Hugging Face's logo

internlm
/
CapRL-InternVL3.5-8B

Image-Text-to-Text
Transformers
Safetensors
English
internvl
multimodal
image caption
captioning
conversational
Model card Files
xet
Community
yuhangzang commited on
Commit
ffc47d5
·
verified ·
1 Parent(s): 9361eee

Add files using upload-large-folder tool

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +38 -0
  3. chat_template.jinja +6 -0
  4. config.json +122 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. model-00001-of-00004.safetensors +3 -0
  8. model-00002-of-00004.safetensors +3 -0
  9. model-00003-of-00004.safetensors +3 -0
  10. model-00004-of-00004.safetensors +3 -0
  11. model.safetensors.index.json +849 -0
  12. preprocessor_config.json +35 -0
  13. processor_config.json +4 -0
  14. special_tokens_map.json +44 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +339 -0
  17. video_preprocessor_config.json +38 -0
  18. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151677,
3
+ "</img>": 151670,
4
+ "</quad>": 151673,
5
+ "</ref>": 151675,
6
+ "</think>": 151668,
7
+ "</tool_call>": 151658,
8
+ "</tool_response>": 151666,
9
+ "<IMG_CONTEXT>": 151671,
10
+ "<box>": 151676,
11
+ "<img>": 151669,
12
+ "<quad>": 151672,
13
+ "<ref>": 151674,
14
+ "<think>": 151667,
15
+ "<tool_call>": 151657,
16
+ "<tool_response>": 151665,
17
+ "<video>": 151678,
18
+ "<|box_end|>": 151649,
19
+ "<|box_start|>": 151648,
20
+ "<|endoftext|>": 151643,
21
+ "<|file_sep|>": 151664,
22
+ "<|fim_middle|>": 151660,
23
+ "<|fim_pad|>": 151662,
24
+ "<|fim_prefix|>": 151659,
25
+ "<|fim_suffix|>": 151661,
26
+ "<|im_end|>": 151645,
27
+ "<|im_start|>": 151644,
28
+ "<|image_pad|>": 151655,
29
+ "<|object_ref_end|>": 151647,
30
+ "<|object_ref_start|>": 151646,
31
+ "<|quad_end|>": 151651,
32
+ "<|quad_start|>": 151650,
33
+ "<|repo_name|>": 151663,
34
+ "<|video_pad|>": 151656,
35
+ "<|vision_end|>": 151653,
36
+ "<|vision_pad|>": 151654,
37
+ "<|vision_start|>": 151652
38
+ }
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
+ ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
+ ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "InternVLForConditionalGeneration"
4
+ ],
5
+ "downsample_ratio": 0.5,
6
+ "dtype": "bfloat16",
7
+ "image_seq_length": 256,
8
+ "image_token_id": 151671,
9
+ "model_type": "internvl",
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "_name_or_path": "/root/codespace/checkpoints/Qwen3-8B",
13
+ "architectures": [
14
+ "Qwen3ForCausalLM"
15
+ ],
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "bos_token_id": 151643,
19
+ "debug": false,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": 151645,
22
+ "ep_size": 1,
23
+ "head_dim": 128,
24
+ "hidden_act": "silu",
25
+ "hidden_size": 4096,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 12288,
28
+ "layer_types": [
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention"
65
+ ],
66
+ "max_position_embeddings": 40960,
67
+ "max_window_layers": 36,
68
+ "micro_forward": false,
69
+ "model_type": "qwen3",
70
+ "num_attention_heads": 32,
71
+ "num_hidden_layers": 36,
72
+ "num_key_value_heads": 8,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000,
76
+ "skip_checkpoint": false,
77
+ "sliding_window": null,
78
+ "use_cache": true,
79
+ "use_deepep": false,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 151936
82
+ },
83
+ "transformers_version": "4.56.1",
84
+ "use_cache": false,
85
+ "vision_config": {
86
+ "architectures": [
87
+ "InternVisionModel"
88
+ ],
89
+ "attention_bias": true,
90
+ "attention_dropout": 0.0,
91
+ "dropout": 0.0,
92
+ "dtype": "bfloat16",
93
+ "hidden_act": "gelu",
94
+ "hidden_dropout_prob": 0.0,
95
+ "hidden_size": 1024,
96
+ "image_size": [
97
+ 448,
98
+ 448
99
+ ],
100
+ "initializer_factor": 0.1,
101
+ "initializer_range": 1e-10,
102
+ "intermediate_size": 4096,
103
+ "layer_norm_eps": 1e-06,
104
+ "layer_scale_init_value": 0.1,
105
+ "model_type": "internvl_vision",
106
+ "norm_type": "layer_norm",
107
+ "num_attention_heads": 16,
108
+ "num_channels": 3,
109
+ "num_hidden_layers": 24,
110
+ "patch_size": [
111
+ 14,
112
+ 14
113
+ ],
114
+ "projection_dropout": 0.0,
115
+ "use_absolute_position_embeddings": true,
116
+ "use_mask_token": false,
117
+ "use_mean_pooling": true,
118
+ "use_qk_norm": false
119
+ },
120
+ "vision_feature_layer": -1,
121
+ "vision_feature_select_strategy": "default"
122
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.56.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574c473de2110b4d981414f0bd314e462a5089d1e4ccfde087bd95ba0654bdc1
3
+ size 4906355392
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fae19e38adc33ad2b881b9ee3491091ed2e0bc59d34ad076f5d94c92c98776e
3
+ size 4915962480
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7028de344e6e15f1a9afc84f91d1a40c674d60d0e3ca65ea2cac41734a5d18b
3
+ size 4915962496
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f7bc222f32d4a25a467c835d9b4bc39e05b4fd2b7db0939e87372911b9f29a
3
+ size 2318463688
model.safetensors.index.json ADDED
@@ -0,0 +1,849 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8528318464,
4
+ "total_size": 17056636928
5
+ },
6
+ "weight_map": {
7
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
119
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
120
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
121
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
122
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
123
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
130
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
131
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
136
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
137
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
138
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
139
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
140
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
147
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
150
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
152
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
155
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
158
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
159
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
160
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
161
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
162
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
163
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
217
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
218
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
251
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
254
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
255
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
261
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
262
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
275
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
276
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
277
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "language_model.model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
279
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
280
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
281
+ "language_model.model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
282
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
283
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
+ "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
285
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
286
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
287
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
288
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "language_model.model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
290
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
291
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
292
+ "language_model.model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
293
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
+ "language_model.model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
296
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
297
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
298
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
299
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "language_model.model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
301
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
+ "language_model.model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
304
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
306
+ "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
307
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
308
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
309
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
310
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
311
+ "language_model.model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
312
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
313
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
314
+ "language_model.model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
315
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
316
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
317
+ "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
318
+ "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
319
+ "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
320
+ "language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
321
+ "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
322
+ "language_model.model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
323
+ "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
324
+ "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
325
+ "language_model.model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
326
+ "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
327
+ "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
328
+ "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
329
+ "language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
330
+ "language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
331
+ "language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
332
+ "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "language_model.model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
334
+ "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
335
+ "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
336
+ "language_model.model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
337
+ "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
338
+ "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
339
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
340
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
341
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
342
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
343
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
344
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
345
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
348
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
356
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
357
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
358
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
359
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
360
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
362
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
365
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
366
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
367
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
368
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
369
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
370
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
371
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
372
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
373
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
374
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
375
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
376
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
377
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
378
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
380
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
381
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
383
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
384
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
385
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
386
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
387
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
388
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
389
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
390
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
391
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
392
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
393
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
394
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
397
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
400
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
401
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
402
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
403
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
404
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
405
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
406
+ "multi_modal_projector.layer_norm.bias": "model-00001-of-00004.safetensors",
407
+ "multi_modal_projector.layer_norm.weight": "model-00001-of-00004.safetensors",
408
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
409
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
410
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
411
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
412
+ "vision_tower.embeddings.cls_token": "model-00001-of-00004.safetensors",
413
+ "vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00004.safetensors",
414
+ "vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00004.safetensors",
415
+ "vision_tower.embeddings.position_embeddings": "model-00001-of-00004.safetensors",
416
+ "vision_tower.encoder.layer.0.attention.k_proj.bias": "model-00001-of-00004.safetensors",
417
+ "vision_tower.encoder.layer.0.attention.k_proj.weight": "model-00001-of-00004.safetensors",
418
+ "vision_tower.encoder.layer.0.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
419
+ "vision_tower.encoder.layer.0.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
420
+ "vision_tower.encoder.layer.0.attention.q_proj.bias": "model-00001-of-00004.safetensors",
421
+ "vision_tower.encoder.layer.0.attention.q_proj.weight": "model-00001-of-00004.safetensors",
422
+ "vision_tower.encoder.layer.0.attention.v_proj.bias": "model-00001-of-00004.safetensors",
423
+ "vision_tower.encoder.layer.0.attention.v_proj.weight": "model-00001-of-00004.safetensors",
424
+ "vision_tower.encoder.layer.0.lambda_1": "model-00001-of-00004.safetensors",
425
+ "vision_tower.encoder.layer.0.lambda_2": "model-00001-of-00004.safetensors",
426
+ "vision_tower.encoder.layer.0.layernorm_after.bias": "model-00001-of-00004.safetensors",
427
+ "vision_tower.encoder.layer.0.layernorm_after.weight": "model-00001-of-00004.safetensors",
428
+ "vision_tower.encoder.layer.0.layernorm_before.bias": "model-00001-of-00004.safetensors",
429
+ "vision_tower.encoder.layer.0.layernorm_before.weight": "model-00001-of-00004.safetensors",
430
+ "vision_tower.encoder.layer.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
431
+ "vision_tower.encoder.layer.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
432
+ "vision_tower.encoder.layer.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
433
+ "vision_tower.encoder.layer.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
434
+ "vision_tower.encoder.layer.1.attention.k_proj.bias": "model-00001-of-00004.safetensors",
435
+ "vision_tower.encoder.layer.1.attention.k_proj.weight": "model-00001-of-00004.safetensors",
436
+ "vision_tower.encoder.layer.1.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
437
+ "vision_tower.encoder.layer.1.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
438
+ "vision_tower.encoder.layer.1.attention.q_proj.bias": "model-00001-of-00004.safetensors",
439
+ "vision_tower.encoder.layer.1.attention.q_proj.weight": "model-00001-of-00004.safetensors",
440
+ "vision_tower.encoder.layer.1.attention.v_proj.bias": "model-00001-of-00004.safetensors",
441
+ "vision_tower.encoder.layer.1.attention.v_proj.weight": "model-00001-of-00004.safetensors",
442
+ "vision_tower.encoder.layer.1.lambda_1": "model-00001-of-00004.safetensors",
443
+ "vision_tower.encoder.layer.1.lambda_2": "model-00001-of-00004.safetensors",
444
+ "vision_tower.encoder.layer.1.layernorm_after.bias": "model-00001-of-00004.safetensors",
445
+ "vision_tower.encoder.layer.1.layernorm_after.weight": "model-00001-of-00004.safetensors",
446
+ "vision_tower.encoder.layer.1.layernorm_before.bias": "model-00001-of-00004.safetensors",
447
+ "vision_tower.encoder.layer.1.layernorm_before.weight": "model-00001-of-00004.safetensors",
448
+ "vision_tower.encoder.layer.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
449
+ "vision_tower.encoder.layer.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
450
+ "vision_tower.encoder.layer.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
451
+ "vision_tower.encoder.layer.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
452
+ "vision_tower.encoder.layer.10.attention.k_proj.bias": "model-00001-of-00004.safetensors",
453
+ "vision_tower.encoder.layer.10.attention.k_proj.weight": "model-00001-of-00004.safetensors",
454
+ "vision_tower.encoder.layer.10.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
455
+ "vision_tower.encoder.layer.10.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
456
+ "vision_tower.encoder.layer.10.attention.q_proj.bias": "model-00001-of-00004.safetensors",
457
+ "vision_tower.encoder.layer.10.attention.q_proj.weight": "model-00001-of-00004.safetensors",
458
+ "vision_tower.encoder.layer.10.attention.v_proj.bias": "model-00001-of-00004.safetensors",
459
+ "vision_tower.encoder.layer.10.attention.v_proj.weight": "model-00001-of-00004.safetensors",
460
+ "vision_tower.encoder.layer.10.lambda_1": "model-00001-of-00004.safetensors",
461
+ "vision_tower.encoder.layer.10.lambda_2": "model-00001-of-00004.safetensors",
462
+ "vision_tower.encoder.layer.10.layernorm_after.bias": "model-00001-of-00004.safetensors",
463
+ "vision_tower.encoder.layer.10.layernorm_after.weight": "model-00001-of-00004.safetensors",
464
+ "vision_tower.encoder.layer.10.layernorm_before.bias": "model-00001-of-00004.safetensors",
465
+ "vision_tower.encoder.layer.10.layernorm_before.weight": "model-00001-of-00004.safetensors",
466
+ "vision_tower.encoder.layer.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
467
+ "vision_tower.encoder.layer.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
468
+ "vision_tower.encoder.layer.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
469
+ "vision_tower.encoder.layer.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
470
+ "vision_tower.encoder.layer.11.attention.k_proj.bias": "model-00001-of-00004.safetensors",
471
+ "vision_tower.encoder.layer.11.attention.k_proj.weight": "model-00001-of-00004.safetensors",
472
+ "vision_tower.encoder.layer.11.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
473
+ "vision_tower.encoder.layer.11.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
474
+ "vision_tower.encoder.layer.11.attention.q_proj.bias": "model-00001-of-00004.safetensors",
475
+ "vision_tower.encoder.layer.11.attention.q_proj.weight": "model-00001-of-00004.safetensors",
476
+ "vision_tower.encoder.layer.11.attention.v_proj.bias": "model-00001-of-00004.safetensors",
477
+ "vision_tower.encoder.layer.11.attention.v_proj.weight": "model-00001-of-00004.safetensors",
478
+ "vision_tower.encoder.layer.11.lambda_1": "model-00001-of-00004.safetensors",
479
+ "vision_tower.encoder.layer.11.lambda_2": "model-00001-of-00004.safetensors",
480
+ "vision_tower.encoder.layer.11.layernorm_after.bias": "model-00001-of-00004.safetensors",
481
+ "vision_tower.encoder.layer.11.layernorm_after.weight": "model-00001-of-00004.safetensors",
482
+ "vision_tower.encoder.layer.11.layernorm_before.bias": "model-00001-of-00004.safetensors",
483
+ "vision_tower.encoder.layer.11.layernorm_before.weight": "model-00001-of-00004.safetensors",
484
+ "vision_tower.encoder.layer.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
485
+ "vision_tower.encoder.layer.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
486
+ "vision_tower.encoder.layer.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
487
+ "vision_tower.encoder.layer.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
488
+ "vision_tower.encoder.layer.12.attention.k_proj.bias": "model-00001-of-00004.safetensors",
489
+ "vision_tower.encoder.layer.12.attention.k_proj.weight": "model-00001-of-00004.safetensors",
490
+ "vision_tower.encoder.layer.12.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
491
+ "vision_tower.encoder.layer.12.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
492
+ "vision_tower.encoder.layer.12.attention.q_proj.bias": "model-00001-of-00004.safetensors",
493
+ "vision_tower.encoder.layer.12.attention.q_proj.weight": "model-00001-of-00004.safetensors",
494
+ "vision_tower.encoder.layer.12.attention.v_proj.bias": "model-00001-of-00004.safetensors",
495
+ "vision_tower.encoder.layer.12.attention.v_proj.weight": "model-00001-of-00004.safetensors",
496
+ "vision_tower.encoder.layer.12.lambda_1": "model-00001-of-00004.safetensors",
497
+ "vision_tower.encoder.layer.12.lambda_2": "model-00001-of-00004.safetensors",
498
+ "vision_tower.encoder.layer.12.layernorm_after.bias": "model-00001-of-00004.safetensors",
499
+ "vision_tower.encoder.layer.12.layernorm_after.weight": "model-00001-of-00004.safetensors",
500
+ "vision_tower.encoder.layer.12.layernorm_before.bias": "model-00001-of-00004.safetensors",
501
+ "vision_tower.encoder.layer.12.layernorm_before.weight": "model-00001-of-00004.safetensors",
502
+ "vision_tower.encoder.layer.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
503
+ "vision_tower.encoder.layer.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
504
+ "vision_tower.encoder.layer.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
505
+ "vision_tower.encoder.layer.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
506
+ "vision_tower.encoder.layer.13.attention.k_proj.bias": "model-00001-of-00004.safetensors",
507
+ "vision_tower.encoder.layer.13.attention.k_proj.weight": "model-00001-of-00004.safetensors",
508
+ "vision_tower.encoder.layer.13.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
509
+ "vision_tower.encoder.layer.13.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
510
+ "vision_tower.encoder.layer.13.attention.q_proj.bias": "model-00001-of-00004.safetensors",
511
+ "vision_tower.encoder.layer.13.attention.q_proj.weight": "model-00001-of-00004.safetensors",
512
+ "vision_tower.encoder.layer.13.attention.v_proj.bias": "model-00001-of-00004.safetensors",
513
+ "vision_tower.encoder.layer.13.attention.v_proj.weight": "model-00001-of-00004.safetensors",
514
+ "vision_tower.encoder.layer.13.lambda_1": "model-00001-of-00004.safetensors",
515
+ "vision_tower.encoder.layer.13.lambda_2": "model-00001-of-00004.safetensors",
516
+ "vision_tower.encoder.layer.13.layernorm_after.bias": "model-00001-of-00004.safetensors",
517
+ "vision_tower.encoder.layer.13.layernorm_after.weight": "model-00001-of-00004.safetensors",
518
+ "vision_tower.encoder.layer.13.layernorm_before.bias": "model-00001-of-00004.safetensors",
519
+ "vision_tower.encoder.layer.13.layernorm_before.weight": "model-00001-of-00004.safetensors",
520
+ "vision_tower.encoder.layer.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
521
+ "vision_tower.encoder.layer.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
522
+ "vision_tower.encoder.layer.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
523
+ "vision_tower.encoder.layer.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
524
+ "vision_tower.encoder.layer.14.attention.k_proj.bias": "model-00001-of-00004.safetensors",
525
+ "vision_tower.encoder.layer.14.attention.k_proj.weight": "model-00001-of-00004.safetensors",
526
+ "vision_tower.encoder.layer.14.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
527
+ "vision_tower.encoder.layer.14.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
528
+ "vision_tower.encoder.layer.14.attention.q_proj.bias": "model-00001-of-00004.safetensors",
529
+ "vision_tower.encoder.layer.14.attention.q_proj.weight": "model-00001-of-00004.safetensors",
530
+ "vision_tower.encoder.layer.14.attention.v_proj.bias": "model-00001-of-00004.safetensors",
531
+ "vision_tower.encoder.layer.14.attention.v_proj.weight": "model-00001-of-00004.safetensors",
532
+ "vision_tower.encoder.layer.14.lambda_1": "model-00001-of-00004.safetensors",
533
+ "vision_tower.encoder.layer.14.lambda_2": "model-00001-of-00004.safetensors",
534
+ "vision_tower.encoder.layer.14.layernorm_after.bias": "model-00001-of-00004.safetensors",
535
+ "vision_tower.encoder.layer.14.layernorm_after.weight": "model-00001-of-00004.safetensors",
536
+ "vision_tower.encoder.layer.14.layernorm_before.bias": "model-00001-of-00004.safetensors",
537
+ "vision_tower.encoder.layer.14.layernorm_before.weight": "model-00001-of-00004.safetensors",
538
+ "vision_tower.encoder.layer.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
539
+ "vision_tower.encoder.layer.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
540
+ "vision_tower.encoder.layer.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
541
+ "vision_tower.encoder.layer.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
542
+ "vision_tower.encoder.layer.15.attention.k_proj.bias": "model-00001-of-00004.safetensors",
543
+ "vision_tower.encoder.layer.15.attention.k_proj.weight": "model-00001-of-00004.safetensors",
544
+ "vision_tower.encoder.layer.15.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
545
+ "vision_tower.encoder.layer.15.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
546
+ "vision_tower.encoder.layer.15.attention.q_proj.bias": "model-00001-of-00004.safetensors",
547
+ "vision_tower.encoder.layer.15.attention.q_proj.weight": "model-00001-of-00004.safetensors",
548
+ "vision_tower.encoder.layer.15.attention.v_proj.bias": "model-00001-of-00004.safetensors",
549
+ "vision_tower.encoder.layer.15.attention.v_proj.weight": "model-00001-of-00004.safetensors",
550
+ "vision_tower.encoder.layer.15.lambda_1": "model-00001-of-00004.safetensors",
551
+ "vision_tower.encoder.layer.15.lambda_2": "model-00001-of-00004.safetensors",
552
+ "vision_tower.encoder.layer.15.layernorm_after.bias": "model-00001-of-00004.safetensors",
553
+ "vision_tower.encoder.layer.15.layernorm_after.weight": "model-00001-of-00004.safetensors",
554
+ "vision_tower.encoder.layer.15.layernorm_before.bias": "model-00001-of-00004.safetensors",
555
+ "vision_tower.encoder.layer.15.layernorm_before.weight": "model-00001-of-00004.safetensors",
556
+ "vision_tower.encoder.layer.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
557
+ "vision_tower.encoder.layer.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
558
+ "vision_tower.encoder.layer.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
559
+ "vision_tower.encoder.layer.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
560
+ "vision_tower.encoder.layer.16.attention.k_proj.bias": "model-00001-of-00004.safetensors",
561
+ "vision_tower.encoder.layer.16.attention.k_proj.weight": "model-00001-of-00004.safetensors",
562
+ "vision_tower.encoder.layer.16.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
563
+ "vision_tower.encoder.layer.16.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
564
+ "vision_tower.encoder.layer.16.attention.q_proj.bias": "model-00001-of-00004.safetensors",
565
+ "vision_tower.encoder.layer.16.attention.q_proj.weight": "model-00001-of-00004.safetensors",
566
+ "vision_tower.encoder.layer.16.attention.v_proj.bias": "model-00001-of-00004.safetensors",
567
+ "vision_tower.encoder.layer.16.attention.v_proj.weight": "model-00001-of-00004.safetensors",
568
+ "vision_tower.encoder.layer.16.lambda_1": "model-00001-of-00004.safetensors",
569
+ "vision_tower.encoder.layer.16.lambda_2": "model-00001-of-00004.safetensors",
570
+ "vision_tower.encoder.layer.16.layernorm_after.bias": "model-00001-of-00004.safetensors",
571
+ "vision_tower.encoder.layer.16.layernorm_after.weight": "model-00001-of-00004.safetensors",
572
+ "vision_tower.encoder.layer.16.layernorm_before.bias": "model-00001-of-00004.safetensors",
573
+ "vision_tower.encoder.layer.16.layernorm_before.weight": "model-00001-of-00004.safetensors",
574
+ "vision_tower.encoder.layer.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
575
+ "vision_tower.encoder.layer.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
576
+ "vision_tower.encoder.layer.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
577
+ "vision_tower.encoder.layer.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
578
+ "vision_tower.encoder.layer.17.attention.k_proj.bias": "model-00001-of-00004.safetensors",
579
+ "vision_tower.encoder.layer.17.attention.k_proj.weight": "model-00001-of-00004.safetensors",
580
+ "vision_tower.encoder.layer.17.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
581
+ "vision_tower.encoder.layer.17.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
582
+ "vision_tower.encoder.layer.17.attention.q_proj.bias": "model-00001-of-00004.safetensors",
583
+ "vision_tower.encoder.layer.17.attention.q_proj.weight": "model-00001-of-00004.safetensors",
584
+ "vision_tower.encoder.layer.17.attention.v_proj.bias": "model-00001-of-00004.safetensors",
585
+ "vision_tower.encoder.layer.17.attention.v_proj.weight": "model-00001-of-00004.safetensors",
586
+ "vision_tower.encoder.layer.17.lambda_1": "model-00001-of-00004.safetensors",
587
+ "vision_tower.encoder.layer.17.lambda_2": "model-00001-of-00004.safetensors",
588
+ "vision_tower.encoder.layer.17.layernorm_after.bias": "model-00001-of-00004.safetensors",
589
+ "vision_tower.encoder.layer.17.layernorm_after.weight": "model-00001-of-00004.safetensors",
590
+ "vision_tower.encoder.layer.17.layernorm_before.bias": "model-00001-of-00004.safetensors",
591
+ "vision_tower.encoder.layer.17.layernorm_before.weight": "model-00001-of-00004.safetensors",
592
+ "vision_tower.encoder.layer.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
593
+ "vision_tower.encoder.layer.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
594
+ "vision_tower.encoder.layer.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
595
+ "vision_tower.encoder.layer.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
596
+ "vision_tower.encoder.layer.18.attention.k_proj.bias": "model-00001-of-00004.safetensors",
597
+ "vision_tower.encoder.layer.18.attention.k_proj.weight": "model-00001-of-00004.safetensors",
598
+ "vision_tower.encoder.layer.18.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
599
+ "vision_tower.encoder.layer.18.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
600
+ "vision_tower.encoder.layer.18.attention.q_proj.bias": "model-00001-of-00004.safetensors",
601
+ "vision_tower.encoder.layer.18.attention.q_proj.weight": "model-00001-of-00004.safetensors",
602
+ "vision_tower.encoder.layer.18.attention.v_proj.bias": "model-00001-of-00004.safetensors",
603
+ "vision_tower.encoder.layer.18.attention.v_proj.weight": "model-00001-of-00004.safetensors",
604
+ "vision_tower.encoder.layer.18.lambda_1": "model-00001-of-00004.safetensors",
605
+ "vision_tower.encoder.layer.18.lambda_2": "model-00001-of-00004.safetensors",
606
+ "vision_tower.encoder.layer.18.layernorm_after.bias": "model-00001-of-00004.safetensors",
607
+ "vision_tower.encoder.layer.18.layernorm_after.weight": "model-00001-of-00004.safetensors",
608
+ "vision_tower.encoder.layer.18.layernorm_before.bias": "model-00001-of-00004.safetensors",
609
+ "vision_tower.encoder.layer.18.layernorm_before.weight": "model-00001-of-00004.safetensors",
610
+ "vision_tower.encoder.layer.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
611
+ "vision_tower.encoder.layer.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
612
+ "vision_tower.encoder.layer.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
613
+ "vision_tower.encoder.layer.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
614
+ "vision_tower.encoder.layer.19.attention.k_proj.bias": "model-00001-of-00004.safetensors",
615
+ "vision_tower.encoder.layer.19.attention.k_proj.weight": "model-00001-of-00004.safetensors",
616
+ "vision_tower.encoder.layer.19.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
617
+ "vision_tower.encoder.layer.19.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
618
+ "vision_tower.encoder.layer.19.attention.q_proj.bias": "model-00001-of-00004.safetensors",
619
+ "vision_tower.encoder.layer.19.attention.q_proj.weight": "model-00001-of-00004.safetensors",
620
+ "vision_tower.encoder.layer.19.attention.v_proj.bias": "model-00001-of-00004.safetensors",
621
+ "vision_tower.encoder.layer.19.attention.v_proj.weight": "model-00001-of-00004.safetensors",
622
+ "vision_tower.encoder.layer.19.lambda_1": "model-00001-of-00004.safetensors",
623
+ "vision_tower.encoder.layer.19.lambda_2": "model-00001-of-00004.safetensors",
624
+ "vision_tower.encoder.layer.19.layernorm_after.bias": "model-00001-of-00004.safetensors",
625
+ "vision_tower.encoder.layer.19.layernorm_after.weight": "model-00001-of-00004.safetensors",
626
+ "vision_tower.encoder.layer.19.layernorm_before.bias": "model-00001-of-00004.safetensors",
627
+ "vision_tower.encoder.layer.19.layernorm_before.weight": "model-00001-of-00004.safetensors",
628
+ "vision_tower.encoder.layer.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
629
+ "vision_tower.encoder.layer.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
630
+ "vision_tower.encoder.layer.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
631
+ "vision_tower.encoder.layer.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
632
+ "vision_tower.encoder.layer.2.attention.k_proj.bias": "model-00001-of-00004.safetensors",
633
+ "vision_tower.encoder.layer.2.attention.k_proj.weight": "model-00001-of-00004.safetensors",
634
+ "vision_tower.encoder.layer.2.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
635
+ "vision_tower.encoder.layer.2.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
636
+ "vision_tower.encoder.layer.2.attention.q_proj.bias": "model-00001-of-00004.safetensors",
637
+ "vision_tower.encoder.layer.2.attention.q_proj.weight": "model-00001-of-00004.safetensors",
638
+ "vision_tower.encoder.layer.2.attention.v_proj.bias": "model-00001-of-00004.safetensors",
639
+ "vision_tower.encoder.layer.2.attention.v_proj.weight": "model-00001-of-00004.safetensors",
640
+ "vision_tower.encoder.layer.2.lambda_1": "model-00001-of-00004.safetensors",
641
+ "vision_tower.encoder.layer.2.lambda_2": "model-00001-of-00004.safetensors",
642
+ "vision_tower.encoder.layer.2.layernorm_after.bias": "model-00001-of-00004.safetensors",
643
+ "vision_tower.encoder.layer.2.layernorm_after.weight": "model-00001-of-00004.safetensors",
644
+ "vision_tower.encoder.layer.2.layernorm_before.bias": "model-00001-of-00004.safetensors",
645
+ "vision_tower.encoder.layer.2.layernorm_before.weight": "model-00001-of-00004.safetensors",
646
+ "vision_tower.encoder.layer.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
647
+ "vision_tower.encoder.layer.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
648
+ "vision_tower.encoder.layer.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
649
+ "vision_tower.encoder.layer.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
650
+ "vision_tower.encoder.layer.20.attention.k_proj.bias": "model-00001-of-00004.safetensors",
651
+ "vision_tower.encoder.layer.20.attention.k_proj.weight": "model-00001-of-00004.safetensors",
652
+ "vision_tower.encoder.layer.20.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
653
+ "vision_tower.encoder.layer.20.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
654
+ "vision_tower.encoder.layer.20.attention.q_proj.bias": "model-00001-of-00004.safetensors",
655
+ "vision_tower.encoder.layer.20.attention.q_proj.weight": "model-00001-of-00004.safetensors",
656
+ "vision_tower.encoder.layer.20.attention.v_proj.bias": "model-00001-of-00004.safetensors",
657
+ "vision_tower.encoder.layer.20.attention.v_proj.weight": "model-00001-of-00004.safetensors",
658
+ "vision_tower.encoder.layer.20.lambda_1": "model-00001-of-00004.safetensors",
659
+ "vision_tower.encoder.layer.20.lambda_2": "model-00001-of-00004.safetensors",
660
+ "vision_tower.encoder.layer.20.layernorm_after.bias": "model-00001-of-00004.safetensors",
661
+ "vision_tower.encoder.layer.20.layernorm_after.weight": "model-00001-of-00004.safetensors",
662
+ "vision_tower.encoder.layer.20.layernorm_before.bias": "model-00001-of-00004.safetensors",
663
+ "vision_tower.encoder.layer.20.layernorm_before.weight": "model-00001-of-00004.safetensors",
664
+ "vision_tower.encoder.layer.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
665
+ "vision_tower.encoder.layer.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
666
+ "vision_tower.encoder.layer.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
667
+ "vision_tower.encoder.layer.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
668
+ "vision_tower.encoder.layer.21.attention.k_proj.bias": "model-00001-of-00004.safetensors",
669
+ "vision_tower.encoder.layer.21.attention.k_proj.weight": "model-00001-of-00004.safetensors",
670
+ "vision_tower.encoder.layer.21.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
671
+ "vision_tower.encoder.layer.21.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
672
+ "vision_tower.encoder.layer.21.attention.q_proj.bias": "model-00001-of-00004.safetensors",
673
+ "vision_tower.encoder.layer.21.attention.q_proj.weight": "model-00001-of-00004.safetensors",
674
+ "vision_tower.encoder.layer.21.attention.v_proj.bias": "model-00001-of-00004.safetensors",
675
+ "vision_tower.encoder.layer.21.attention.v_proj.weight": "model-00001-of-00004.safetensors",
676
+ "vision_tower.encoder.layer.21.lambda_1": "model-00001-of-00004.safetensors",
677
+ "vision_tower.encoder.layer.21.lambda_2": "model-00001-of-00004.safetensors",
678
+ "vision_tower.encoder.layer.21.layernorm_after.bias": "model-00001-of-00004.safetensors",
679
+ "vision_tower.encoder.layer.21.layernorm_after.weight": "model-00001-of-00004.safetensors",
680
+ "vision_tower.encoder.layer.21.layernorm_before.bias": "model-00001-of-00004.safetensors",
681
+ "vision_tower.encoder.layer.21.layernorm_before.weight": "model-00001-of-00004.safetensors",
682
+ "vision_tower.encoder.layer.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
683
+ "vision_tower.encoder.layer.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
684
+ "vision_tower.encoder.layer.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
685
+ "vision_tower.encoder.layer.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
686
+ "vision_tower.encoder.layer.22.attention.k_proj.bias": "model-00001-of-00004.safetensors",
687
+ "vision_tower.encoder.layer.22.attention.k_proj.weight": "model-00001-of-00004.safetensors",
688
+ "vision_tower.encoder.layer.22.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
689
+ "vision_tower.encoder.layer.22.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
690
+ "vision_tower.encoder.layer.22.attention.q_proj.bias": "model-00001-of-00004.safetensors",
691
+ "vision_tower.encoder.layer.22.attention.q_proj.weight": "model-00001-of-00004.safetensors",
692
+ "vision_tower.encoder.layer.22.attention.v_proj.bias": "model-00001-of-00004.safetensors",
693
+ "vision_tower.encoder.layer.22.attention.v_proj.weight": "model-00001-of-00004.safetensors",
694
+ "vision_tower.encoder.layer.22.lambda_1": "model-00001-of-00004.safetensors",
695
+ "vision_tower.encoder.layer.22.lambda_2": "model-00001-of-00004.safetensors",
696
+ "vision_tower.encoder.layer.22.layernorm_after.bias": "model-00001-of-00004.safetensors",
697
+ "vision_tower.encoder.layer.22.layernorm_after.weight": "model-00001-of-00004.safetensors",
698
+ "vision_tower.encoder.layer.22.layernorm_before.bias": "model-00001-of-00004.safetensors",
699
+ "vision_tower.encoder.layer.22.layernorm_before.weight": "model-00001-of-00004.safetensors",
700
+ "vision_tower.encoder.layer.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
701
+ "vision_tower.encoder.layer.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
702
+ "vision_tower.encoder.layer.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
703
+ "vision_tower.encoder.layer.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
704
+ "vision_tower.encoder.layer.23.attention.k_proj.bias": "model-00001-of-00004.safetensors",
705
+ "vision_tower.encoder.layer.23.attention.k_proj.weight": "model-00001-of-00004.safetensors",
706
+ "vision_tower.encoder.layer.23.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
707
+ "vision_tower.encoder.layer.23.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
708
+ "vision_tower.encoder.layer.23.attention.q_proj.bias": "model-00001-of-00004.safetensors",
709
+ "vision_tower.encoder.layer.23.attention.q_proj.weight": "model-00001-of-00004.safetensors",
710
+ "vision_tower.encoder.layer.23.attention.v_proj.bias": "model-00001-of-00004.safetensors",
711
+ "vision_tower.encoder.layer.23.attention.v_proj.weight": "model-00001-of-00004.safetensors",
712
+ "vision_tower.encoder.layer.23.lambda_1": "model-00001-of-00004.safetensors",
713
+ "vision_tower.encoder.layer.23.lambda_2": "model-00001-of-00004.safetensors",
714
+ "vision_tower.encoder.layer.23.layernorm_after.bias": "model-00001-of-00004.safetensors",
715
+ "vision_tower.encoder.layer.23.layernorm_after.weight": "model-00001-of-00004.safetensors",
716
+ "vision_tower.encoder.layer.23.layernorm_before.bias": "model-00001-of-00004.safetensors",
717
+ "vision_tower.encoder.layer.23.layernorm_before.weight": "model-00001-of-00004.safetensors",
718
+ "vision_tower.encoder.layer.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
719
+ "vision_tower.encoder.layer.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
720
+ "vision_tower.encoder.layer.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
721
+ "vision_tower.encoder.layer.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
722
+ "vision_tower.encoder.layer.3.attention.k_proj.bias": "model-00001-of-00004.safetensors",
723
+ "vision_tower.encoder.layer.3.attention.k_proj.weight": "model-00001-of-00004.safetensors",
724
+ "vision_tower.encoder.layer.3.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
725
+ "vision_tower.encoder.layer.3.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
726
+ "vision_tower.encoder.layer.3.attention.q_proj.bias": "model-00001-of-00004.safetensors",
727
+ "vision_tower.encoder.layer.3.attention.q_proj.weight": "model-00001-of-00004.safetensors",
728
+ "vision_tower.encoder.layer.3.attention.v_proj.bias": "model-00001-of-00004.safetensors",
729
+ "vision_tower.encoder.layer.3.attention.v_proj.weight": "model-00001-of-00004.safetensors",
730
+ "vision_tower.encoder.layer.3.lambda_1": "model-00001-of-00004.safetensors",
731
+ "vision_tower.encoder.layer.3.lambda_2": "model-00001-of-00004.safetensors",
732
+ "vision_tower.encoder.layer.3.layernorm_after.bias": "model-00001-of-00004.safetensors",
733
+ "vision_tower.encoder.layer.3.layernorm_after.weight": "model-00001-of-00004.safetensors",
734
+ "vision_tower.encoder.layer.3.layernorm_before.bias": "model-00001-of-00004.safetensors",
735
+ "vision_tower.encoder.layer.3.layernorm_before.weight": "model-00001-of-00004.safetensors",
736
+ "vision_tower.encoder.layer.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
737
+ "vision_tower.encoder.layer.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
738
+ "vision_tower.encoder.layer.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
739
+ "vision_tower.encoder.layer.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
740
+ "vision_tower.encoder.layer.4.attention.k_proj.bias": "model-00001-of-00004.safetensors",
741
+ "vision_tower.encoder.layer.4.attention.k_proj.weight": "model-00001-of-00004.safetensors",
742
+ "vision_tower.encoder.layer.4.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
743
+ "vision_tower.encoder.layer.4.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
744
+ "vision_tower.encoder.layer.4.attention.q_proj.bias": "model-00001-of-00004.safetensors",
745
+ "vision_tower.encoder.layer.4.attention.q_proj.weight": "model-00001-of-00004.safetensors",
746
+ "vision_tower.encoder.layer.4.attention.v_proj.bias": "model-00001-of-00004.safetensors",
747
+ "vision_tower.encoder.layer.4.attention.v_proj.weight": "model-00001-of-00004.safetensors",
748
+ "vision_tower.encoder.layer.4.lambda_1": "model-00001-of-00004.safetensors",
749
+ "vision_tower.encoder.layer.4.lambda_2": "model-00001-of-00004.safetensors",
750
+ "vision_tower.encoder.layer.4.layernorm_after.bias": "model-00001-of-00004.safetensors",
751
+ "vision_tower.encoder.layer.4.layernorm_after.weight": "model-00001-of-00004.safetensors",
752
+ "vision_tower.encoder.layer.4.layernorm_before.bias": "model-00001-of-00004.safetensors",
753
+ "vision_tower.encoder.layer.4.layernorm_before.weight": "model-00001-of-00004.safetensors",
754
+ "vision_tower.encoder.layer.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
755
+ "vision_tower.encoder.layer.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
756
+ "vision_tower.encoder.layer.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
757
+ "vision_tower.encoder.layer.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
758
+ "vision_tower.encoder.layer.5.attention.k_proj.bias": "model-00001-of-00004.safetensors",
759
+ "vision_tower.encoder.layer.5.attention.k_proj.weight": "model-00001-of-00004.safetensors",
760
+ "vision_tower.encoder.layer.5.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
761
+ "vision_tower.encoder.layer.5.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
762
+ "vision_tower.encoder.layer.5.attention.q_proj.bias": "model-00001-of-00004.safetensors",
763
+ "vision_tower.encoder.layer.5.attention.q_proj.weight": "model-00001-of-00004.safetensors",
764
+ "vision_tower.encoder.layer.5.attention.v_proj.bias": "model-00001-of-00004.safetensors",
765
+ "vision_tower.encoder.layer.5.attention.v_proj.weight": "model-00001-of-00004.safetensors",
766
+ "vision_tower.encoder.layer.5.lambda_1": "model-00001-of-00004.safetensors",
767
+ "vision_tower.encoder.layer.5.lambda_2": "model-00001-of-00004.safetensors",
768
+ "vision_tower.encoder.layer.5.layernorm_after.bias": "model-00001-of-00004.safetensors",
769
+ "vision_tower.encoder.layer.5.layernorm_after.weight": "model-00001-of-00004.safetensors",
770
+ "vision_tower.encoder.layer.5.layernorm_before.bias": "model-00001-of-00004.safetensors",
771
+ "vision_tower.encoder.layer.5.layernorm_before.weight": "model-00001-of-00004.safetensors",
772
+ "vision_tower.encoder.layer.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
773
+ "vision_tower.encoder.layer.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
774
+ "vision_tower.encoder.layer.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
775
+ "vision_tower.encoder.layer.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
776
+ "vision_tower.encoder.layer.6.attention.k_proj.bias": "model-00001-of-00004.safetensors",
777
+ "vision_tower.encoder.layer.6.attention.k_proj.weight": "model-00001-of-00004.safetensors",
778
+ "vision_tower.encoder.layer.6.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
779
+ "vision_tower.encoder.layer.6.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
780
+ "vision_tower.encoder.layer.6.attention.q_proj.bias": "model-00001-of-00004.safetensors",
781
+ "vision_tower.encoder.layer.6.attention.q_proj.weight": "model-00001-of-00004.safetensors",
782
+ "vision_tower.encoder.layer.6.attention.v_proj.bias": "model-00001-of-00004.safetensors",
783
+ "vision_tower.encoder.layer.6.attention.v_proj.weight": "model-00001-of-00004.safetensors",
784
+ "vision_tower.encoder.layer.6.lambda_1": "model-00001-of-00004.safetensors",
785
+ "vision_tower.encoder.layer.6.lambda_2": "model-00001-of-00004.safetensors",
786
+ "vision_tower.encoder.layer.6.layernorm_after.bias": "model-00001-of-00004.safetensors",
787
+ "vision_tower.encoder.layer.6.layernorm_after.weight": "model-00001-of-00004.safetensors",
788
+ "vision_tower.encoder.layer.6.layernorm_before.bias": "model-00001-of-00004.safetensors",
789
+ "vision_tower.encoder.layer.6.layernorm_before.weight": "model-00001-of-00004.safetensors",
790
+ "vision_tower.encoder.layer.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
791
+ "vision_tower.encoder.layer.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
792
+ "vision_tower.encoder.layer.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
793
+ "vision_tower.encoder.layer.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
794
+ "vision_tower.encoder.layer.7.attention.k_proj.bias": "model-00001-of-00004.safetensors",
795
+ "vision_tower.encoder.layer.7.attention.k_proj.weight": "model-00001-of-00004.safetensors",
796
+ "vision_tower.encoder.layer.7.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
797
+ "vision_tower.encoder.layer.7.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
798
+ "vision_tower.encoder.layer.7.attention.q_proj.bias": "model-00001-of-00004.safetensors",
799
+ "vision_tower.encoder.layer.7.attention.q_proj.weight": "model-00001-of-00004.safetensors",
800
+ "vision_tower.encoder.layer.7.attention.v_proj.bias": "model-00001-of-00004.safetensors",
801
+ "vision_tower.encoder.layer.7.attention.v_proj.weight": "model-00001-of-00004.safetensors",
802
+ "vision_tower.encoder.layer.7.lambda_1": "model-00001-of-00004.safetensors",
803
+ "vision_tower.encoder.layer.7.lambda_2": "model-00001-of-00004.safetensors",
804
+ "vision_tower.encoder.layer.7.layernorm_after.bias": "model-00001-of-00004.safetensors",
805
+ "vision_tower.encoder.layer.7.layernorm_after.weight": "model-00001-of-00004.safetensors",
806
+ "vision_tower.encoder.layer.7.layernorm_before.bias": "model-00001-of-00004.safetensors",
807
+ "vision_tower.encoder.layer.7.layernorm_before.weight": "model-00001-of-00004.safetensors",
808
+ "vision_tower.encoder.layer.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
809
+ "vision_tower.encoder.layer.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
810
+ "vision_tower.encoder.layer.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
811
+ "vision_tower.encoder.layer.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
812
+ "vision_tower.encoder.layer.8.attention.k_proj.bias": "model-00001-of-00004.safetensors",
813
+ "vision_tower.encoder.layer.8.attention.k_proj.weight": "model-00001-of-00004.safetensors",
814
+ "vision_tower.encoder.layer.8.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
815
+ "vision_tower.encoder.layer.8.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
816
+ "vision_tower.encoder.layer.8.attention.q_proj.bias": "model-00001-of-00004.safetensors",
817
+ "vision_tower.encoder.layer.8.attention.q_proj.weight": "model-00001-of-00004.safetensors",
818
+ "vision_tower.encoder.layer.8.attention.v_proj.bias": "model-00001-of-00004.safetensors",
819
+ "vision_tower.encoder.layer.8.attention.v_proj.weight": "model-00001-of-00004.safetensors",
820
+ "vision_tower.encoder.layer.8.lambda_1": "model-00001-of-00004.safetensors",
821
+ "vision_tower.encoder.layer.8.lambda_2": "model-00001-of-00004.safetensors",
822
+ "vision_tower.encoder.layer.8.layernorm_after.bias": "model-00001-of-00004.safetensors",
823
+ "vision_tower.encoder.layer.8.layernorm_after.weight": "model-00001-of-00004.safetensors",
824
+ "vision_tower.encoder.layer.8.layernorm_before.bias": "model-00001-of-00004.safetensors",
825
+ "vision_tower.encoder.layer.8.layernorm_before.weight": "model-00001-of-00004.safetensors",
826
+ "vision_tower.encoder.layer.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
827
+ "vision_tower.encoder.layer.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
828
+ "vision_tower.encoder.layer.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
829
+ "vision_tower.encoder.layer.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
830
+ "vision_tower.encoder.layer.9.attention.k_proj.bias": "model-00001-of-00004.safetensors",
831
+ "vision_tower.encoder.layer.9.attention.k_proj.weight": "model-00001-of-00004.safetensors",
832
+ "vision_tower.encoder.layer.9.attention.projection_layer.bias": "model-00001-of-00004.safetensors",
833
+ "vision_tower.encoder.layer.9.attention.projection_layer.weight": "model-00001-of-00004.safetensors",
834
+ "vision_tower.encoder.layer.9.attention.q_proj.bias": "model-00001-of-00004.safetensors",
835
+ "vision_tower.encoder.layer.9.attention.q_proj.weight": "model-00001-of-00004.safetensors",
836
+ "vision_tower.encoder.layer.9.attention.v_proj.bias": "model-00001-of-00004.safetensors",
837
+ "vision_tower.encoder.layer.9.attention.v_proj.weight": "model-00001-of-00004.safetensors",
838
+ "vision_tower.encoder.layer.9.lambda_1": "model-00001-of-00004.safetensors",
839
+ "vision_tower.encoder.layer.9.lambda_2": "model-00001-of-00004.safetensors",
840
+ "vision_tower.encoder.layer.9.layernorm_after.bias": "model-00001-of-00004.safetensors",
841
+ "vision_tower.encoder.layer.9.layernorm_after.weight": "model-00001-of-00004.safetensors",
842
+ "vision_tower.encoder.layer.9.layernorm_before.bias": "model-00001-of-00004.safetensors",
843
+ "vision_tower.encoder.layer.9.layernorm_before.weight": "model-00001-of-00004.safetensors",
844
+ "vision_tower.encoder.layer.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
845
+ "vision_tower.encoder.layer.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
846
+ "vision_tower.encoder.layer.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
847
+ "vision_tower.encoder.layer.9.mlp.fc2.weight": "model-00001-of-00004.safetensors"
848
+ }
849
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "crop_to_patches": false,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "disable_grouping": null,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.485,
15
+ 0.456,
16
+ 0.406
17
+ ],
18
+ "image_processor_type": "GotOcr2ImageProcessorFast",
19
+ "image_std": [
20
+ 0.229,
21
+ 0.224,
22
+ 0.225
23
+ ],
24
+ "input_data_format": null,
25
+ "max_patches": 12,
26
+ "min_patches": 1,
27
+ "processor_class": "InternVLProcessor",
28
+ "resample": 3,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "return_tensors": null,
31
+ "size": {
32
+ "height": 448,
33
+ "width": 448
34
+ }
35
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "InternVLProcessor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<img>",
17
+ "</img>",
18
+ "<IMG_CONTEXT>",
19
+ "<quad>",
20
+ "</quad>",
21
+ "<ref>",
22
+ "</ref>",
23
+ "<box>",
24
+ "</box>"
25
+ ],
26
+ "context_image_token": "<IMG_CONTEXT>",
27
+ "end_image_token": "</img>",
28
+ "eos_token": {
29
+ "content": "<|im_end|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "start_image_token": "<img>",
43
+ "video_token": "<video>"
44
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a533f74ee4dd57d29df7eefa5c0b07d89d4ed9eda82121b2a093a7478e41235a
3
+ size 11424583
tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<tool_response>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "151666": {
191
+ "content": "</tool_response>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "151667": {
199
+ "content": "<think>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "151668": {
207
+ "content": "</think>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "151669": {
215
+ "content": "<img>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "151670": {
223
+ "content": "</img>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "151671": {
231
+ "content": "<IMG_CONTEXT>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "151672": {
239
+ "content": "<quad>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "151673": {
247
+ "content": "</quad>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "151674": {
255
+ "content": "<ref>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "151675": {
263
+ "content": "</ref>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "151676": {
271
+ "content": "<box>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "151677": {
279
+ "content": "</box>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "151678": {
287
+ "content": "<video>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ }
294
+ },
295
+ "additional_special_tokens": [
296
+ "<|im_start|>",
297
+ "<|im_end|>",
298
+ "<|object_ref_start|>",
299
+ "<|object_ref_end|>",
300
+ "<|box_start|>",
301
+ "<|box_end|>",
302
+ "<|quad_start|>",
303
+ "<|quad_end|>",
304
+ "<|vision_start|>",
305
+ "<|vision_end|>",
306
+ "<|vision_pad|>",
307
+ "<|image_pad|>",
308
+ "<|video_pad|>",
309
+ "<img>",
310
+ "</img>",
311
+ "<IMG_CONTEXT>",
312
+ "<quad>",
313
+ "</quad>",
314
+ "<ref>",
315
+ "</ref>",
316
+ "<box>",
317
+ "</box>"
318
+ ],
319
+ "bos_token": null,
320
+ "clean_up_tokenization_spaces": false,
321
+ "context_image_token": "<IMG_CONTEXT>",
322
+ "end_image_token": "</img>",
323
+ "eos_token": "<|im_end|>",
324
+ "errors": "replace",
325
+ "extra_special_tokens": {
326
+ "context_image_token": "<IMG_CONTEXT>",
327
+ "end_image_token": "</img>",
328
+ "start_image_token": "<img>",
329
+ "video_token": "<video>"
330
+ },
331
+ "model_max_length": 40960,
332
+ "pad_token": "<|endoftext|>",
333
+ "processor_class": "InternVLProcessor",
334
+ "split_special_tokens": false,
335
+ "start_image_token": "<img>",
336
+ "tokenizer_class": "Qwen2Tokenizer",
337
+ "unk_token": null,
338
+ "video_token": "<video>"
339
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initial_shift": true,
25
+ "input_data_format": null,
26
+ "num_frames": null,
27
+ "processor_class": "InternVLProcessor",
28
+ "resample": 3,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "return_metadata": false,
31
+ "size": {
32
+ "height": 384,
33
+ "width": 384
34
+ },
35
+ "size_divisor": null,
36
+ "video_metadata": null,
37
+ "video_processor_type": "InternVLVideoProcessor"
38
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff