Hugging Face's logo

vidore
/
colpali-v1.3-hf

Transformers
Safetensors
ColPali
English
pretraining
Inference Endpoints
Model card Files Community
1
tonywu71 commited on
Commit
9e7e1b3
•
1 Parent(s): 9d21abe

Upload ColPaliForRetrieval

Browse files
Files changed (4) hide show
  1. config.json +53 -0
  2. model-00001-of-00002.safetensors +3 -0
  3. model-00002-of-00002.safetensors +3 -0
  4. model.safetensors.index.json +612 -0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ColPaliForRetrieval"
4
+ ],
5
+ "embedding_dim": 128,
6
+ "is_composition": false,
7
+ "model_type": "colpali",
8
+ "text_config": {
9
+ "hidden_size": 2048,
10
+ "intermediate_size": 16384,
11
+ "model_type": "gemma",
12
+ "num_attention_heads": 8,
13
+ "num_hidden_layers": 18,
14
+ "num_image_tokens": 1024,
15
+ "num_key_value_heads": 1,
16
+ "torch_dtype": "float32",
17
+ "vocab_size": 257216
18
+ },
19
+ "torch_dtype": "bfloat16",
20
+ "transformers_version": "4.48.0.dev0",
21
+ "vlm_config": {
22
+ "_name_or_path": "google/paligemma-3b-mix-448",
23
+ "_vocab_size": 257216,
24
+ "bos_token_id": 2,
25
+ "eos_token_id": 1,
26
+ "image_token_index": 257152,
27
+ "model_type": "paligemma",
28
+ "pad_token_id": 0,
29
+ "text_config": {
30
+ "hidden_size": 2048,
31
+ "intermediate_size": 16384,
32
+ "num_attention_heads": 8,
33
+ "num_hidden_layers": 18,
34
+ "num_image_tokens": 1024,
35
+ "num_key_value_heads": 1,
36
+ "torch_dtype": "float32",
37
+ "vocab_size": 257216
38
+ },
39
+ "torch_dtype": "bfloat16",
40
+ "vision_config": {
41
+ "hidden_size": 1152,
42
+ "image_size": 448,
43
+ "intermediate_size": 4304,
44
+ "num_attention_heads": 16,
45
+ "num_hidden_layers": 27,
46
+ "num_image_tokens": 1024,
47
+ "patch_size": 14,
48
+ "projection_dim": 2048,
49
+ "projector_hidden_act": "gelu_fast",
50
+ "vision_use_head": false
51
+ }
52
+ }
53
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4706678a55bb40df34f0e65939d7ee4cb6f41df1fac29a1fb9402d35a1d96a64
3
+ size 4986816144
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d97e225d93f2bf10c89ea87495d6df1e1dd7004c07ad43d7b713aeeb36c982d
3
+ size 862495464
model.safetensors.index.json ADDED
@@ -0,0 +1,612 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5849226976
4
+ },
5
+ "weight_map": {
6
+ "embedding_proj_layer.bias": "model-00002-of-00002.safetensors",
7
+ "embedding_proj_layer.weight": "model-00002-of-00002.safetensors",
8
+ "vlm.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "vlm.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "vlm.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "vlm.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "vlm.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "vlm.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "vlm.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "vlm.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "vlm.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "vlm.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "vlm.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "vlm.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "vlm.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "vlm.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "vlm.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "vlm.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "vlm.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "vlm.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "vlm.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
27
+ "vlm.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "vlm.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
29
+ "vlm.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
30
+ "vlm.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
31
+ "vlm.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "vlm.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "vlm.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "vlm.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "vlm.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "vlm.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "vlm.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
38
+ "vlm.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
39
+ "vlm.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "vlm.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "vlm.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
42
+ "vlm.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "vlm.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
44
+ "vlm.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "vlm.language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "vlm.language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "vlm.language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "vlm.language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "vlm.language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "vlm.language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "vlm.language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "vlm.language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "vlm.language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "vlm.language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "vlm.language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
56
+ "vlm.language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
57
+ "vlm.language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "vlm.language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "vlm.language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "vlm.language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "vlm.language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "vlm.language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "vlm.language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
64
+ "vlm.language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
65
+ "vlm.language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
66
+ "vlm.language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
67
+ "vlm.language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "vlm.language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "vlm.language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "vlm.language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
71
+ "vlm.language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "vlm.language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
73
+ "vlm.language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
74
+ "vlm.language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
75
+ "vlm.language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "vlm.language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "vlm.language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
78
+ "vlm.language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
79
+ "vlm.language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
80
+ "vlm.language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
81
+ "vlm.language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
82
+ "vlm.language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
83
+ "vlm.language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
84
+ "vlm.language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
85
+ "vlm.language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "vlm.language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
87
+ "vlm.language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
88
+ "vlm.language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
89
+ "vlm.language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
90
+ "vlm.language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "vlm.language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
92
+ "vlm.language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
93
+ "vlm.language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "vlm.language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "vlm.language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
96
+ "vlm.language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
97
+ "vlm.language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
98
+ "vlm.language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
99
+ "vlm.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "vlm.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "vlm.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
102
+ "vlm.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
103
+ "vlm.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "vlm.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "vlm.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
106
+ "vlm.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "vlm.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "vlm.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "vlm.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
110
+ "vlm.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
+ "vlm.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "vlm.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "vlm.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "vlm.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "vlm.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "vlm.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "vlm.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "vlm.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "vlm.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "vlm.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "vlm.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "vlm.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "vlm.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "vlm.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "vlm.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
126
+ "vlm.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
127
+ "vlm.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
128
+ "vlm.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
129
+ "vlm.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
130
+ "vlm.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
131
+ "vlm.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
132
+ "vlm.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
133
+ "vlm.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "vlm.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "vlm.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "vlm.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
137
+ "vlm.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
138
+ "vlm.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
139
+ "vlm.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "vlm.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
141
+ "vlm.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
142
+ "vlm.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
143
+ "vlm.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
144
+ "vlm.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "vlm.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
146
+ "vlm.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
147
+ "vlm.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "vlm.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "vlm.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "vlm.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "vlm.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
152
+ "vlm.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "vlm.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "vlm.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "vlm.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "vlm.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "vlm.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "vlm.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "vlm.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "vlm.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "vlm.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "vlm.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "vlm.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
164
+ "vlm.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
165
+ "vlm.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "vlm.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "vlm.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
168
+ "vlm.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "vlm.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
+ "vlm.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
171
+ "vlm.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
172
+ "vlm.multi_modal_projector.linear.bias": "model-00001-of-00002.safetensors",
173
+ "vlm.multi_modal_projector.linear.weight": "model-00001-of-00002.safetensors",
174
+ "vlm.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
175
+ "vlm.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
176
+ "vlm.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
177
+ "vlm.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
178
+ "vlm.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
179
+ "vlm.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
180
+ "vlm.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
181
+ "vlm.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
182
+ "vlm.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
183
+ "vlm.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
184
+ "vlm.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
185
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
186
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
187
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
188
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
189
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
190
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
191
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
192
+ "vlm.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "vlm.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
194
+ "vlm.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
195
+ "vlm.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
196
+ "vlm.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
197
+ "vlm.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
198
+ "vlm.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
199
+ "vlm.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
200
+ "vlm.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
201
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
202
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
204
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
205
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
206
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
207
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
208
+ "vlm.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
209
+ "vlm.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
210
+ "vlm.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
211
+ "vlm.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
212
+ "vlm.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
213
+ "vlm.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
214
+ "vlm.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
215
+ "vlm.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
216
+ "vlm.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
217
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
218
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
219
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
220
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
221
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
222
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
224
+ "vlm.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
225
+ "vlm.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
226
+ "vlm.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
227
+ "vlm.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
228
+ "vlm.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
229
+ "vlm.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
230
+ "vlm.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
231
+ "vlm.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
232
+ "vlm.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
233
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
234
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
235
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
236
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
237
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
238
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
239
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
240
+ "vlm.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
+ "vlm.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
242
+ "vlm.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
243
+ "vlm.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
244
+ "vlm.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
245
+ "vlm.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
246
+ "vlm.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
247
+ "vlm.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
248
+ "vlm.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
249
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
250
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
251
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
252
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
253
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
254
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
256
+ "vlm.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
257
+ "vlm.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
258
+ "vlm.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
259
+ "vlm.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
260
+ "vlm.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
261
+ "vlm.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
262
+ "vlm.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
263
+ "vlm.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
264
+ "vlm.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
265
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
266
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
268
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
269
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
270
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
272
+ "vlm.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "vlm.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
274
+ "vlm.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
275
+ "vlm.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
276
+ "vlm.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
277
+ "vlm.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
278
+ "vlm.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
279
+ "vlm.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
280
+ "vlm.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
281
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
282
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
283
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
284
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
285
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
286
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
287
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
288
+ "vlm.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
289
+ "vlm.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
290
+ "vlm.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
291
+ "vlm.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
292
+ "vlm.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
293
+ "vlm.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
294
+ "vlm.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
295
+ "vlm.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
296
+ "vlm.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
297
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
298
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
299
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
300
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
301
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
302
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
303
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
304
+ "vlm.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
305
+ "vlm.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
306
+ "vlm.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
307
+ "vlm.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
308
+ "vlm.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
309
+ "vlm.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
310
+ "vlm.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
311
+ "vlm.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
312
+ "vlm.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
313
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
314
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
316
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
317
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
318
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
320
+ "vlm.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
321
+ "vlm.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
322
+ "vlm.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
323
+ "vlm.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
324
+ "vlm.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
325
+ "vlm.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
326
+ "vlm.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
327
+ "vlm.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
328
+ "vlm.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
329
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
330
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
331
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
332
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
333
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
334
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
335
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
336
+ "vlm.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
337
+ "vlm.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
338
+ "vlm.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
339
+ "vlm.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
340
+ "vlm.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
341
+ "vlm.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
342
+ "vlm.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
343
+ "vlm.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
344
+ "vlm.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
345
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
346
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
347
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
348
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
349
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
350
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
351
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
352
+ "vlm.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
353
+ "vlm.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
354
+ "vlm.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
355
+ "vlm.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
356
+ "vlm.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
357
+ "vlm.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
358
+ "vlm.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
359
+ "vlm.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
360
+ "vlm.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
361
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
362
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
363
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
364
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
365
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
366
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
367
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
368
+ "vlm.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
369
+ "vlm.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
370
+ "vlm.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
371
+ "vlm.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
372
+ "vlm.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
373
+ "vlm.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
374
+ "vlm.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
375
+ "vlm.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
376
+ "vlm.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
377
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
378
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
379
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
380
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
381
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
382
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
383
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
384
+ "vlm.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
385
+ "vlm.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
386
+ "vlm.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
387
+ "vlm.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
388
+ "vlm.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
389
+ "vlm.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
390
+ "vlm.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
391
+ "vlm.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
392
+ "vlm.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
393
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
394
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
395
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
396
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
397
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
398
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
399
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
400
+ "vlm.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
401
+ "vlm.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
402
+ "vlm.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
403
+ "vlm.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
404
+ "vlm.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
405
+ "vlm.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
406
+ "vlm.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
407
+ "vlm.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
408
+ "vlm.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
409
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
412
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
413
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
+ "vlm.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
+ "vlm.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
418
+ "vlm.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
419
+ "vlm.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
420
+ "vlm.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
421
+ "vlm.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
422
+ "vlm.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
423
+ "vlm.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
424
+ "vlm.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
425
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
426
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
427
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
428
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
429
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
430
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
431
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
432
+ "vlm.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
433
+ "vlm.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
434
+ "vlm.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
435
+ "vlm.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
436
+ "vlm.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
437
+ "vlm.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
438
+ "vlm.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
439
+ "vlm.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
440
+ "vlm.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
441
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
442
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
443
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
444
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
445
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
446
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
447
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
448
+ "vlm.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
449
+ "vlm.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
450
+ "vlm.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
451
+ "vlm.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
452
+ "vlm.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
453
+ "vlm.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
454
+ "vlm.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
455
+ "vlm.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
456
+ "vlm.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
457
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
458
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
459
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
460
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
461
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
462
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
463
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
464
+ "vlm.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
465
+ "vlm.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
466
+ "vlm.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
467
+ "vlm.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
468
+ "vlm.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
469
+ "vlm.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
470
+ "vlm.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
471
+ "vlm.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
472
+ "vlm.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
473
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
474
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
475
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
476
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
477
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
478
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
479
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
480
+ "vlm.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
481
+ "vlm.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
482
+ "vlm.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
483
+ "vlm.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
484
+ "vlm.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
485
+ "vlm.vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
486
+ "vlm.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
487
+ "vlm.vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
488
+ "vlm.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
489
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
490
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
491
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
492
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
493
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
494
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
495
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
496
+ "vlm.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
497
+ "vlm.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
498
+ "vlm.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
499
+ "vlm.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
500
+ "vlm.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
501
+ "vlm.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
502
+ "vlm.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
503
+ "vlm.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
504
+ "vlm.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
505
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
506
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
507
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
508
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
509
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
510
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
511
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
512
+ "vlm.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
513
+ "vlm.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
514
+ "vlm.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
515
+ "vlm.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
516
+ "vlm.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
517
+ "vlm.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
518
+ "vlm.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
519
+ "vlm.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
520
+ "vlm.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
521
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
522
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
523
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
524
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
525
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
526
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
527
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
528
+ "vlm.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
529
+ "vlm.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
530
+ "vlm.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
531
+ "vlm.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
532
+ "vlm.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
533
+ "vlm.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
534
+ "vlm.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
535
+ "vlm.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
536
+ "vlm.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
537
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
538
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
539
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
540
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
541
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
542
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
543
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
544
+ "vlm.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
545
+ "vlm.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
546
+ "vlm.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
547
+ "vlm.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
548
+ "vlm.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
549
+ "vlm.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
550
+ "vlm.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
551
+ "vlm.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
552
+ "vlm.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
553
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
554
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
555
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
556
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
557
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
558
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
559
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
560
+ "vlm.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
561
+ "vlm.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
562
+ "vlm.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
563
+ "vlm.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
564
+ "vlm.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
565
+ "vlm.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
566
+ "vlm.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
567
+ "vlm.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
568
+ "vlm.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
569
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
570
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
571
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
572
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
573
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
574
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
575
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
576
+ "vlm.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
577
+ "vlm.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
578
+ "vlm.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
579
+ "vlm.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
580
+ "vlm.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
581
+ "vlm.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
582
+ "vlm.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
583
+ "vlm.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
584
+ "vlm.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
585
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
586
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
587
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
588
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
589
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
590
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
591
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
592
+ "vlm.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
593
+ "vlm.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
594
+ "vlm.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
595
+ "vlm.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
596
+ "vlm.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
597
+ "vlm.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
598
+ "vlm.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
599
+ "vlm.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
600
+ "vlm.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
601
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
602
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
603
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
604
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
605
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
606
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
607
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
608
+ "vlm.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
609
+ "vlm.vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
610
+ "vlm.vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
611
+ }
612
+ }