Hugging Face's logo

RuoliuYang
/
analysis

Safetensors
Model card Files
xet
 Community
RuoliuYang commited on
Commit
d2e67ca
·
verified ·
1 Parent(s): 2b5724e

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. stage_ablation_2ep/merge_c626/added_tokens.json +29 -0
  3. stage_ablation_2ep/merge_c626/chat_template.jinja +7 -0
  4. stage_ablation_2ep/merge_c626/config.json +144 -0
  5. stage_ablation_2ep/merge_c626/generation_config.json +12 -0
  6. stage_ablation_2ep/merge_c626/merges.txt +0 -0
  7. stage_ablation_2ep/merge_c626/model-00001-of-00004.safetensors +3 -0
  8. stage_ablation_2ep/merge_c626/model-00002-of-00004.safetensors +3 -0
  9. stage_ablation_2ep/merge_c626/model-00003-of-00004.safetensors +3 -0
  10. stage_ablation_2ep/merge_c626/model-00004-of-00004.safetensors +3 -0
  11. stage_ablation_2ep/merge_c626/model.safetensors.index.json +737 -0
  12. stage_ablation_2ep/merge_c626/preprocessor_config.json +37 -0
  13. stage_ablation_2ep/merge_c626/special_tokens_map.json +31 -0
  14. stage_ablation_2ep/merge_c626/tokenizer.json +3 -0
  15. stage_ablation_2ep/merge_c626/tokenizer_config.json +249 -0
  16. stage_ablation_2ep/merge_c626/trainer_state.json +716 -0
  17. stage_ablation_2ep/merge_c626/video_preprocessor_config.json +43 -0
  18. stage_ablation_2ep/merge_c626/vocab.json +0 -0
.gitattributes CHANGED
@@ -513,3 +513,4 @@ size-100k/stage2_final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
513
  size-100k/stage3_cos_final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
514
  size-100k/stage3_linear_final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
515
  stage_ablation_2ep/nos2_c626/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
513
  size-100k/stage3_cos_final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
514
  size-100k/stage3_linear_final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
515
  stage_ablation_2ep/nos2_c626/tokenizer.json filter=lfs diff=lfs merge=lfs -text
516
+ stage_ablation_2ep/merge_c626/tokenizer.json filter=lfs diff=lfs merge=lfs -text
stage_ablation_2ep/merge_c626/added_tokens.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</abs_vis_token>": 151667,
3
+ "</observation>": 151669,
4
+ "</tool_call>": 151658,
5
+ "<abs_vis_token>": 151666,
6
+ "<abs_vis_token_pad>": 151665,
7
+ "<observation>": 151668,
8
+ "<tool_call>": 151657,
9
+ "<|box_end|>": 151649,
10
+ "<|box_start|>": 151648,
11
+ "<|endoftext|>": 151643,
12
+ "<|file_sep|>": 151664,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|im_end|>": 151645,
18
+ "<|im_start|>": 151644,
19
+ "<|image_pad|>": 151655,
20
+ "<|object_ref_end|>": 151647,
21
+ "<|object_ref_start|>": 151646,
22
+ "<|quad_end|>": 151651,
23
+ "<|quad_start|>": 151650,
24
+ "<|repo_name|>": 151663,
25
+ "<|video_pad|>": 151656,
26
+ "<|vision_end|>": 151653,
27
+ "<|vision_pad|>": 151654,
28
+ "<|vision_start|>": 151652
29
+ }
stage_ablation_2ep/merge_c626/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
stage_ablation_2ep/merge_c626/config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "answer_start_pattern": [
3
+ 151644,
4
+ 77091
5
+ ],
6
+ "architectures": [
7
+ "Qwen2_5_VLForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 151643,
11
+ "eos_token_id": 151645,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3584,
14
+ "image_token_id": 151655,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 18944,
17
+ "latent_end_id": 151667,
18
+ "latent_start_id": 151666,
19
+ "latent_token_id": 151665,
20
+ "loss_type": "ForCausalLMLoss",
21
+ "max_position_embeddings": 128000,
22
+ "max_window_layers": 28,
23
+ "model_type": "qwen2_5_vl",
24
+ "num_attention_heads": 28,
25
+ "num_hidden_layers": 28,
26
+ "num_key_value_heads": 4,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": {
29
+ "mrope_section": [
30
+ 16,
31
+ 24,
32
+ 24
33
+ ],
34
+ "rope_type": "default",
35
+ "type": "default"
36
+ },
37
+ "rope_theta": 1000000.0,
38
+ "sliding_window": 32768,
39
+ "stage": "sft_stage3",
40
+ "text_config": {
41
+ "architectures": [
42
+ "Qwen2_5_VLForConditionalGeneration"
43
+ ],
44
+ "attention_dropout": 0.0,
45
+ "bos_token_id": 151643,
46
+ "eos_token_id": 151645,
47
+ "hidden_act": "silu",
48
+ "hidden_size": 3584,
49
+ "image_token_id": null,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 18944,
52
+ "layer_types": [
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention"
81
+ ],
82
+ "max_position_embeddings": 128000,
83
+ "max_window_layers": 28,
84
+ "model_type": "qwen2_5_vl_text",
85
+ "num_attention_heads": 28,
86
+ "num_hidden_layers": 28,
87
+ "num_key_value_heads": 4,
88
+ "rms_norm_eps": 1e-06,
89
+ "rope_scaling": {
90
+ "mrope_section": [
91
+ 16,
92
+ 24,
93
+ 24
94
+ ],
95
+ "rope_type": "default",
96
+ "type": "default"
97
+ },
98
+ "rope_theta": 1000000.0,
99
+ "sliding_window": null,
100
+ "torch_dtype": "bfloat16",
101
+ "use_cache": true,
102
+ "use_sliding_window": false,
103
+ "video_token_id": null,
104
+ "vision_end_token_id": 151653,
105
+ "vision_start_token_id": 151652,
106
+ "vision_token_id": 151654,
107
+ "vocab_size": 151670
108
+ },
109
+ "tie_word_embeddings": false,
110
+ "torch_dtype": "bfloat16",
111
+ "transformers_version": "4.54.0",
112
+ "use_cache": false,
113
+ "use_sliding_window": false,
114
+ "video_token_id": 151656,
115
+ "vision_config": {
116
+ "depth": 32,
117
+ "fullatt_block_indexes": [
118
+ 7,
119
+ 15,
120
+ 23,
121
+ 31
122
+ ],
123
+ "hidden_act": "silu",
124
+ "hidden_size": 1280,
125
+ "in_channels": 3,
126
+ "in_chans": 3,
127
+ "initializer_range": 0.02,
128
+ "intermediate_size": 3420,
129
+ "model_type": "qwen2_5_vl",
130
+ "num_heads": 16,
131
+ "out_hidden_size": 3584,
132
+ "patch_size": 14,
133
+ "spatial_merge_size": 2,
134
+ "spatial_patch_size": 14,
135
+ "temporal_patch_size": 2,
136
+ "tokens_per_second": 2,
137
+ "torch_dtype": "bfloat16",
138
+ "window_size": 112
139
+ },
140
+ "vision_end_token_id": 151653,
141
+ "vision_start_token_id": 151652,
142
+ "vision_token_id": 151654,
143
+ "vocab_size": 151670
144
+ }
stage_ablation_2ep/merge_c626/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.54.0"
12
+ }
stage_ablation_2ep/merge_c626/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
stage_ablation_2ep/merge_c626/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd037fb518351317863b0e0cf4bb238204cbc4f8a73e7b54cda9886da8814e8
3
+ size 4965419112
stage_ablation_2ep/merge_c626/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557d6eeeda452afef2507ea7248778621ab388999da46540e255ed518e7b6f17
3
+ size 4991495816
stage_ablation_2ep/merge_c626/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:517d0e159fdfb295c46efe9155f176a3d4b9a121c7c336294102e58c9878d28f
3
+ size 4932751040
stage_ablation_2ep/merge_c626/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6d0d28b61ec8af9f722dd649127758b9398da298da249de60f7a21dfcf7177e
3
+ size 1689100192
stage_ablation_2ep/merge_c626/model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8289342464,
4
+ "total_size": 16578684928
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
stage_ablation_2ep/merge_c626/preprocessor_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessorFast",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_pixels": 12845056,
25
+ "merge_size": 2,
26
+ "min_pixels": 3136,
27
+ "patch_size": 14,
28
+ "processor_class": "Qwen2_5_VLProcessor",
29
+ "resample": 3,
30
+ "rescale_factor": 0.00392156862745098,
31
+ "return_tensors": null,
32
+ "size": {
33
+ "longest_edge": 12845056,
34
+ "shortest_edge": 3136
35
+ },
36
+ "temporal_patch_size": 2
37
+ }
stage_ablation_2ep/merge_c626/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
stage_ablation_2ep/merge_c626/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f9fae7ca98ea5ec3491610545d8b0662b8dc45a16f3dec6dd051cc84ae422f
3
+ size 11423026
stage_ablation_2ep/merge_c626/tokenizer_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<abs_vis_token_pad>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<abs_vis_token>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "</abs_vis_token>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<observation>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "</observation>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ }
221
+ },
222
+ "additional_special_tokens": [
223
+ "<|im_start|>",
224
+ "<|im_end|>",
225
+ "<|object_ref_start|>",
226
+ "<|object_ref_end|>",
227
+ "<|box_start|>",
228
+ "<|box_end|>",
229
+ "<|quad_start|>",
230
+ "<|quad_end|>",
231
+ "<|vision_start|>",
232
+ "<|vision_end|>",
233
+ "<|vision_pad|>",
234
+ "<|image_pad|>",
235
+ "<|video_pad|>"
236
+ ],
237
+ "bos_token": null,
238
+ "clean_up_tokenization_spaces": false,
239
+ "eos_token": "<|im_end|>",
240
+ "errors": "replace",
241
+ "extra_special_tokens": {},
242
+ "model_max_length": 131072,
243
+ "pad_token": "<|endoftext|>",
244
+ "processor_class": "Qwen2_5_VLProcessor",
245
+ "split_special_tokens": false,
246
+ "tokenizer_class": "Qwen2Tokenizer",
247
+ "unk_token": null,
248
+ "use_fast": true
249
+ }
stage_ablation_2ep/merge_c626/trainer_state.json ADDED
@@ -0,0 +1,716 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 626,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "alignment_loss": 0.959321,
14
+ "epoch": 0.032,
15
+ "grad_norm": 288.22515869140625,
16
+ "learning_rate": 2.368421052631579e-06,
17
+ "loss": 7.7317,
18
+ "mean_token_accuracy": 0.577549284696579,
19
+ "num_tokens": 232738.0,
20
+ "step": 10,
21
+ "student_ce_loss": 5.708587
22
+ },
23
+ {
24
+ "alignment_loss": 0.961583,
25
+ "epoch": 0.064,
26
+ "grad_norm": 43.49296569824219,
27
+ "learning_rate": 5e-06,
28
+ "loss": 4.7091,
29
+ "mean_token_accuracy": 0.6889920800924301,
30
+ "num_tokens": 457100.0,
31
+ "step": 20,
32
+ "student_ce_loss": 2.679379
33
+ },
34
+ {
35
+ "alignment_loss": 0.978942,
36
+ "epoch": 0.096,
37
+ "grad_norm": 24.87029457092285,
38
+ "learning_rate": 4.917627677100494e-06,
39
+ "loss": 3.315,
40
+ "mean_token_accuracy": 0.7594781041145324,
41
+ "num_tokens": 686030.0,
42
+ "step": 30,
43
+ "student_ce_loss": 1.309346
44
+ },
45
+ {
46
+ "alignment_loss": 0.978465,
47
+ "epoch": 0.128,
48
+ "grad_norm": 26.0273380279541,
49
+ "learning_rate": 4.835255354200989e-06,
50
+ "loss": 3.0023,
51
+ "mean_token_accuracy": 0.7827262997627258,
52
+ "num_tokens": 917056.0,
53
+ "step": 40,
54
+ "student_ce_loss": 0.943775
55
+ },
56
+ {
57
+ "alignment_loss": 0.972033,
58
+ "epoch": 0.16,
59
+ "grad_norm": 22.497652053833008,
60
+ "learning_rate": 4.7528830313014825e-06,
61
+ "loss": 2.8736,
62
+ "mean_token_accuracy": 0.7781289160251618,
63
+ "num_tokens": 1146888.0,
64
+ "step": 50,
65
+ "student_ce_loss": 0.930594
66
+ },
67
+ {
68
+ "alignment_loss": 0.959871,
69
+ "epoch": 0.192,
70
+ "grad_norm": 20.67714500427246,
71
+ "learning_rate": 4.670510708401977e-06,
72
+ "loss": 2.7057,
73
+ "mean_token_accuracy": 0.8188202947378158,
74
+ "num_tokens": 1379720.0,
75
+ "step": 60,
76
+ "student_ce_loss": 0.755639
77
+ },
78
+ {
79
+ "alignment_loss": 0.925796,
80
+ "epoch": 0.224,
81
+ "grad_norm": 15.355382919311523,
82
+ "learning_rate": 4.588138385502472e-06,
83
+ "loss": 2.4975,
84
+ "mean_token_accuracy": 0.8569179981946945,
85
+ "num_tokens": 1610186.0,
86
+ "step": 70,
87
+ "student_ce_loss": 0.673174
88
+ },
89
+ {
90
+ "alignment_loss": 0.887404,
91
+ "epoch": 0.256,
92
+ "grad_norm": 9.609471321105957,
93
+ "learning_rate": 4.5057660626029655e-06,
94
+ "loss": 2.312,
95
+ "mean_token_accuracy": 0.8552648782730102,
96
+ "num_tokens": 1840854.0,
97
+ "step": 80,
98
+ "student_ce_loss": 0.447062
99
+ },
100
+ {
101
+ "alignment_loss": 0.834419,
102
+ "epoch": 0.288,
103
+ "grad_norm": 5.4535698890686035,
104
+ "learning_rate": 4.42339373970346e-06,
105
+ "loss": 2.1853,
106
+ "mean_token_accuracy": 0.8510835260152817,
107
+ "num_tokens": 2065639.0,
108
+ "step": 90,
109
+ "student_ce_loss": 0.562349
110
+ },
111
+ {
112
+ "alignment_loss": 0.741999,
113
+ "epoch": 0.32,
114
+ "grad_norm": 4.904428958892822,
115
+ "learning_rate": 4.341021416803955e-06,
116
+ "loss": 1.9824,
117
+ "mean_token_accuracy": 0.8461377412080765,
118
+ "num_tokens": 2292596.0,
119
+ "step": 100,
120
+ "student_ce_loss": 0.561277
121
+ },
122
+ {
123
+ "alignment_loss": 0.681011,
124
+ "epoch": 0.352,
125
+ "grad_norm": 3.712263584136963,
126
+ "learning_rate": 4.2586490939044485e-06,
127
+ "loss": 1.8148,
128
+ "mean_token_accuracy": 0.8623093694448472,
129
+ "num_tokens": 2514328.0,
130
+ "step": 110,
131
+ "student_ce_loss": 0.470692
132
+ },
133
+ {
134
+ "alignment_loss": 0.625928,
135
+ "epoch": 0.384,
136
+ "grad_norm": 3.9196927547454834,
137
+ "learning_rate": 4.176276771004943e-06,
138
+ "loss": 1.703,
139
+ "mean_token_accuracy": 0.8677410036325455,
140
+ "num_tokens": 2744540.0,
141
+ "step": 120,
142
+ "student_ce_loss": 0.435604
143
+ },
144
+ {
145
+ "alignment_loss": 0.592771,
146
+ "epoch": 0.416,
147
+ "grad_norm": 3.680621385574341,
148
+ "learning_rate": 4.093904448105437e-06,
149
+ "loss": 1.6334,
150
+ "mean_token_accuracy": 0.8652973473072052,
151
+ "num_tokens": 2967758.0,
152
+ "step": 130,
153
+ "student_ce_loss": 0.438567
154
+ },
155
+ {
156
+ "alignment_loss": 0.559862,
157
+ "epoch": 0.448,
158
+ "grad_norm": 3.67236328125,
159
+ "learning_rate": 4.0115321252059315e-06,
160
+ "loss": 1.6141,
161
+ "mean_token_accuracy": 0.8557980507612228,
162
+ "num_tokens": 3194766.0,
163
+ "step": 140,
164
+ "student_ce_loss": 0.392981
165
+ },
166
+ {
167
+ "alignment_loss": 0.567406,
168
+ "epoch": 0.48,
169
+ "grad_norm": 3.536939859390259,
170
+ "learning_rate": 3.929159802306425e-06,
171
+ "loss": 1.5635,
172
+ "mean_token_accuracy": 0.866544532775879,
173
+ "num_tokens": 3423295.0,
174
+ "step": 150,
175
+ "student_ce_loss": 0.465931
176
+ },
177
+ {
178
+ "alignment_loss": 0.558488,
179
+ "epoch": 0.512,
180
+ "grad_norm": 3.7496066093444824,
181
+ "learning_rate": 3.846787479406919e-06,
182
+ "loss": 1.5024,
183
+ "mean_token_accuracy": 0.8763937592506409,
184
+ "num_tokens": 3654650.0,
185
+ "step": 160,
186
+ "student_ce_loss": 0.461349
187
+ },
188
+ {
189
+ "alignment_loss": 0.53884,
190
+ "epoch": 0.544,
191
+ "grad_norm": 3.5967488288879395,
192
+ "learning_rate": 3.7644151565074136e-06,
193
+ "loss": 1.5057,
194
+ "mean_token_accuracy": 0.8661749601364136,
195
+ "num_tokens": 3883181.0,
196
+ "step": 170,
197
+ "student_ce_loss": 0.448559
198
+ },
199
+ {
200
+ "alignment_loss": 0.54358,
201
+ "epoch": 0.576,
202
+ "grad_norm": 3.745586633682251,
203
+ "learning_rate": 3.682042833607908e-06,
204
+ "loss": 1.5029,
205
+ "mean_token_accuracy": 0.8630174219608306,
206
+ "num_tokens": 4111471.0,
207
+ "step": 180,
208
+ "student_ce_loss": 0.502599
209
+ },
210
+ {
211
+ "alignment_loss": 0.525246,
212
+ "epoch": 0.608,
213
+ "grad_norm": 3.9150030612945557,
214
+ "learning_rate": 3.5996705107084024e-06,
215
+ "loss": 1.4636,
216
+ "mean_token_accuracy": 0.8658594340085983,
217
+ "num_tokens": 4334769.0,
218
+ "step": 190,
219
+ "student_ce_loss": 0.449682
220
+ },
221
+ {
222
+ "alignment_loss": 0.515595,
223
+ "epoch": 0.64,
224
+ "grad_norm": 3.9583852291107178,
225
+ "learning_rate": 3.517298187808896e-06,
226
+ "loss": 1.4583,
227
+ "mean_token_accuracy": 0.8634992003440857,
228
+ "num_tokens": 4560675.0,
229
+ "step": 200,
230
+ "student_ce_loss": 0.408408
231
+ },
232
+ {
233
+ "alignment_loss": 0.499636,
234
+ "epoch": 0.672,
235
+ "grad_norm": 4.064545154571533,
236
+ "learning_rate": 3.434925864909391e-06,
237
+ "loss": 1.4307,
238
+ "mean_token_accuracy": 0.8722353994846344,
239
+ "num_tokens": 4793717.0,
240
+ "step": 210,
241
+ "student_ce_loss": 0.493844
242
+ },
243
+ {
244
+ "alignment_loss": 0.514014,
245
+ "epoch": 0.704,
246
+ "grad_norm": 4.126977920532227,
247
+ "learning_rate": 3.352553542009885e-06,
248
+ "loss": 1.42,
249
+ "mean_token_accuracy": 0.8716267824172974,
250
+ "num_tokens": 5024297.0,
251
+ "step": 220,
252
+ "student_ce_loss": 0.341596
253
+ },
254
+ {
255
+ "alignment_loss": 0.517264,
256
+ "epoch": 0.736,
257
+ "grad_norm": 3.7240042686462402,
258
+ "learning_rate": 3.270181219110379e-06,
259
+ "loss": 1.4322,
260
+ "mean_token_accuracy": 0.8684907674789428,
261
+ "num_tokens": 5251266.0,
262
+ "step": 230,
263
+ "student_ce_loss": 0.441522
264
+ },
265
+ {
266
+ "alignment_loss": 0.499193,
267
+ "epoch": 0.768,
268
+ "grad_norm": 3.5627481937408447,
269
+ "learning_rate": 3.1878088962108734e-06,
270
+ "loss": 1.4071,
271
+ "mean_token_accuracy": 0.86993607878685,
272
+ "num_tokens": 5479898.0,
273
+ "step": 240,
274
+ "student_ce_loss": 0.448617
275
+ },
276
+ {
277
+ "alignment_loss": 0.486691,
278
+ "epoch": 0.8,
279
+ "grad_norm": 3.5347883701324463,
280
+ "learning_rate": 3.105436573311368e-06,
281
+ "loss": 1.3982,
282
+ "mean_token_accuracy": 0.8668092101812362,
283
+ "num_tokens": 5709885.0,
284
+ "step": 250,
285
+ "student_ce_loss": 0.439553
286
+ },
287
+ {
288
+ "alignment_loss": 0.481557,
289
+ "epoch": 0.832,
290
+ "grad_norm": 3.6041319370269775,
291
+ "learning_rate": 3.0230642504118618e-06,
292
+ "loss": 1.4205,
293
+ "mean_token_accuracy": 0.8536424428224564,
294
+ "num_tokens": 5938745.0,
295
+ "step": 260,
296
+ "student_ce_loss": 0.428512
297
+ },
298
+ {
299
+ "alignment_loss": 0.489778,
300
+ "epoch": 0.864,
301
+ "grad_norm": 3.6519017219543457,
302
+ "learning_rate": 2.9406919275123564e-06,
303
+ "loss": 1.3977,
304
+ "mean_token_accuracy": 0.8601963251829148,
305
+ "num_tokens": 6164937.0,
306
+ "step": 270,
307
+ "student_ce_loss": 0.414584
308
+ },
309
+ {
310
+ "alignment_loss": 0.472692,
311
+ "epoch": 0.896,
312
+ "grad_norm": 4.053863525390625,
313
+ "learning_rate": 2.85831960461285e-06,
314
+ "loss": 1.3687,
315
+ "mean_token_accuracy": 0.8660070031881333,
316
+ "num_tokens": 6392404.0,
317
+ "step": 280,
318
+ "student_ce_loss": 0.38117
319
+ },
320
+ {
321
+ "alignment_loss": 0.474552,
322
+ "epoch": 0.928,
323
+ "grad_norm": 3.6165175437927246,
324
+ "learning_rate": 2.7759472817133443e-06,
325
+ "loss": 1.3634,
326
+ "mean_token_accuracy": 0.8711693465709687,
327
+ "num_tokens": 6621995.0,
328
+ "step": 290,
329
+ "student_ce_loss": 0.466054
330
+ },
331
+ {
332
+ "alignment_loss": 0.461458,
333
+ "epoch": 0.96,
334
+ "grad_norm": 4.045195579528809,
335
+ "learning_rate": 2.693574958813839e-06,
336
+ "loss": 1.3736,
337
+ "mean_token_accuracy": 0.8663843452930451,
338
+ "num_tokens": 6854335.0,
339
+ "step": 300,
340
+ "student_ce_loss": 0.448026
341
+ },
342
+ {
343
+ "alignment_loss": 0.460456,
344
+ "epoch": 0.992,
345
+ "grad_norm": 3.6360766887664795,
346
+ "learning_rate": 2.6112026359143327e-06,
347
+ "loss": 1.3631,
348
+ "mean_token_accuracy": 0.8654103368520737,
349
+ "num_tokens": 7086636.0,
350
+ "step": 310,
351
+ "student_ce_loss": 0.389693
352
+ },
353
+ {
354
+ "alignment_loss": 0.45942,
355
+ "epoch": 1.0224,
356
+ "grad_norm": 3.5527138710021973,
357
+ "learning_rate": 2.5288303130148273e-06,
358
+ "loss": 1.2123,
359
+ "mean_token_accuracy": 0.8882091923763877,
360
+ "num_tokens": 7304046.0,
361
+ "step": 320,
362
+ "student_ce_loss": 0.330199
363
+ },
364
+ {
365
+ "alignment_loss": 0.464639,
366
+ "epoch": 1.0544,
367
+ "grad_norm": 3.216679096221924,
368
+ "learning_rate": 2.4464579901153215e-06,
369
+ "loss": 1.2049,
370
+ "mean_token_accuracy": 0.9062695652246475,
371
+ "num_tokens": 7536354.0,
372
+ "step": 330,
373
+ "student_ce_loss": 0.240837
374
+ },
375
+ {
376
+ "alignment_loss": 0.450771,
377
+ "epoch": 1.0864,
378
+ "grad_norm": 2.9375364780426025,
379
+ "learning_rate": 2.3640856672158157e-06,
380
+ "loss": 1.2216,
381
+ "mean_token_accuracy": 0.8996289253234864,
382
+ "num_tokens": 7761125.0,
383
+ "step": 340,
384
+ "student_ce_loss": 0.312439
385
+ },
386
+ {
387
+ "alignment_loss": 0.457484,
388
+ "epoch": 1.1184,
389
+ "grad_norm": 3.2681849002838135,
390
+ "learning_rate": 2.28171334431631e-06,
391
+ "loss": 1.2128,
392
+ "mean_token_accuracy": 0.902117469906807,
393
+ "num_tokens": 7990081.0,
394
+ "step": 350,
395
+ "student_ce_loss": 0.319445
396
+ },
397
+ {
398
+ "alignment_loss": 0.462431,
399
+ "epoch": 1.1504,
400
+ "grad_norm": 3.521085739135742,
401
+ "learning_rate": 2.199341021416804e-06,
402
+ "loss": 1.2142,
403
+ "mean_token_accuracy": 0.8998272389173507,
404
+ "num_tokens": 8220846.0,
405
+ "step": 360,
406
+ "student_ce_loss": 0.376999
407
+ },
408
+ {
409
+ "alignment_loss": 0.454978,
410
+ "epoch": 1.1824,
411
+ "grad_norm": 3.268390655517578,
412
+ "learning_rate": 2.1169686985172982e-06,
413
+ "loss": 1.1831,
414
+ "mean_token_accuracy": 0.9079845815896987,
415
+ "num_tokens": 8450233.0,
416
+ "step": 370,
417
+ "student_ce_loss": 0.24728
418
+ },
419
+ {
420
+ "alignment_loss": 0.444953,
421
+ "epoch": 1.2144,
422
+ "grad_norm": 3.219233989715576,
423
+ "learning_rate": 2.0345963756177924e-06,
424
+ "loss": 1.2112,
425
+ "mean_token_accuracy": 0.8994165867567062,
426
+ "num_tokens": 8681418.0,
427
+ "step": 380,
428
+ "student_ce_loss": 0.251072
429
+ },
430
+ {
431
+ "alignment_loss": 0.456667,
432
+ "epoch": 1.2464,
433
+ "grad_norm": 3.573242664337158,
434
+ "learning_rate": 1.9522240527182866e-06,
435
+ "loss": 1.2055,
436
+ "mean_token_accuracy": 0.8993523776531219,
437
+ "num_tokens": 8907566.0,
438
+ "step": 390,
439
+ "student_ce_loss": 0.33932
440
+ },
441
+ {
442
+ "alignment_loss": 0.448943,
443
+ "epoch": 1.2784,
444
+ "grad_norm": 3.7022528648376465,
445
+ "learning_rate": 1.869851729818781e-06,
446
+ "loss": 1.2082,
447
+ "mean_token_accuracy": 0.8965563952922821,
448
+ "num_tokens": 9141799.0,
449
+ "step": 400,
450
+ "student_ce_loss": 0.281565
451
+ },
452
+ {
453
+ "alignment_loss": 0.444555,
454
+ "epoch": 1.3104,
455
+ "grad_norm": 3.5564444065093994,
456
+ "learning_rate": 1.7874794069192752e-06,
457
+ "loss": 1.2223,
458
+ "mean_token_accuracy": 0.8911885768175125,
459
+ "num_tokens": 9370863.0,
460
+ "step": 410,
461
+ "student_ce_loss": 0.296593
462
+ },
463
+ {
464
+ "alignment_loss": 0.439943,
465
+ "epoch": 1.3424,
466
+ "grad_norm": 3.416459321975708,
467
+ "learning_rate": 1.7051070840197694e-06,
468
+ "loss": 1.2021,
469
+ "mean_token_accuracy": 0.8912496030330658,
470
+ "num_tokens": 9595993.0,
471
+ "step": 420,
472
+ "student_ce_loss": 0.318373
473
+ },
474
+ {
475
+ "alignment_loss": 0.450294,
476
+ "epoch": 1.3744,
477
+ "grad_norm": 3.39276123046875,
478
+ "learning_rate": 1.6227347611202638e-06,
479
+ "loss": 1.2037,
480
+ "mean_token_accuracy": 0.8998627454042435,
481
+ "num_tokens": 9825473.0,
482
+ "step": 430,
483
+ "student_ce_loss": 0.244895
484
+ },
485
+ {
486
+ "alignment_loss": 0.448484,
487
+ "epoch": 1.4064,
488
+ "grad_norm": 3.389965057373047,
489
+ "learning_rate": 1.540362438220758e-06,
490
+ "loss": 1.2028,
491
+ "mean_token_accuracy": 0.8933465272188187,
492
+ "num_tokens": 10055385.0,
493
+ "step": 440,
494
+ "student_ce_loss": 0.324854
495
+ },
496
+ {
497
+ "alignment_loss": 0.440189,
498
+ "epoch": 1.4384000000000001,
499
+ "grad_norm": 3.232836961746216,
500
+ "learning_rate": 1.4579901153212522e-06,
501
+ "loss": 1.1662,
502
+ "mean_token_accuracy": 0.9023067742586136,
503
+ "num_tokens": 10281622.0,
504
+ "step": 450,
505
+ "student_ce_loss": 0.32019
506
+ },
507
+ {
508
+ "alignment_loss": 0.437653,
509
+ "epoch": 1.4704,
510
+ "grad_norm": 3.6234006881713867,
511
+ "learning_rate": 1.3756177924217466e-06,
512
+ "loss": 1.1803,
513
+ "mean_token_accuracy": 0.9058025807142258,
514
+ "num_tokens": 10505850.0,
515
+ "step": 460,
516
+ "student_ce_loss": 0.244465
517
+ },
518
+ {
519
+ "alignment_loss": 0.427158,
520
+ "epoch": 1.5024,
521
+ "grad_norm": 3.570405960083008,
522
+ "learning_rate": 1.2932454695222407e-06,
523
+ "loss": 1.1729,
524
+ "mean_token_accuracy": 0.8998123049736023,
525
+ "num_tokens": 10733222.0,
526
+ "step": 470,
527
+ "student_ce_loss": 0.313906
528
+ },
529
+ {
530
+ "alignment_loss": 0.429971,
531
+ "epoch": 1.5344,
532
+ "grad_norm": 3.408435821533203,
533
+ "learning_rate": 1.210873146622735e-06,
534
+ "loss": 1.1663,
535
+ "mean_token_accuracy": 0.9075150847434997,
536
+ "num_tokens": 10962344.0,
537
+ "step": 480,
538
+ "student_ce_loss": 0.273231
539
+ },
540
+ {
541
+ "alignment_loss": 0.449655,
542
+ "epoch": 1.5664,
543
+ "grad_norm": 3.2459113597869873,
544
+ "learning_rate": 1.1285008237232291e-06,
545
+ "loss": 1.1928,
546
+ "mean_token_accuracy": 0.9017594397068024,
547
+ "num_tokens": 11196395.0,
548
+ "step": 490,
549
+ "student_ce_loss": 0.266921
550
+ },
551
+ {
552
+ "alignment_loss": 0.454309,
553
+ "epoch": 1.5984,
554
+ "grad_norm": 3.378347396850586,
555
+ "learning_rate": 1.0461285008237233e-06,
556
+ "loss": 1.1678,
557
+ "mean_token_accuracy": 0.9047713190317154,
558
+ "num_tokens": 11421139.0,
559
+ "step": 500,
560
+ "student_ce_loss": 0.308299
561
+ },
562
+ {
563
+ "alignment_loss": 0.45753,
564
+ "epoch": 1.6303999999999998,
565
+ "grad_norm": 3.2015256881713867,
566
+ "learning_rate": 9.637561779242175e-07,
567
+ "loss": 1.204,
568
+ "mean_token_accuracy": 0.8986049801111221,
569
+ "num_tokens": 11651627.0,
570
+ "step": 510,
571
+ "student_ce_loss": 0.290834
572
+ },
573
+ {
574
+ "alignment_loss": 0.440362,
575
+ "epoch": 1.6623999999999999,
576
+ "grad_norm": 3.2747654914855957,
577
+ "learning_rate": 8.813838550247118e-07,
578
+ "loss": 1.1989,
579
+ "mean_token_accuracy": 0.8999978750944138,
580
+ "num_tokens": 11880354.0,
581
+ "step": 520,
582
+ "student_ce_loss": 0.338233
583
+ },
584
+ {
585
+ "alignment_loss": 0.444625,
586
+ "epoch": 1.6944,
587
+ "grad_norm": 3.427901268005371,
588
+ "learning_rate": 7.99011532125206e-07,
589
+ "loss": 1.1825,
590
+ "mean_token_accuracy": 0.8998278498649597,
591
+ "num_tokens": 12108571.0,
592
+ "step": 530,
593
+ "student_ce_loss": 0.307574
594
+ },
595
+ {
596
+ "alignment_loss": 0.420043,
597
+ "epoch": 1.7264,
598
+ "grad_norm": 3.2479658126831055,
599
+ "learning_rate": 7.166392092257002e-07,
600
+ "loss": 1.2053,
601
+ "mean_token_accuracy": 0.8953103482723236,
602
+ "num_tokens": 12338200.0,
603
+ "step": 540,
604
+ "student_ce_loss": 0.279031
605
+ },
606
+ {
607
+ "alignment_loss": 0.430166,
608
+ "epoch": 1.7584,
609
+ "grad_norm": 3.435574531555176,
610
+ "learning_rate": 6.342668863261945e-07,
611
+ "loss": 1.1651,
612
+ "mean_token_accuracy": 0.9026517033576965,
613
+ "num_tokens": 12565935.0,
614
+ "step": 550,
615
+ "student_ce_loss": 0.265311
616
+ },
617
+ {
618
+ "alignment_loss": 0.427686,
619
+ "epoch": 1.7904,
620
+ "grad_norm": 3.4701385498046875,
621
+ "learning_rate": 5.518945634266886e-07,
622
+ "loss": 1.1659,
623
+ "mean_token_accuracy": 0.9053906977176667,
624
+ "num_tokens": 12796939.0,
625
+ "step": 560,
626
+ "student_ce_loss": 0.266552
627
+ },
628
+ {
629
+ "alignment_loss": 0.435195,
630
+ "epoch": 1.8224,
631
+ "grad_norm": 3.376873254776001,
632
+ "learning_rate": 4.6952224052718294e-07,
633
+ "loss": 1.1846,
634
+ "mean_token_accuracy": 0.8964692324399948,
635
+ "num_tokens": 13025012.0,
636
+ "step": 570,
637
+ "student_ce_loss": 0.315301
638
+ },
639
+ {
640
+ "alignment_loss": 0.451159,
641
+ "epoch": 1.8544,
642
+ "grad_norm": 3.281425952911377,
643
+ "learning_rate": 3.8714991762767713e-07,
644
+ "loss": 1.171,
645
+ "mean_token_accuracy": 0.8984391689300537,
646
+ "num_tokens": 13250535.0,
647
+ "step": 580,
648
+ "student_ce_loss": 0.348867
649
+ },
650
+ {
651
+ "alignment_loss": 0.455995,
652
+ "epoch": 1.8864,
653
+ "grad_norm": 3.080890417098999,
654
+ "learning_rate": 3.0477759472817137e-07,
655
+ "loss": 1.1897,
656
+ "mean_token_accuracy": 0.9005747228860855,
657
+ "num_tokens": 13475102.0,
658
+ "step": 590,
659
+ "student_ce_loss": 0.231659
660
+ },
661
+ {
662
+ "alignment_loss": 0.450271,
663
+ "epoch": 1.9184,
664
+ "grad_norm": 3.2822272777557373,
665
+ "learning_rate": 2.224052718286656e-07,
666
+ "loss": 1.1962,
667
+ "mean_token_accuracy": 0.8959783226251602,
668
+ "num_tokens": 13704195.0,
669
+ "step": 600,
670
+ "student_ce_loss": 0.249835
671
+ },
672
+ {
673
+ "alignment_loss": 0.435287,
674
+ "epoch": 1.9504000000000001,
675
+ "grad_norm": 3.6094486713409424,
676
+ "learning_rate": 1.4003294892915982e-07,
677
+ "loss": 1.1696,
678
+ "mean_token_accuracy": 0.9018221467733383,
679
+ "num_tokens": 13934517.0,
680
+ "step": 610,
681
+ "student_ce_loss": 0.308769
682
+ },
683
+ {
684
+ "alignment_loss": 0.425761,
685
+ "epoch": 1.9824000000000002,
686
+ "grad_norm": 3.5100579261779785,
687
+ "learning_rate": 5.7660626029654044e-08,
688
+ "loss": 1.1676,
689
+ "mean_token_accuracy": 0.896885696053505,
690
+ "num_tokens": 14160420.0,
691
+ "step": 620,
692
+ "student_ce_loss": 0.317542
693
+ }
694
+ ],
695
+ "logging_steps": 10,
696
+ "max_steps": 626,
697
+ "num_input_tokens_seen": 0,
698
+ "num_train_epochs": 2,
699
+ "save_steps": 313,
700
+ "stateful_callbacks": {
701
+ "TrainerControl": {
702
+ "args": {
703
+ "should_epoch_stop": false,
704
+ "should_evaluate": false,
705
+ "should_log": false,
706
+ "should_save": true,
707
+ "should_training_stop": true
708
+ },
709
+ "attributes": {}
710
+ }
711
+ },
712
+ "total_flos": 0.0,
713
+ "train_batch_size": 8,
714
+ "trial_name": null,
715
+ "trial_params": null
716
+ }
stage_ablation_2ep/merge_c626/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "size": {
36
+ "longest_edge": 12845056,
37
+ "shortest_edge": 3136
38
+ },
39
+ "size_divisor": null,
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
stage_ablation_2ep/merge_c626/vocab.json ADDED
The diff for this file is too large to render. See raw diff