 |
+
"lstrip": false,
|
| 1020 |
+
"normalized": false,
|
| 1021 |
+
"rstrip": false,
|
| 1022 |
+
"single_word": false
|
| 1023 |
+
},
|
| 1024 |
+
"pad_token": {
|
| 1025 |
+
"content": "<|endoftext|>",
|
| 1026 |
+
"lstrip": false,
|
| 1027 |
+
"normalized": false,
|
| 1028 |
+
"rstrip": false,
|
| 1029 |
+
"single_word": false
|
| 1030 |
+
}
|
| 1031 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/global_step_50/actor/huggingface/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 2048,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
+
"max_window_layers": 70,
|
| 14 |
+
"model_type": "qwen2_5_vl",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_hidden_layers": 36,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"depth": 32,
|
| 39 |
+
"fullatt_block_indexes": [
|
| 40 |
+
7,
|
| 41 |
+
15,
|
| 42 |
+
23,
|
| 43 |
+
31
|
| 44 |
+
],
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 1280,
|
| 47 |
+
"in_channels": 3,
|
| 48 |
+
"in_chans": 3,
|
| 49 |
+
"intermediate_size": 3420,
|
| 50 |
+
"model_type": "qwen2_5_vl",
|
| 51 |
+
"num_heads": 16,
|
| 52 |
+
"out_hidden_size": 2048,
|
| 53 |
+
"patch_size": 14,
|
| 54 |
+
"spatial_merge_size": 2,
|
| 55 |
+
"spatial_patch_size": 14,
|
| 56 |
+
"temporal_patch_size": 2,
|
| 57 |
+
"tokens_per_second": 2,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"window_size": 112
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652,
|
| 63 |
+
"vision_token_id": 151654,
|
| 64 |
+
"vocab_size": 151936
|
| 65 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.51.3",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3446d47be05c711fbdcd3b5a1de74f9507f0f382f57443f1b6cca49cf5471561
|
| 3 |
+
size 4977621880
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d7bf4f612a8ba55ee6774440b361c427997eb4101ebd6d6e80266a116e7bbdc
|
| 3 |
+
size 3154046120
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8131575808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.norm.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.26.norm2.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.27.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.27.norm1.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.27.norm2.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 726 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 732 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 738 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 739 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"visual.blocks.30.norm2.weight": "model-00002-of-00002.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 744 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 750 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 751 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 756 |
+
"visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 762 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 763 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 768 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 774 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 775 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 780 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 786 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 792 |
+
"visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 798 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 799 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 804 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 810 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 811 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 816 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 822 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 823 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 825 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 827 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.bias": "model-00002-of-00002.safetensors",
|
| 829 |
+
"visual.merger.mlp.2.weight": "model-00002-of-00002.safetensors",
|
| 830 |
+
"visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors"
|
| 831 |
+
}
|
| 832 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 2007040,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 12544,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 2007040,
|
| 26 |
+
"shortest_edge": 12544
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/special_tokens_map.json
ADDED
|
@@ -0,0 +1,1031 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<0>",
|
| 17 |
+
"<1>",
|
| 18 |
+
"<2>",
|
| 19 |
+
"<3>",
|
| 20 |
+
"<4>",
|
| 21 |
+
"<5>",
|
| 22 |
+
"<6>",
|
| 23 |
+
"<7>",
|
| 24 |
+
"<8>",
|
| 25 |
+
"<9>",
|
| 26 |
+
"<10>",
|
| 27 |
+
"<11>",
|
| 28 |
+
"<12>",
|
| 29 |
+
"<13>",
|
| 30 |
+
"<14>",
|
| 31 |
+
"<15>",
|
| 32 |
+
"<16>",
|
| 33 |
+
"<17>",
|
| 34 |
+
"<18>",
|
| 35 |
+
"<19>",
|
| 36 |
+
"<20>",
|
| 37 |
+
"<21>",
|
| 38 |
+
"<22>",
|
| 39 |
+
"<23>",
|
| 40 |
+
"<24>",
|
| 41 |
+
"<25>",
|
| 42 |
+
"<26>",
|
| 43 |
+
"<27>",
|
| 44 |
+
"<28>",
|
| 45 |
+
"<29>",
|
| 46 |
+
"<30>",
|
| 47 |
+
"<31>",
|
| 48 |
+
"<32>",
|
| 49 |
+
"<33>",
|
| 50 |
+
"<34>",
|
| 51 |
+
"<35>",
|
| 52 |
+
"<36>",
|
| 53 |
+
"<37>",
|
| 54 |
+
"<38>",
|
| 55 |
+
"<39>",
|
| 56 |
+
"<40>",
|
| 57 |
+
"<41>",
|
| 58 |
+
"<42>",
|
| 59 |
+
"<43>",
|
| 60 |
+
"<44>",
|
| 61 |
+
"<45>",
|
| 62 |
+
"<46>",
|
| 63 |
+
"<47>",
|
| 64 |
+
"<48>",
|
| 65 |
+
"<49>",
|
| 66 |
+
"<50>",
|
| 67 |
+
"<51>",
|
| 68 |
+
"<52>",
|
| 69 |
+
"<53>",
|
| 70 |
+
"<54>",
|
| 71 |
+
"<55>",
|
| 72 |
+
"<56>",
|
| 73 |
+
"<57>",
|
| 74 |
+
"<58>",
|
| 75 |
+
"<59>",
|
| 76 |
+
"<60>",
|
| 77 |
+
"<61>",
|
| 78 |
+
"<62>",
|
| 79 |
+
"<63>",
|
| 80 |
+
"<64>",
|
| 81 |
+
"<65>",
|
| 82 |
+
"<66>",
|
| 83 |
+
"<67>",
|
| 84 |
+
"<68>",
|
| 85 |
+
"<69>",
|
| 86 |
+
"<70>",
|
| 87 |
+
"<71>",
|
| 88 |
+
"<72>",
|
| 89 |
+
"<73>",
|
| 90 |
+
"<74>",
|
| 91 |
+
"<75>",
|
| 92 |
+
"<76>",
|
| 93 |
+
"<77>",
|
| 94 |
+
"<78>",
|
| 95 |
+
"<79>",
|
| 96 |
+
"<80>",
|
| 97 |
+
"<81>",
|
| 98 |
+
"<82>",
|
| 99 |
+
"<83>",
|
| 100 |
+
"<84>",
|
| 101 |
+
"<85>",
|
| 102 |
+
"<86>",
|
| 103 |
+
"<87>",
|
| 104 |
+
"<88>",
|
| 105 |
+
"<89>",
|
| 106 |
+
"<90>",
|
| 107 |
+
"<91>",
|
| 108 |
+
"<92>",
|
| 109 |
+
"<93>",
|
| 110 |
+
"<94>",
|
| 111 |
+
"<95>",
|
| 112 |
+
"<96>",
|
| 113 |
+
"<97>",
|
| 114 |
+
"<98>",
|
| 115 |
+
"<99>",
|
| 116 |
+
"<100>",
|
| 117 |
+
"<101>",
|
| 118 |
+
"<102>",
|
| 119 |
+
"<103>",
|
| 120 |
+
"<104>",
|
| 121 |
+
"<105>",
|
| 122 |
+
"<106>",
|
| 123 |
+
"<107>",
|
| 124 |
+
"<108>",
|
| 125 |
+
"<109>",
|
| 126 |
+
"<110>",
|
| 127 |
+
"<111>",
|
| 128 |
+
"<112>",
|
| 129 |
+
"<113>",
|
| 130 |
+
"<114>",
|
| 131 |
+
"<115>",
|
| 132 |
+
"<116>",
|
| 133 |
+
"<117>",
|
| 134 |
+
"<118>",
|
| 135 |
+
"<119>",
|
| 136 |
+
"<120>",
|
| 137 |
+
"<121>",
|
| 138 |
+
"<122>",
|
| 139 |
+
"<123>",
|
| 140 |
+
"<124>",
|
| 141 |
+
"<125>",
|
| 142 |
+
"<126>",
|
| 143 |
+
"<127>",
|
| 144 |
+
"<128>",
|
| 145 |
+
"<129>",
|
| 146 |
+
"<130>",
|
| 147 |
+
"<131>",
|
| 148 |
+
"<132>",
|
| 149 |
+
"<133>",
|
| 150 |
+
"<134>",
|
| 151 |
+
"<135>",
|
| 152 |
+
"<136>",
|
| 153 |
+
"<137>",
|
| 154 |
+
"<138>",
|
| 155 |
+
"<139>",
|
| 156 |
+
"<140>",
|
| 157 |
+
"<141>",
|
| 158 |
+
"<142>",
|
| 159 |
+
"<143>",
|
| 160 |
+
"<144>",
|
| 161 |
+
"<145>",
|
| 162 |
+
"<146>",
|
| 163 |
+
"<147>",
|
| 164 |
+
"<148>",
|
| 165 |
+
"<149>",
|
| 166 |
+
"<150>",
|
| 167 |
+
"<151>",
|
| 168 |
+
"<152>",
|
| 169 |
+
"<153>",
|
| 170 |
+
"<154>",
|
| 171 |
+
"<155>",
|
| 172 |
+
"<156>",
|
| 173 |
+
"<157>",
|
| 174 |
+
"<158>",
|
| 175 |
+
"<159>",
|
| 176 |
+
"<160>",
|
| 177 |
+
"<161>",
|
| 178 |
+
"<162>",
|
| 179 |
+
"<163>",
|
| 180 |
+
"<164>",
|
| 181 |
+
"<165>",
|
| 182 |
+
"<166>",
|
| 183 |
+
"<167>",
|
| 184 |
+
"<168>",
|
| 185 |
+
"<169>",
|
| 186 |
+
"<170>",
|
| 187 |
+
"<171>",
|
| 188 |
+
"<172>",
|
| 189 |
+
"<173>",
|
| 190 |
+
"<174>",
|
| 191 |
+
"<175>",
|
| 192 |
+
"<176>",
|
| 193 |
+
"<177>",
|
| 194 |
+
"<178>",
|
| 195 |
+
"<179>",
|
| 196 |
+
"<180>",
|
| 197 |
+
"<181>",
|
| 198 |
+
"<182>",
|
| 199 |
+
"<183>",
|
| 200 |
+
"<184>",
|
| 201 |
+
"<185>",
|
| 202 |
+
"<186>",
|
| 203 |
+
"<187>",
|
| 204 |
+
"<188>",
|
| 205 |
+
"<189>",
|
| 206 |
+
"<190>",
|
| 207 |
+
"<191>",
|
| 208 |
+
"<192>",
|
| 209 |
+
"<193>",
|
| 210 |
+
"<194>",
|
| 211 |
+
"<195>",
|
| 212 |
+
"<196>",
|
| 213 |
+
"<197>",
|
| 214 |
+
"<198>",
|
| 215 |
+
"<199>",
|
| 216 |
+
"<200>",
|
| 217 |
+
"<201>",
|
| 218 |
+
"<202>",
|
| 219 |
+
"<203>",
|
| 220 |
+
"<204>",
|
| 221 |
+
"<205>",
|
| 222 |
+
"<206>",
|
| 223 |
+
"<207>",
|
| 224 |
+
"<208>",
|
| 225 |
+
"<209>",
|
| 226 |
+
"<210>",
|
| 227 |
+
"<211>",
|
| 228 |
+
"<212>",
|
| 229 |
+
"<213>",
|
| 230 |
+
"<214>",
|
| 231 |
+
"<215>",
|
| 232 |
+
"<216>",
|
| 233 |
+
"<217>",
|
| 234 |
+
"<218>",
|
| 235 |
+
"<219>",
|
| 236 |
+
"<220>",
|
| 237 |
+
"<221>",
|
| 238 |
+
"<222>",
|
| 239 |
+
"<223>",
|
| 240 |
+
"<224>",
|
| 241 |
+
"<225>",
|
| 242 |
+
"<226>",
|
| 243 |
+
"<227>",
|
| 244 |
+
"<228>",
|
| 245 |
+
"<229>",
|
| 246 |
+
"<230>",
|
| 247 |
+
"<231>",
|
| 248 |
+
"<232>",
|
| 249 |
+
"<233>",
|
| 250 |
+
"<234>",
|
| 251 |
+
"<235>",
|
| 252 |
+
"<236>",
|
| 253 |
+
"<237>",
|
| 254 |
+
"<238>",
|
| 255 |
+
"<239>",
|
| 256 |
+
"<240>",
|
| 257 |
+
"<241>",
|
| 258 |
+
"<242>",
|
| 259 |
+
"<243>",
|
| 260 |
+
"<244>",
|
| 261 |
+
"<245>",
|
| 262 |
+
"<246>",
|
| 263 |
+
"<247>",
|
| 264 |
+
"<248>",
|
| 265 |
+
"<249>",
|
| 266 |
+
"<250>",
|
| 267 |
+
"<251>",
|
| 268 |
+
"<252>",
|
| 269 |
+
"<253>",
|
| 270 |
+
"<254>",
|
| 271 |
+
"<255>",
|
| 272 |
+
"<256>",
|
| 273 |
+
"<257>",
|
| 274 |
+
"<258>",
|
| 275 |
+
"<259>",
|
| 276 |
+
"<260>",
|
| 277 |
+
"<261>",
|
| 278 |
+
"<262>",
|
| 279 |
+
"<263>",
|
| 280 |
+
"<264>",
|
| 281 |
+
"<265>",
|
| 282 |
+
"<266>",
|
| 283 |
+
"<267>",
|
| 284 |
+
"<268>",
|
| 285 |
+
"<269>",
|
| 286 |
+
"<270>",
|
| 287 |
+
"<271>",
|
| 288 |
+
"<272>",
|
| 289 |
+
"<273>",
|
| 290 |
+
"<274>",
|
| 291 |
+
"<275>",
|
| 292 |
+
"<276>",
|
| 293 |
+
"<277>",
|
| 294 |
+
"<278>",
|
| 295 |
+
"<279>",
|
| 296 |
+
"<280>",
|
| 297 |
+
"<281>",
|
| 298 |
+
"<282>",
|
| 299 |
+
"<283>",
|
| 300 |
+
"<284>",
|
| 301 |
+
"<285>",
|
| 302 |
+
"<286>",
|
| 303 |
+
"<287>",
|
| 304 |
+
"<288>",
|
| 305 |
+
"<289>",
|
| 306 |
+
"<290>",
|
| 307 |
+
"<291>",
|
| 308 |
+
"<292>",
|
| 309 |
+
"<293>",
|
| 310 |
+
"<294>",
|
| 311 |
+
"<295>",
|
| 312 |
+
"<296>",
|
| 313 |
+
"<297>",
|
| 314 |
+
"<298>",
|
| 315 |
+
"<299>",
|
| 316 |
+
"<300>",
|
| 317 |
+
"<301>",
|
| 318 |
+
"<302>",
|
| 319 |
+
"<303>",
|
| 320 |
+
"<304>",
|
| 321 |
+
"<305>",
|
| 322 |
+
"<306>",
|
| 323 |
+
"<307>",
|
| 324 |
+
"<308>",
|
| 325 |
+
"<309>",
|
| 326 |
+
"<310>",
|
| 327 |
+
"<311>",
|
| 328 |
+
"<312>",
|
| 329 |
+
"<313>",
|
| 330 |
+
"<314>",
|
| 331 |
+
"<315>",
|
| 332 |
+
"<316>",
|
| 333 |
+
"<317>",
|
| 334 |
+
"<318>",
|
| 335 |
+
"<319>",
|
| 336 |
+
"<320>",
|
| 337 |
+
"<321>",
|
| 338 |
+
"<322>",
|
| 339 |
+
"<323>",
|
| 340 |
+
"<324>",
|
| 341 |
+
"<325>",
|
| 342 |
+
"<326>",
|
| 343 |
+
"<327>",
|
| 344 |
+
"<328>",
|
| 345 |
+
"<329>",
|
| 346 |
+
"<330>",
|
| 347 |
+
"<331>",
|
| 348 |
+
"<332>",
|
| 349 |
+
"<333>",
|
| 350 |
+
"<334>",
|
| 351 |
+
"<335>",
|
| 352 |
+
"<336>",
|
| 353 |
+
"<337>",
|
| 354 |
+
"<338>",
|
| 355 |
+
"<339>",
|
| 356 |
+
"<340>",
|
| 357 |
+
"<341>",
|
| 358 |
+
"<342>",
|
| 359 |
+
"<343>",
|
| 360 |
+
"<344>",
|
| 361 |
+
"<345>",
|
| 362 |
+
"<346>",
|
| 363 |
+
"<347>",
|
| 364 |
+
"<348>",
|
| 365 |
+
"<349>",
|
| 366 |
+
"<350>",
|
| 367 |
+
"<351>",
|
| 368 |
+
"<352>",
|
| 369 |
+
"<353>",
|
| 370 |
+
"<354>",
|
| 371 |
+
"<355>",
|
| 372 |
+
"<356>",
|
| 373 |
+
"<357>",
|
| 374 |
+
"<358>",
|
| 375 |
+
"<359>",
|
| 376 |
+
"<360>",
|
| 377 |
+
"<361>",
|
| 378 |
+
"<362>",
|
| 379 |
+
"<363>",
|
| 380 |
+
"<364>",
|
| 381 |
+
"<365>",
|
| 382 |
+
"<366>",
|
| 383 |
+
"<367>",
|
| 384 |
+
"<368>",
|
| 385 |
+
"<369>",
|
| 386 |
+
"<370>",
|
| 387 |
+
"<371>",
|
| 388 |
+
"<372>",
|
| 389 |
+
"<373>",
|
| 390 |
+
"<374>",
|
| 391 |
+
"<375>",
|
| 392 |
+
"<376>",
|
| 393 |
+
"<377>",
|
| 394 |
+
"<378>",
|
| 395 |
+
"<379>",
|
| 396 |
+
"<380>",
|
| 397 |
+
"<381>",
|
| 398 |
+
"<382>",
|
| 399 |
+
"<383>",
|
| 400 |
+
"<384>",
|
| 401 |
+
"<385>",
|
| 402 |
+
"<386>",
|
| 403 |
+
"<387>",
|
| 404 |
+
"<388>",
|
| 405 |
+
"<389>",
|
| 406 |
+
"<390>",
|
| 407 |
+
"<391>",
|
| 408 |
+
"<392>",
|
| 409 |
+
"<393>",
|
| 410 |
+
"<394>",
|
| 411 |
+
"<395>",
|
| 412 |
+
"<396>",
|
| 413 |
+
"<397>",
|
| 414 |
+
"<398>",
|
| 415 |
+
"<399>",
|
| 416 |
+
"<400>",
|
| 417 |
+
"<401>",
|
| 418 |
+
"<402>",
|
| 419 |
+
"<403>",
|
| 420 |
+
"<404>",
|
| 421 |
+
"<405>",
|
| 422 |
+
"<406>",
|
| 423 |
+
"<407>",
|
| 424 |
+
"<408>",
|
| 425 |
+
"<409>",
|
| 426 |
+
"<410>",
|
| 427 |
+
"<411>",
|
| 428 |
+
"<412>",
|
| 429 |
+
"<413>",
|
| 430 |
+
"<414>",
|
| 431 |
+
"<415>",
|
| 432 |
+
"<416>",
|
| 433 |
+
"<417>",
|
| 434 |
+
"<418>",
|
| 435 |
+
"<419>",
|
| 436 |
+
"<420>",
|
| 437 |
+
"<421>",
|
| 438 |
+
"<422>",
|
| 439 |
+
"<423>",
|
| 440 |
+
"<424>",
|
| 441 |
+
"<425>",
|
| 442 |
+
"<426>",
|
| 443 |
+
"<427>",
|
| 444 |
+
"<428>",
|
| 445 |
+
"<429>",
|
| 446 |
+
"<430>",
|
| 447 |
+
"<431>",
|
| 448 |
+
"<432>",
|
| 449 |
+
"<433>",
|
| 450 |
+
"<434>",
|
| 451 |
+
"<435>",
|
| 452 |
+
"<436>",
|
| 453 |
+
"<437>",
|
| 454 |
+
"<438>",
|
| 455 |
+
"<439>",
|
| 456 |
+
"<440>",
|
| 457 |
+
"<441>",
|
| 458 |
+
"<442>",
|
| 459 |
+
"<443>",
|
| 460 |
+
"<444>",
|
| 461 |
+
"<445>",
|
| 462 |
+
"<446>",
|
| 463 |
+
"<447>",
|
| 464 |
+
"<448>",
|
| 465 |
+
"<449>",
|
| 466 |
+
"<450>",
|
| 467 |
+
"<451>",
|
| 468 |
+
"<452>",
|
| 469 |
+
"<453>",
|
| 470 |
+
"<454>",
|
| 471 |
+
"<455>",
|
| 472 |
+
"<456>",
|
| 473 |
+
"<457>",
|
| 474 |
+
"<458>",
|
| 475 |
+
"<459>",
|
| 476 |
+
"<460>",
|
| 477 |
+
"<461>",
|
| 478 |
+
"<462>",
|
| 479 |
+
"<463>",
|
| 480 |
+
"<464>",
|
| 481 |
+
"<465>",
|
| 482 |
+
"<466>",
|
| 483 |
+
"<467>",
|
| 484 |
+
"<468>",
|
| 485 |
+
"<469>",
|
| 486 |
+
"<470>",
|
| 487 |
+
"<471>",
|
| 488 |
+
"<472>",
|
| 489 |
+
"<473>",
|
| 490 |
+
"<474>",
|
| 491 |
+
"<475>",
|
| 492 |
+
"<476>",
|
| 493 |
+
"<477>",
|
| 494 |
+
"<478>",
|
| 495 |
+
"<479>",
|
| 496 |
+
"<480>",
|
| 497 |
+
"<481>",
|
| 498 |
+
"<482>",
|
| 499 |
+
"<483>",
|
| 500 |
+
"<484>",
|
| 501 |
+
"<485>",
|
| 502 |
+
"<486>",
|
| 503 |
+
"<487>",
|
| 504 |
+
"<488>",
|
| 505 |
+
"<489>",
|
| 506 |
+
"<490>",
|
| 507 |
+
"<491>",
|
| 508 |
+
"<492>",
|
| 509 |
+
"<493>",
|
| 510 |
+
"<494>",
|
| 511 |
+
"<495>",
|
| 512 |
+
"<496>",
|
| 513 |
+
"<497>",
|
| 514 |
+
"<498>",
|
| 515 |
+
"<499>",
|
| 516 |
+
"<500>",
|
| 517 |
+
"<501>",
|
| 518 |
+
"<502>",
|
| 519 |
+
"<503>",
|
| 520 |
+
"<504>",
|
| 521 |
+
"<505>",
|
| 522 |
+
"<506>",
|
| 523 |
+
"<507>",
|
| 524 |
+
"<508>",
|
| 525 |
+
"<509>",
|
| 526 |
+
"<510>",
|
| 527 |
+
"<511>",
|
| 528 |
+
"<512>",
|
| 529 |
+
"<513>",
|
| 530 |
+
"<514>",
|
| 531 |
+
"<515>",
|
| 532 |
+
"<516>",
|
| 533 |
+
"<517>",
|
| 534 |
+
"<518>",
|
| 535 |
+
"<519>",
|
| 536 |
+
"<520>",
|
| 537 |
+
"<521>",
|
| 538 |
+
"<522>",
|
| 539 |
+
"<523>",
|
| 540 |
+
"<524>",
|
| 541 |
+
"<525>",
|
| 542 |
+
"<526>",
|
| 543 |
+
"<527>",
|
| 544 |
+
"<528>",
|
| 545 |
+
"<529>",
|
| 546 |
+
"<530>",
|
| 547 |
+
"<531>",
|
| 548 |
+
"<532>",
|
| 549 |
+
"<533>",
|
| 550 |
+
"<534>",
|
| 551 |
+
"<535>",
|
| 552 |
+
"<536>",
|
| 553 |
+
"<537>",
|
| 554 |
+
"<538>",
|
| 555 |
+
"<539>",
|
| 556 |
+
"<540>",
|
| 557 |
+
"<541>",
|
| 558 |
+
"<542>",
|
| 559 |
+
"<543>",
|
| 560 |
+
"<544>",
|
| 561 |
+
"<545>",
|
| 562 |
+
"<546>",
|
| 563 |
+
"<547>",
|
| 564 |
+
"<548>",
|
| 565 |
+
"<549>",
|
| 566 |
+
"<550>",
|
| 567 |
+
"<551>",
|
| 568 |
+
"<552>",
|
| 569 |
+
"<553>",
|
| 570 |
+
"<554>",
|
| 571 |
+
"<555>",
|
| 572 |
+
"<556>",
|
| 573 |
+
"<557>",
|
| 574 |
+
"<558>",
|
| 575 |
+
"<559>",
|
| 576 |
+
"<560>",
|
| 577 |
+
"<561>",
|
| 578 |
+
"<562>",
|
| 579 |
+
"<563>",
|
| 580 |
+
"<564>",
|
| 581 |
+
"<565>",
|
| 582 |
+
"<566>",
|
| 583 |
+
"<567>",
|
| 584 |
+
"<568>",
|
| 585 |
+
"<569>",
|
| 586 |
+
"<570>",
|
| 587 |
+
"<571>",
|
| 588 |
+
"<572>",
|
| 589 |
+
"<573>",
|
| 590 |
+
"<574>",
|
| 591 |
+
"<575>",
|
| 592 |
+
"<576>",
|
| 593 |
+
"<577>",
|
| 594 |
+
"<578>",
|
| 595 |
+
"<579>",
|
| 596 |
+
"<580>",
|
| 597 |
+
"<581>",
|
| 598 |
+
"<582>",
|
| 599 |
+
"<583>",
|
| 600 |
+
"<584>",
|
| 601 |
+
"<585>",
|
| 602 |
+
"<586>",
|
| 603 |
+
"<587>",
|
| 604 |
+
"<588>",
|
| 605 |
+
"<589>",
|
| 606 |
+
"<590>",
|
| 607 |
+
"<591>",
|
| 608 |
+
"<592>",
|
| 609 |
+
"<593>",
|
| 610 |
+
"<594>",
|
| 611 |
+
"<595>",
|
| 612 |
+
"<596>",
|
| 613 |
+
"<597>",
|
| 614 |
+
"<598>",
|
| 615 |
+
"<599>",
|
| 616 |
+
"<600>",
|
| 617 |
+
"<601>",
|
| 618 |
+
"<602>",
|
| 619 |
+
"<603>",
|
| 620 |
+
"<604>",
|
| 621 |
+
"<605>",
|
| 622 |
+
"<606>",
|
| 623 |
+
"<607>",
|
| 624 |
+
"<608>",
|
| 625 |
+
"<609>",
|
| 626 |
+
"<610>",
|
| 627 |
+
"<611>",
|
| 628 |
+
"<612>",
|
| 629 |
+
"<613>",
|
| 630 |
+
"<614>",
|
| 631 |
+
"<615>",
|
| 632 |
+
"<616>",
|
| 633 |
+
"<617>",
|
| 634 |
+
"<618>",
|
| 635 |
+
"<619>",
|
| 636 |
+
"<620>",
|
| 637 |
+
"<621>",
|
| 638 |
+
"<622>",
|
| 639 |
+
"<623>",
|
| 640 |
+
"<624>",
|
| 641 |
+
"<625>",
|
| 642 |
+
"<626>",
|
| 643 |
+
"<627>",
|
| 644 |
+
"<628>",
|
| 645 |
+
"<629>",
|
| 646 |
+
"<630>",
|
| 647 |
+
"<631>",
|
| 648 |
+
"<632>",
|
| 649 |
+
"<633>",
|
| 650 |
+
"<634>",
|
| 651 |
+
"<635>",
|
| 652 |
+
"<636>",
|
| 653 |
+
"<637>",
|
| 654 |
+
"<638>",
|
| 655 |
+
"<639>",
|
| 656 |
+
"<640>",
|
| 657 |
+
"<641>",
|
| 658 |
+
"<642>",
|
| 659 |
+
"<643>",
|
| 660 |
+
"<644>",
|
| 661 |
+
"<645>",
|
| 662 |
+
"<646>",
|
| 663 |
+
"<647>",
|
| 664 |
+
"<648>",
|
| 665 |
+
"<649>",
|
| 666 |
+
"<650>",
|
| 667 |
+
"<651>",
|
| 668 |
+
"<652>",
|
| 669 |
+
"<653>",
|
| 670 |
+
"<654>",
|
| 671 |
+
"<655>",
|
| 672 |
+
"<656>",
|
| 673 |
+
"<657>",
|
| 674 |
+
"<658>",
|
| 675 |
+
"<659>",
|
| 676 |
+
"<660>",
|
| 677 |
+
"<661>",
|
| 678 |
+
"<662>",
|
| 679 |
+
"<663>",
|
| 680 |
+
"<664>",
|
| 681 |
+
"<665>",
|
| 682 |
+
"<666>",
|
| 683 |
+
"<667>",
|
| 684 |
+
"<668>",
|
| 685 |
+
"<669>",
|
| 686 |
+
"<670>",
|
| 687 |
+
"<671>",
|
| 688 |
+
"<672>",
|
| 689 |
+
"<673>",
|
| 690 |
+
"<674>",
|
| 691 |
+
"<675>",
|
| 692 |
+
"<676>",
|
| 693 |
+
"<677>",
|
| 694 |
+
"<678>",
|
| 695 |
+
"<679>",
|
| 696 |
+
"<680>",
|
| 697 |
+
"<681>",
|
| 698 |
+
"<682>",
|
| 699 |
+
"<683>",
|
| 700 |
+
"<684>",
|
| 701 |
+
"<685>",
|
| 702 |
+
"<686>",
|
| 703 |
+
"<687>",
|
| 704 |
+
"<688>",
|
| 705 |
+
"<689>",
|
| 706 |
+
"<690>",
|
| 707 |
+
"<691>",
|
| 708 |
+
"<692>",
|
| 709 |
+
"<693>",
|
| 710 |
+
"<694>",
|
| 711 |
+
"<695>",
|
| 712 |
+
"<696>",
|
| 713 |
+
"<697>",
|
| 714 |
+
"<698>",
|
| 715 |
+
"<699>",
|
| 716 |
+
"<700>",
|
| 717 |
+
"<701>",
|
| 718 |
+
"<702>",
|
| 719 |
+
"<703>",
|
| 720 |
+
"<704>",
|
| 721 |
+
"<705>",
|
| 722 |
+
"<706>",
|
| 723 |
+
"<707>",
|
| 724 |
+
"<708>",
|
| 725 |
+
"<709>",
|
| 726 |
+
"<710>",
|
| 727 |
+
"<711>",
|
| 728 |
+
"<712>",
|
| 729 |
+
"<713>",
|
| 730 |
+
"<714>",
|
| 731 |
+
"<715>",
|
| 732 |
+
"<716>",
|
| 733 |
+
"<717>",
|
| 734 |
+
"<718>",
|
| 735 |
+
"<719>",
|
| 736 |
+
"<720>",
|
| 737 |
+
"<721>",
|
| 738 |
+
"<722>",
|
| 739 |
+
"<723>",
|
| 740 |
+
"<724>",
|
| 741 |
+
"<725>",
|
| 742 |
+
"<726>",
|
| 743 |
+
"<727>",
|
| 744 |
+
"<728>",
|
| 745 |
+
"<729>",
|
| 746 |
+
"<730>",
|
| 747 |
+
"<731>",
|
| 748 |
+
"<732>",
|
| 749 |
+
"<733>",
|
| 750 |
+
"<734>",
|
| 751 |
+
"<735>",
|
| 752 |
+
"<736>",
|
| 753 |
+
"<737>",
|
| 754 |
+
"<738>",
|
| 755 |
+
"<739>",
|
| 756 |
+
"<740>",
|
| 757 |
+
"<741>",
|
| 758 |
+
"<742>",
|
| 759 |
+
"<743>",
|
| 760 |
+
"<744>",
|
| 761 |
+
"<745>",
|
| 762 |
+
"<746>",
|
| 763 |
+
"<747>",
|
| 764 |
+
"<748>",
|
| 765 |
+
"<749>",
|
| 766 |
+
"<750>",
|
| 767 |
+
"<751>",
|
| 768 |
+
"<752>",
|
| 769 |
+
"<753>",
|
| 770 |
+
"<754>",
|
| 771 |
+
"<755>",
|
| 772 |
+
"<756>",
|
| 773 |
+
"<757>",
|
| 774 |
+
"<758>",
|
| 775 |
+
"<759>",
|
| 776 |
+
"<760>",
|
| 777 |
+
"<761>",
|
| 778 |
+
"<762>",
|
| 779 |
+
"<763>",
|
| 780 |
+
"<764>",
|
| 781 |
+
"<765>",
|
| 782 |
+
"<766>",
|
| 783 |
+
"<767>",
|
| 784 |
+
"<768>",
|
| 785 |
+
"<769>",
|
| 786 |
+
"<770>",
|
| 787 |
+
"<771>",
|
| 788 |
+
"<772>",
|
| 789 |
+
"<773>",
|
| 790 |
+
"<774>",
|
| 791 |
+
"<775>",
|
| 792 |
+
"<776>",
|
| 793 |
+
"<777>",
|
| 794 |
+
"<778>",
|
| 795 |
+
"<779>",
|
| 796 |
+
"<780>",
|
| 797 |
+
"<781>",
|
| 798 |
+
"<782>",
|
| 799 |
+
"<783>",
|
| 800 |
+
"<784>",
|
| 801 |
+
"<785>",
|
| 802 |
+
"<786>",
|
| 803 |
+
"<787>",
|
| 804 |
+
"<788>",
|
| 805 |
+
"<789>",
|
| 806 |
+
"<790>",
|
| 807 |
+
"<791>",
|
| 808 |
+
"<792>",
|
| 809 |
+
"<793>",
|
| 810 |
+
"<794>",
|
| 811 |
+
"<795>",
|
| 812 |
+
"<796>",
|
| 813 |
+
"<797>",
|
| 814 |
+
"<798>",
|
| 815 |
+
"<799>",
|
| 816 |
+
"<800>",
|
| 817 |
+
"<801>",
|
| 818 |
+
"<802>",
|
| 819 |
+
"<803>",
|
| 820 |
+
"<804>",
|
| 821 |
+
"<805>",
|
| 822 |
+
"<806>",
|
| 823 |
+
"<807>",
|
| 824 |
+
"<808>",
|
| 825 |
+
"<809>",
|
| 826 |
+
"<810>",
|
| 827 |
+
"<811>",
|
| 828 |
+
"<812>",
|
| 829 |
+
"<813>",
|
| 830 |
+
"<814>",
|
| 831 |
+
"<815>",
|
| 832 |
+
"<816>",
|
| 833 |
+
"<817>",
|
| 834 |
+
"<818>",
|
| 835 |
+
"<819>",
|
| 836 |
+
"<820>",
|
| 837 |
+
"<821>",
|
| 838 |
+
"<822>",
|
| 839 |
+
"<823>",
|
| 840 |
+
"<824>",
|
| 841 |
+
"<825>",
|
| 842 |
+
"<826>",
|
| 843 |
+
"<827>",
|
| 844 |
+
"<828>",
|
| 845 |
+
"<829>",
|
| 846 |
+
"<830>",
|
| 847 |
+
"<831>",
|
| 848 |
+
"<832>",
|
| 849 |
+
"<833>",
|
| 850 |
+
"<834>",
|
| 851 |
+
"<835>",
|
| 852 |
+
"<836>",
|
| 853 |
+
"<837>",
|
| 854 |
+
"<838>",
|
| 855 |
+
"<839>",
|
| 856 |
+
"<840>",
|
| 857 |
+
"<841>",
|
| 858 |
+
"<842>",
|
| 859 |
+
"<843>",
|
| 860 |
+
"<844>",
|
| 861 |
+
"<845>",
|
| 862 |
+
"<846>",
|
| 863 |
+
"<847>",
|
| 864 |
+
"<848>",
|
| 865 |
+
"<849>",
|
| 866 |
+
"<850>",
|
| 867 |
+
"<851>",
|
| 868 |
+
"<852>",
|
| 869 |
+
"<853>",
|
| 870 |
+
"<854>",
|
| 871 |
+
"<855>",
|
| 872 |
+
"<856>",
|
| 873 |
+
"<857>",
|
| 874 |
+
"<858>",
|
| 875 |
+
"<859>",
|
| 876 |
+
"<860>",
|
| 877 |
+
"<861>",
|
| 878 |
+
"<862>",
|
| 879 |
+
"<863>",
|
| 880 |
+
"<864>",
|
| 881 |
+
"<865>",
|
| 882 |
+
"<866>",
|
| 883 |
+
"<867>",
|
| 884 |
+
"<868>",
|
| 885 |
+
"<869>",
|
| 886 |
+
"<870>",
|
| 887 |
+
"<871>",
|
| 888 |
+
"<872>",
|
| 889 |
+
"<873>",
|
| 890 |
+
"<874>",
|
| 891 |
+
"<875>",
|
| 892 |
+
"<876>",
|
| 893 |
+
"<877>",
|
| 894 |
+
"<878>",
|
| 895 |
+
"<879>",
|
| 896 |
+
"<880>",
|
| 897 |
+
"<881>",
|
| 898 |
+
"<882>",
|
| 899 |
+
"<883>",
|
| 900 |
+
"<884>",
|
| 901 |
+
"<885>",
|
| 902 |
+
"<886>",
|
| 903 |
+
"<887>",
|
| 904 |
+
"<888>",
|
| 905 |
+
"<889>",
|
| 906 |
+
"<890>",
|
| 907 |
+
"<891>",
|
| 908 |
+
"<892>",
|
| 909 |
+
"<893>",
|
| 910 |
+
"<894>",
|
| 911 |
+
"<895>",
|
| 912 |
+
"<896>",
|
| 913 |
+
"<897>",
|
| 914 |
+
"<898>",
|
| 915 |
+
"<899>",
|
| 916 |
+
"<900>",
|
| 917 |
+
"<901>",
|
| 918 |
+
"<902>",
|
| 919 |
+
"<903>",
|
| 920 |
+
"<904>",
|
| 921 |
+
"<905>",
|
| 922 |
+
"<906>",
|
| 923 |
+
"<907>",
|
| 924 |
+
"<908>",
|
| 925 |
+
"<909>",
|
| 926 |
+
"<910>",
|
| 927 |
+
"<911>",
|
| 928 |
+
"<912>",
|
| 929 |
+
"<913>",
|
| 930 |
+
"<914>",
|
| 931 |
+
"<915>",
|
| 932 |
+
"<916>",
|
| 933 |
+
"<917>",
|
| 934 |
+
"<918>",
|
| 935 |
+
"<919>",
|
| 936 |
+
"<920>",
|
| 937 |
+
"<921>",
|
| 938 |
+
"<922>",
|
| 939 |
+
"<923>",
|
| 940 |
+
"<924>",
|
| 941 |
+
"<925>",
|
| 942 |
+
"<926>",
|
| 943 |
+
"<927>",
|
| 944 |
+
"<928>",
|
| 945 |
+
"<929>",
|
| 946 |
+
"<930>",
|
| 947 |
+
"<931>",
|
| 948 |
+
"<932>",
|
| 949 |
+
"<933>",
|
| 950 |
+
"<934>",
|
| 951 |
+
"<935>",
|
| 952 |
+
"<936>",
|
| 953 |
+
"<937>",
|
| 954 |
+
"<938>",
|
| 955 |
+
"<939>",
|
| 956 |
+
"<940>",
|
| 957 |
+
"<941>",
|
| 958 |
+
"<942>",
|
| 959 |
+
"<943>",
|
| 960 |
+
"<944>",
|
| 961 |
+
"<945>",
|
| 962 |
+
"<946>",
|
| 963 |
+
"<947>",
|
| 964 |
+
"<948>",
|
| 965 |
+
"<949>",
|
| 966 |
+
"<950>",
|
| 967 |
+
"<951>",
|
| 968 |
+
"<952>",
|
| 969 |
+
"<953>",
|
| 970 |
+
"<954>",
|
| 971 |
+
"<955>",
|
| 972 |
+
"<956>",
|
| 973 |
+
"<957>",
|
| 974 |
+
"<958>",
|
| 975 |
+
"<959>",
|
| 976 |
+
"<960>",
|
| 977 |
+
"<961>",
|
| 978 |
+
"<962>",
|
| 979 |
+
"<963>",
|
| 980 |
+
"<964>",
|
| 981 |
+
"<965>",
|
| 982 |
+
"<966>",
|
| 983 |
+
"<967>",
|
| 984 |
+
"<968>",
|
| 985 |
+
"<969>",
|
| 986 |
+
"<970>",
|
| 987 |
+
"<971>",
|
| 988 |
+
"<972>",
|
| 989 |
+
"<973>",
|
| 990 |
+
"<974>",
|
| 991 |
+
"<975>",
|
| 992 |
+
"<976>",
|
| 993 |
+
"<977>",
|
| 994 |
+
"<978>",
|
| 995 |
+
"<979>",
|
| 996 |
+
"<980>",
|
| 997 |
+
"<981>",
|
| 998 |
+
"<982>",
|
| 999 |
+
"<983>",
|
| 1000 |
+
"<984>",
|
| 1001 |
+
"<985>",
|
| 1002 |
+
"<986>",
|
| 1003 |
+
"<987>",
|
| 1004 |
+
"<988>",
|
| 1005 |
+
"<989>",
|
| 1006 |
+
"<990>",
|
| 1007 |
+
"<991>",
|
| 1008 |
+
"<992>",
|
| 1009 |
+
"<993>",
|
| 1010 |
+
"<994>",
|
| 1011 |
+
"<995>",
|
| 1012 |
+
"<996>",
|
| 1013 |
+
"<997>",
|
| 1014 |
+
"<998>",
|
| 1015 |
+
"<999>"
|
| 1016 |
+
],
|
| 1017 |
+
"eos_token": {
|
| 1018 |
+
"content": "<|im_end|>",
|
| 1019 |
+
"lstrip": false,
|
| 1020 |
+
"normalized": false,
|
| 1021 |
+
"rstrip": false,
|
| 1022 |
+
"single_word": false
|
| 1023 |
+
},
|
| 1024 |
+
"pad_token": {
|
| 1025 |
+
"content": "<|endoftext|>",
|
| 1026 |
+
"lstrip": false,
|
| 1027 |
+
"normalized": false,
|
| 1028 |
+
"rstrip": false,
|
| 1029 |
+
"single_word": false
|
| 1030 |
+
}
|
| 1031 |
+
}
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/global_step_60/actor/huggingface/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_crop/latest_global_step.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
75
|
version2_ori_from_1200_reward1_crop/log.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 2048,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 128000,
|
| 13 |
+
"max_window_layers": 70,
|
| 14 |
+
"model_type": "qwen2_5_vl",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_hidden_layers": 36,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pad_token_id": 151643,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"video_token_id": 151656,
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"depth": 32,
|
| 39 |
+
"fullatt_block_indexes": [
|
| 40 |
+
7,
|
| 41 |
+
15,
|
| 42 |
+
23,
|
| 43 |
+
31
|
| 44 |
+
],
|
| 45 |
+
"hidden_act": "silu",
|
| 46 |
+
"hidden_size": 1280,
|
| 47 |
+
"in_channels": 3,
|
| 48 |
+
"in_chans": 3,
|
| 49 |
+
"intermediate_size": 3420,
|
| 50 |
+
"model_type": "qwen2_5_vl",
|
| 51 |
+
"num_heads": 16,
|
| 52 |
+
"out_hidden_size": 2048,
|
| 53 |
+
"patch_size": 14,
|
| 54 |
+
"spatial_merge_size": 2,
|
| 55 |
+
"spatial_patch_size": 14,
|
| 56 |
+
"temporal_patch_size": 2,
|
| 57 |
+
"tokens_per_second": 2,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"window_size": 112
|
| 60 |
+
},
|
| 61 |
+
"vision_end_token_id": 151653,
|
| 62 |
+
"vision_start_token_id": 151652,
|
| 63 |
+
"vision_token_id": 151654,
|
| 64 |
+
"vocab_size": 151936
|
| 65 |
+
}
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.51.3",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7267f9246c5083f3f91f6618fb2c54d049e1a9ba0da897356d107f029e13fad6
|
| 3 |
+
size 4977059256
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e3b0d41491e2993c5d8bd3167fe6c7c728c063bc16f4bdf1af7002fa17e388
|
| 3 |
+
size 3154608736
|
version2_ori_from_1200_reward1_mixed/global_step_400/actor/huggingface/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8131575808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.27.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.28.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.29.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 726 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 732 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 738 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"visual.blocks.30.norm1.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"visual.blocks.30.norm2.weight": "model-00002-of-00002.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 744 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 750 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 756 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 762 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 763 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 768 |
+
"visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 774 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 775 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 780 |
+
"visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 786 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 788 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 792 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 798 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 799 |
+
"visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 804 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 810 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 811 |
+
"visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 812 |
+
"visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 816 |
+
"visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
|
| 822 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 823 |
+
"visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 824 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 825 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 827 |
+
"visual.merger.mlp.0.weight": "model-00002-of-00002.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.bias": "model-00002-of-00002.safetensors",
|
| 829 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 830 |
+
"visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors"
|
| 831 |
+
}
|
| 832 |
+
}
|