Hugging Face's logo

HymanH
/
AITQE

Safetensors
mm
Model card Files Community
HymanH commited on
Commit
4489d10
·
verified ·
1 Parent(s): c726238

init commit

Browse files
Files changed (10) hide show
  1. config.json +49 -0
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. model-00001-of-00004.safetensors +3 -0
  5. model-00002-of-00004.safetensors +3 -0
  6. model-00003-of-00004.safetensors +3 -0
  7. model-00004-of-00004.safetensors +3 -0
  8. model.safetensors.index.json +798 -0
  9. tokenizer_config.json +340 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "IGNORE_INDEX": -100,
3
+ "_name_or_path": "aitqe",
4
+ "anyres_max_patch": 6,
5
+ "anyres_overlap_ratio": 7,
6
+ "architectures": [
7
+ "MMForCausalLM"
8
+ ],
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 151643,
12
+ "eos_token_id": 151643,
13
+ "eos_token_index": 151643,
14
+ "frame_pattern": "<frame>",
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3584,
17
+ "image_aspect_ratio": "square",
18
+ "image_pattern": "<image>",
19
+ "image_tile_tokens": 729,
20
+ "image_token_index": 151662,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 18944,
23
+ "language_model_name_or_path": "Qwen/Qwen2-7B",
24
+ "max_position_embeddings": 131072,
25
+ "max_window_layers": 28,
26
+ "mm_projector_type": "mlp",
27
+ "model_type": "mm",
28
+ "num_attention_heads": 28,
29
+ "num_hidden_layers": 28,
30
+ "num_key_value_heads": 4,
31
+ "pad_token_id": 0,
32
+ "pad_token_index": 151672,
33
+ "pesudo_img_size": 384,
34
+ "pesudo_patch_size": 14,
35
+ "pooling_kernel": 1,
36
+ "pretraining_tp": 1,
37
+ "rms_norm_eps": 1e-06,
38
+ "rope_scaling": null,
39
+ "rope_theta": 1000000.0,
40
+ "sliding_window": 131072,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.41.2",
44
+ "use_cache": true,
45
+ "use_sliding_window": false,
46
+ "vision_model_name_or_path": "google/siglip-so400m-patch14-384",
47
+ "visual_hidden_dim": 1152,
48
+ "vocab_size": 152064
49
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
+ }
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 sha256:3da4ffdc6dea5188f308da403626404de30fc32c4e6abd99586550a1a2eb79cf
3
+ size 4877668640
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76542ab80b161222a0b6e0664847a245c2d9c3a703b150eb2dc4fbf411730316
3
+ size 4932751744
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a15396e0cfe94080b693dbf9c3cd496f39485cfdc170306bdf86fb0811ddd5
3
+ size 4330865872
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a4a1abe2ffa042d7926f4bc4c3d18ecf53abdd08d6e200e19edf3a01fbe303
3
+ size 1980462912
model.safetensors.index.json ADDED
@@ -0,0 +1,798 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16121646208
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model-00001-of-00004.safetensors",
7
+ "mm_projector.0.bias": "model-00004-of-00004.safetensors",
8
+ "mm_projector.0.weight": "model-00004-of-00004.safetensors",
9
+ "mm_projector.2.weight": "model-00004-of-00004.safetensors",
10
+ "model.lm_head.weight": "model-00004-of-00004.safetensors",
11
+ "model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
12
+ "model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
21
+ "model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
23
+ "model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
29
+ "model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
33
+ "model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
35
+ "model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
36
+ "model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
45
+ "model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
47
+ "model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
57
+ "model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
59
+ "model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
69
+ "model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
71
+ "model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
81
+ "model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
83
+ "model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
93
+ "model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
95
+ "model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
105
+ "model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
107
+ "model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
117
+ "model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
119
+ "model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
125
+ "model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
129
+ "model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
131
+ "model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
137
+ "model.model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
138
+ "model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
141
+ "model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
142
+ "model.model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
143
+ "model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
144
+ "model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
153
+ "model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
155
+ "model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
158
+ "model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
161
+ "model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
165
+ "model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
166
+ "model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
167
+ "model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
168
+ "model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
177
+ "model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
179
+ "model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
189
+ "model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
191
+ "model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
201
+ "model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
203
+ "model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
209
+ "model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
213
+ "model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
215
+ "model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
225
+ "model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
227
+ "model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
237
+ "model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
239
+ "model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
249
+ "model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
251
+ "model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
257
+ "model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
261
+ "model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
263
+ "model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
264
+ "model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
269
+ "model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
273
+ "model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
275
+ "model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
281
+ "model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
285
+ "model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
287
+ "model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
290
+ "model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
293
+ "model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
297
+ "model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
299
+ "model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
302
+ "model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
305
+ "model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
306
+ "model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
307
+ "model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
309
+ "model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
311
+ "model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
314
+ "model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
317
+ "model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
318
+ "model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
321
+ "model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
322
+ "model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
323
+ "model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
324
+ "model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
326
+ "model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
329
+ "model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
330
+ "model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
333
+ "model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
334
+ "model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
335
+ "model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
336
+ "model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
338
+ "model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
341
+ "model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
345
+ "model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
346
+ "model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
347
+ "model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
348
+ "model.model.norm.weight": "model-00003-of-00004.safetensors",
349
+ "vision_model.vision_model.embeddings.patch_embedding.bias": "model-00004-of-00004.safetensors",
350
+ "vision_model.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
351
+ "vision_model.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
352
+ "vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
353
+ "vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
354
+ "vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
355
+ "vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
356
+ "vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
357
+ "vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
358
+ "vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
359
+ "vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
360
+ "vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
361
+ "vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
362
+ "vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
363
+ "vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
364
+ "vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
365
+ "vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
366
+ "vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
367
+ "vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
368
+ "vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
369
+ "vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
370
+ "vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
371
+ "vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
372
+ "vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
373
+ "vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
374
+ "vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
375
+ "vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
376
+ "vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
377
+ "vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
378
+ "vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
379
+ "vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
380
+ "vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
381
+ "vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
382
+ "vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
383
+ "vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
384
+ "vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
385
+ "vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
386
+ "vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
387
+ "vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
388
+ "vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
389
+ "vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
390
+ "vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
391
+ "vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
392
+ "vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
393
+ "vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
394
+ "vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
395
+ "vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
396
+ "vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
397
+ "vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
398
+ "vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
399
+ "vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
400
+ "vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
401
+ "vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
402
+ "vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
403
+ "vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
404
+ "vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
405
+ "vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
406
+ "vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
407
+ "vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
408
+ "vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
409
+ "vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
410
+ "vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
411
+ "vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
412
+ "vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
413
+ "vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
414
+ "vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
415
+ "vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
416
+ "vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
417
+ "vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
418
+ "vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
419
+ "vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
420
+ "vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
421
+ "vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
422
+ "vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
423
+ "vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
424
+ "vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
425
+ "vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
426
+ "vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
427
+ "vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
428
+ "vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
429
+ "vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
430
+ "vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
431
+ "vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
432
+ "vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
433
+ "vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
434
+ "vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
435
+ "vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
436
+ "vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
437
+ "vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
438
+ "vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
439
+ "vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
440
+ "vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
441
+ "vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
442
+ "vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
443
+ "vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
444
+ "vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
445
+ "vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
446
+ "vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
447
+ "vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
448
+ "vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
449
+ "vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
450
+ "vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
451
+ "vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
452
+ "vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
453
+ "vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
454
+ "vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
455
+ "vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
456
+ "vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
457
+ "vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
458
+ "vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
459
+ "vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
460
+ "vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
461
+ "vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
462
+ "vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
463
+ "vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
464
+ "vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
465
+ "vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
466
+ "vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
467
+ "vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
468
+ "vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
469
+ "vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
470
+ "vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
471
+ "vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
472
+ "vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
473
+ "vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
474
+ "vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
475
+ "vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
476
+ "vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
477
+ "vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
478
+ "vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
479
+ "vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
480
+ "vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
481
+ "vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
482
+ "vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
483
+ "vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
484
+ "vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
485
+ "vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
486
+ "vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
487
+ "vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
488
+ "vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
489
+ "vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
490
+ "vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
491
+ "vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
492
+ "vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
493
+ "vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
494
+ "vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
495
+ "vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
496
+ "vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
497
+ "vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
498
+ "vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
499
+ "vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
500
+ "vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
501
+ "vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
502
+ "vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
503
+ "vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
504
+ "vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
505
+ "vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
506
+ "vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
507
+ "vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
508
+ "vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
509
+ "vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
510
+ "vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
511
+ "vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
512
+ "vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
513
+ "vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
514
+ "vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
515
+ "vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
516
+ "vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
517
+ "vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
518
+ "vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
519
+ "vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
520
+ "vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
521
+ "vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
522
+ "vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
523
+ "vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
524
+ "vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
525
+ "vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
526
+ "vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
527
+ "vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
528
+ "vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
529
+ "vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
530
+ "vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
531
+ "vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
532
+ "vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
533
+ "vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
534
+ "vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
535
+ "vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
536
+ "vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
537
+ "vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
538
+ "vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
539
+ "vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
540
+ "vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
541
+ "vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
542
+ "vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
543
+ "vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
544
+ "vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
545
+ "vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
546
+ "vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
547
+ "vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
548
+ "vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
549
+ "vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
550
+ "vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
551
+ "vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
552
+ "vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
553
+ "vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
554
+ "vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
555
+ "vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
556
+ "vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
557
+ "vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
558
+ "vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
559
+ "vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
560
+ "vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
561
+ "vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
562
+ "vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
563
+ "vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
564
+ "vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
565
+ "vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
566
+ "vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
567
+ "vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
568
+ "vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
569
+ "vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
570
+ "vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
571
+ "vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
572
+ "vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
573
+ "vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
574
+ "vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
575
+ "vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
576
+ "vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
577
+ "vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
578
+ "vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
579
+ "vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
580
+ "vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
581
+ "vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
582
+ "vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
583
+ "vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
584
+ "vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
585
+ "vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
586
+ "vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
587
+ "vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
588
+ "vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
589
+ "vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
590
+ "vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
591
+ "vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
592
+ "vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
593
+ "vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
594
+ "vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
595
+ "vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
596
+ "vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
597
+ "vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
598
+ "vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
599
+ "vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
600
+ "vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
601
+ "vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
602
+ "vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
603
+ "vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
604
+ "vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
605
+ "vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
606
+ "vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
607
+ "vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
608
+ "vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
609
+ "vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
610
+ "vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
611
+ "vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
612
+ "vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
613
+ "vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
614
+ "vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
615
+ "vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
616
+ "vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
617
+ "vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
618
+ "vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
619
+ "vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
620
+ "vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
621
+ "vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
622
+ "vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
623
+ "vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
624
+ "vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
625
+ "vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
626
+ "vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
627
+ "vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
628
+ "vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
629
+ "vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
630
+ "vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
631
+ "vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
632
+ "vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
633
+ "vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
634
+ "vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
635
+ "vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
636
+ "vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
637
+ "vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
638
+ "vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
639
+ "vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
640
+ "vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
641
+ "vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
642
+ "vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
643
+ "vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
644
+ "vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
645
+ "vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
646
+ "vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
647
+ "vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
648
+ "vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
649
+ "vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
650
+ "vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
651
+ "vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
652
+ "vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
653
+ "vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
654
+ "vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
655
+ "vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
656
+ "vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00004-of-00004.safetensors",
657
+ "vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00004-of-00004.safetensors",
658
+ "vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00004-of-00004.safetensors",
659
+ "vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00004-of-00004.safetensors",
660
+ "vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00004-of-00004.safetensors",
661
+ "vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00004-of-00004.safetensors",
662
+ "vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00004-of-00004.safetensors",
663
+ "vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00004-of-00004.safetensors",
664
+ "vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
665
+ "vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
666
+ "vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
667
+ "vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
668
+ "vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
669
+ "vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
670
+ "vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
671
+ "vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
672
+ "vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
673
+ "vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
674
+ "vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
675
+ "vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
676
+ "vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
677
+ "vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
678
+ "vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
679
+ "vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
680
+ "vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
681
+ "vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
682
+ "vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
683
+ "vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
684
+ "vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
685
+ "vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
686
+ "vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
687
+ "vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
688
+ "vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
689
+ "vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
690
+ "vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
691
+ "vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
692
+ "vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
693
+ "vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
694
+ "vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
695
+ "vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
696
+ "vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
697
+ "vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
698
+ "vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
699
+ "vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
700
+ "vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
701
+ "vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
702
+ "vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
703
+ "vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
704
+ "vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
705
+ "vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
706
+ "vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
707
+ "vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
708
+ "vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
709
+ "vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
710
+ "vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
711
+ "vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
712
+ "vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
713
+ "vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
714
+ "vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
715
+ "vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
716
+ "vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
717
+ "vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
718
+ "vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
719
+ "vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
720
+ "vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
721
+ "vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
722
+ "vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
723
+ "vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
724
+ "vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
725
+ "vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
726
+ "vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
727
+ "vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
728
+ "vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
729
+ "vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
730
+ "vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
731
+ "vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
732
+ "vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
733
+ "vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
734
+ "vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
735
+ "vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
736
+ "vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
737
+ "vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
738
+ "vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
739
+ "vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
740
+ "vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
741
+ "vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
742
+ "vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
743
+ "vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
744
+ "vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
745
+ "vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
746
+ "vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
747
+ "vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
748
+ "vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
749
+ "vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
750
+ "vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
751
+ "vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
752
+ "vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
753
+ "vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
754
+ "vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
755
+ "vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
756
+ "vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
757
+ "vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
758
+ "vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
759
+ "vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
760
+ "vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
761
+ "vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
762
+ "vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
763
+ "vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
764
+ "vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
765
+ "vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
766
+ "vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
767
+ "vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
768
+ "vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
769
+ "vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
770
+ "vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
771
+ "vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
772
+ "vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
773
+ "vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
774
+ "vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
775
+ "vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
776
+ "vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
777
+ "vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
778
+ "vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
779
+ "vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
780
+ "vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
781
+ "vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
782
+ "vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
783
+ "vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
784
+ "vision_model.vision_model.head.attention.in_proj_bias": "model-00004-of-00004.safetensors",
785
+ "vision_model.vision_model.head.attention.in_proj_weight": "model-00004-of-00004.safetensors",
786
+ "vision_model.vision_model.head.attention.out_proj.bias": "model-00004-of-00004.safetensors",
787
+ "vision_model.vision_model.head.attention.out_proj.weight": "model-00004-of-00004.safetensors",
788
+ "vision_model.vision_model.head.layernorm.bias": "model-00004-of-00004.safetensors",
789
+ "vision_model.vision_model.head.layernorm.weight": "model-00004-of-00004.safetensors",
790
+ "vision_model.vision_model.head.mlp.fc1.bias": "model-00004-of-00004.safetensors",
791
+ "vision_model.vision_model.head.mlp.fc1.weight": "model-00004-of-00004.safetensors",
792
+ "vision_model.vision_model.head.mlp.fc2.bias": "model-00004-of-00004.safetensors",
793
+ "vision_model.vision_model.head.mlp.fc2.weight": "model-00004-of-00004.safetensors",
794
+ "vision_model.vision_model.head.probe": "model-00004-of-00004.safetensors",
795
+ "vision_model.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
796
+ "vision_model.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
797
+ }
798
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<B_SYS>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<B_USYS>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<C_Q>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<C_A>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<B_FUNC>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<B_CODE>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<B_APE>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": true,
82
+ "special": false
83
+ },
84
+ "151653": {
85
+ "content": "<function_calling>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": true,
90
+ "special": false
91
+ },
92
+ "151654": {
93
+ "content": "<calc_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": true,
98
+ "special": false
99
+ },
100
+ "151655": {
101
+ "content": "<calc_end>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": true,
106
+ "special": false
107
+ },
108
+ "151656": {
109
+ "content": "<inner_think>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": true,
114
+ "special": false
115
+ },
116
+ "151657": {
117
+ "content": "<audio_start>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "151658": {
125
+ "content": "<audio_end>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "151659": {
133
+ "content": "<audio_pad>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "151660": {
141
+ "content": "<img_start>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "151661": {
149
+ "content": "<img_end>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "151662": {
157
+ "content": "<img_pad>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "151663": {
165
+ "content": "<img_newline>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "151664": {
173
+ "content": "<box_start>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "151665": {
181
+ "content": "<box_end>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "151666": {
189
+ "content": "<box_delim>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "151667": {
197
+ "content": "<ref_start>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "151668": {
205
+ "content": "<ref_end>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "151669": {
213
+ "content": "<img_delim>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "151670": {
221
+ "content": "<polygon_start>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "151671": {
229
+ "content": "<polygon_end>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "151672": {
237
+ "content": "<pad_token>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "151673": {
245
+ "content": "<reserved_113>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "151674": {
253
+ "content": "<reserved_114>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "151675": {
261
+ "content": "<reserved_115>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "151676": {
269
+ "content": "<score_caption>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "151677": {
277
+ "content": "</score_caption>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "151678": {
285
+ "content": "<Overall>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ }
292
+ },
293
+ "additional_special_tokens": [
294
+ "<|im_start|>",
295
+ "<|im_end|>",
296
+ "<B_SYS>",
297
+ "<B_USYS>",
298
+ "<C_Q>",
299
+ "<C_A>",
300
+ "<B_FUNC>",
301
+ "<B_CODE>",
302
+ "<B_APE>",
303
+ "<function_calling>",
304
+ "<calc_start>",
305
+ "<calc_end>",
306
+ "<inner_think>",
307
+ "<audio_start>",
308
+ "<audio_end>",
309
+ "<audio_pad>",
310
+ "<img_start>",
311
+ "<img_end>",
312
+ "<img_pad>",
313
+ "<img_newline>",
314
+ "<box_start>",
315
+ "<box_end>",
316
+ "<box_delim>",
317
+ "<ref_start>",
318
+ "<ref_end>",
319
+ "<img_delim>",
320
+ "<polygon_start>",
321
+ "<polygon_end>",
322
+ "<pad_token>",
323
+ "<reserved_113>",
324
+ "<reserved_114>",
325
+ "<reserved_115>",
326
+ "<score_caption>",
327
+ "</score_caption>",
328
+ "<Overall>"
329
+ ],
330
+ "bos_token": null,
331
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<B_SYS>' + message['content']}}{% elif message['role'] == 'user_system' %}{{'<B_USYS>' + message['content']}}{% elif message['role'] == 'user' %}{{'<H_Q>' + message['content']}}{% elif message['role'] == 'assistant' %}{{'<H_A>' + message['content']}}{% elif message['role'] == 'function' %}{{'<B_FUNC>' + message['content']}}{% elif message['role'] == 'code' %}{{'<B_CODE>' + message['content']}}{% else %}{{ raise_exception('Invalid message role: ' + message['role']) }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{'<H_A>'}}{% endif %}",
332
+ "clean_up_tokenization_spaces": false,
333
+ "eos_token": "<|endoftext|>",
334
+ "errors": "replace",
335
+ "model_max_length": 131072,
336
+ "pad_token": "<pad_token>",
337
+ "split_special_tokens": false,
338
+ "tokenizer_class": "Qwen2Tokenizer",
339
+ "unk_token": null
340
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff