Hugging Face's logo

Salesforce
/
xgen-mm-phi3-mini-instruct-interleave-r-v1.5

Image-Text-to-Text
Safetensors
English
xgenmm
conversational
custom_code
Model card Files Community
3
Manli commited on
Commit
4d08ec3
•
1 Parent(s): 2cffd60

upload model

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +3 -0
  2. model-00002-of-00004.safetensors +3 -0
  3. model-00003-of-00004.safetensors +3 -0
  4. model-00004-of-00004.safetensors +3 -0
  5. model.safetensors.index.json +725 -0
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2394080dd0bac25f59461eba060e937989ab2336edffb415db3a36d7f3fc371e
3
+ size 4962660968
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63cfd9676a01932ea6674b0103a88a3863c3c8028b66d6716d4bd36945b66ed
3
+ size 4983112136
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6be012e8534481a9ca4e8dd8f3e482de42af52cb86b23c463b1e55ab5a40a2
3
+ size 4983112168
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e9607ebf4884b3913619693b547dd4ae9bb66d9e6de42e80bcb5357de36914
3
+ size 2508236156
model.safetensors.index.json ADDED
@@ -0,0 +1,725 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17437028876
4
+ },
5
+ "weight_map": {
6
+ "vlm.lang_model.lm_head.additional_fc.bias": "model-00004-of-00004.safetensors",
7
+ "vlm.lang_model.lm_head.additional_fc.weight": "model-00004-of-00004.safetensors",
8
+ "vlm.lang_model.lm_head.bias": "model-00004-of-00004.safetensors",
9
+ "vlm.lang_model.lm_head.weight": "model-00004-of-00004.safetensors",
10
+ "vlm.lang_model.model.embed_tokens.additional_embedding.weight": "model-00001-of-00004.safetensors",
11
+ "vlm.lang_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
12
+ "vlm.lang_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "vlm.lang_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
14
+ "vlm.lang_model.model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
15
+ "vlm.lang_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
16
+ "vlm.lang_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "vlm.lang_model.model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
18
+ "vlm.lang_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "vlm.lang_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "vlm.lang_model.model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "vlm.lang_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "vlm.lang_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "vlm.lang_model.model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
24
+ "vlm.lang_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
25
+ "vlm.lang_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
26
+ "vlm.lang_model.model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
27
+ "vlm.lang_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "vlm.lang_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
29
+ "vlm.lang_model.model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
30
+ "vlm.lang_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "vlm.lang_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
32
+ "vlm.lang_model.model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
33
+ "vlm.lang_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "vlm.lang_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
35
+ "vlm.lang_model.model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
36
+ "vlm.lang_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "vlm.lang_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "vlm.lang_model.model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "vlm.lang_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "vlm.lang_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "vlm.lang_model.model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
42
+ "vlm.lang_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
+ "vlm.lang_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
+ "vlm.lang_model.model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
45
+ "vlm.lang_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "vlm.lang_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
47
+ "vlm.lang_model.model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
48
+ "vlm.lang_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "vlm.lang_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
50
+ "vlm.lang_model.model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
51
+ "vlm.lang_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "vlm.lang_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "vlm.lang_model.model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
54
+ "vlm.lang_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "vlm.lang_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "vlm.lang_model.model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "vlm.lang_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "vlm.lang_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "vlm.lang_model.model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
60
+ "vlm.lang_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
61
+ "vlm.lang_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
62
+ "vlm.lang_model.model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
63
+ "vlm.lang_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
64
+ "vlm.lang_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "vlm.lang_model.model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
66
+ "vlm.lang_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
67
+ "vlm.lang_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
68
+ "vlm.lang_model.model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
69
+ "vlm.lang_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
70
+ "vlm.lang_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
71
+ "vlm.lang_model.model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
72
+ "vlm.lang_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
73
+ "vlm.lang_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
74
+ "vlm.lang_model.model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
75
+ "vlm.lang_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
76
+ "vlm.lang_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
77
+ "vlm.lang_model.model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
78
+ "vlm.lang_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
79
+ "vlm.lang_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
80
+ "vlm.lang_model.model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
81
+ "vlm.lang_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
82
+ "vlm.lang_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
83
+ "vlm.lang_model.model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
84
+ "vlm.lang_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
85
+ "vlm.lang_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
86
+ "vlm.lang_model.model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
87
+ "vlm.lang_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
88
+ "vlm.lang_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
89
+ "vlm.lang_model.model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
90
+ "vlm.lang_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
91
+ "vlm.lang_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
92
+ "vlm.lang_model.model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
93
+ "vlm.lang_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
94
+ "vlm.lang_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
95
+ "vlm.lang_model.model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
96
+ "vlm.lang_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
97
+ "vlm.lang_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
98
+ "vlm.lang_model.model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
99
+ "vlm.lang_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
100
+ "vlm.lang_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
101
+ "vlm.lang_model.model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
102
+ "vlm.lang_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
103
+ "vlm.lang_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
104
+ "vlm.lang_model.model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
105
+ "vlm.lang_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
106
+ "vlm.lang_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
107
+ "vlm.lang_model.model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
108
+ "vlm.lang_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "vlm.lang_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
110
+ "vlm.lang_model.model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "vlm.lang_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "vlm.lang_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
113
+ "vlm.lang_model.model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
114
+ "vlm.lang_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
115
+ "vlm.lang_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
116
+ "vlm.lang_model.model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
117
+ "vlm.lang_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "vlm.lang_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
119
+ "vlm.lang_model.model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
120
+ "vlm.lang_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "vlm.lang_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
122
+ "vlm.lang_model.model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
123
+ "vlm.lang_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
124
+ "vlm.lang_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
+ "vlm.lang_model.model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
126
+ "vlm.lang_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "vlm.lang_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "vlm.lang_model.model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "vlm.lang_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "vlm.lang_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
131
+ "vlm.lang_model.model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
132
+ "vlm.lang_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
133
+ "vlm.lang_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
134
+ "vlm.lang_model.model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
135
+ "vlm.lang_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
136
+ "vlm.lang_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "vlm.lang_model.model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
138
+ "vlm.lang_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
139
+ "vlm.lang_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
140
+ "vlm.lang_model.model.layers.28.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
141
+ "vlm.lang_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
142
+ "vlm.lang_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
143
+ "vlm.lang_model.model.layers.28.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
144
+ "vlm.lang_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
145
+ "vlm.lang_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
146
+ "vlm.lang_model.model.layers.29.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
147
+ "vlm.lang_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
148
+ "vlm.lang_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
149
+ "vlm.lang_model.model.layers.29.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
150
+ "vlm.lang_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
151
+ "vlm.lang_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
152
+ "vlm.lang_model.model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
153
+ "vlm.lang_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "vlm.lang_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
155
+ "vlm.lang_model.model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
156
+ "vlm.lang_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
157
+ "vlm.lang_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
158
+ "vlm.lang_model.model.layers.30.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
159
+ "vlm.lang_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
160
+ "vlm.lang_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
161
+ "vlm.lang_model.model.layers.30.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
162
+ "vlm.lang_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
163
+ "vlm.lang_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
164
+ "vlm.lang_model.model.layers.31.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
165
+ "vlm.lang_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
166
+ "vlm.lang_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
167
+ "vlm.lang_model.model.layers.31.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
168
+ "vlm.lang_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
169
+ "vlm.lang_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
170
+ "vlm.lang_model.model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
171
+ "vlm.lang_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
172
+ "vlm.lang_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
173
+ "vlm.lang_model.model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
174
+ "vlm.lang_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
175
+ "vlm.lang_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
176
+ "vlm.lang_model.model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
177
+ "vlm.lang_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
178
+ "vlm.lang_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
179
+ "vlm.lang_model.model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
180
+ "vlm.lang_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
181
+ "vlm.lang_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
182
+ "vlm.lang_model.model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
183
+ "vlm.lang_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
184
+ "vlm.lang_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
185
+ "vlm.lang_model.model.layers.6.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
186
+ "vlm.lang_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
187
+ "vlm.lang_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
188
+ "vlm.lang_model.model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
189
+ "vlm.lang_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
190
+ "vlm.lang_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
191
+ "vlm.lang_model.model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
192
+ "vlm.lang_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
193
+ "vlm.lang_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
194
+ "vlm.lang_model.model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
195
+ "vlm.lang_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
196
+ "vlm.lang_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
197
+ "vlm.lang_model.model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
198
+ "vlm.lang_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
199
+ "vlm.lang_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
200
+ "vlm.lang_model.model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
201
+ "vlm.lang_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
202
+ "vlm.lang_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
203
+ "vlm.lang_model.model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
204
+ "vlm.lang_model.model.norm.weight": "model-00004-of-00004.safetensors",
205
+ "vlm.vision_encoder.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
206
+ "vlm.vision_encoder.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
207
+ "vlm.vision_encoder.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
208
+ "vlm.vision_encoder.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
209
+ "vlm.vision_encoder.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
210
+ "vlm.vision_encoder.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
211
+ "vlm.vision_encoder.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
212
+ "vlm.vision_encoder.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
213
+ "vlm.vision_encoder.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
214
+ "vlm.vision_encoder.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
215
+ "vlm.vision_encoder.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
216
+ "vlm.vision_encoder.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
217
+ "vlm.vision_encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
218
+ "vlm.vision_encoder.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
219
+ "vlm.vision_encoder.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
220
+ "vlm.vision_encoder.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
221
+ "vlm.vision_encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "vlm.vision_encoder.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
223
+ "vlm.vision_encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "vlm.vision_encoder.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
225
+ "vlm.vision_encoder.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
226
+ "vlm.vision_encoder.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
227
+ "vlm.vision_encoder.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
228
+ "vlm.vision_encoder.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
229
+ "vlm.vision_encoder.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
230
+ "vlm.vision_encoder.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
231
+ "vlm.vision_encoder.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
232
+ "vlm.vision_encoder.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
233
+ "vlm.vision_encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
234
+ "vlm.vision_encoder.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
235
+ "vlm.vision_encoder.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
236
+ "vlm.vision_encoder.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
237
+ "vlm.vision_encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
238
+ "vlm.vision_encoder.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
239
+ "vlm.vision_encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
240
+ "vlm.vision_encoder.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
241
+ "vlm.vision_encoder.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
242
+ "vlm.vision_encoder.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
243
+ "vlm.vision_encoder.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
244
+ "vlm.vision_encoder.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
245
+ "vlm.vision_encoder.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
246
+ "vlm.vision_encoder.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
247
+ "vlm.vision_encoder.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
248
+ "vlm.vision_encoder.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
249
+ "vlm.vision_encoder.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
250
+ "vlm.vision_encoder.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
251
+ "vlm.vision_encoder.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
252
+ "vlm.vision_encoder.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
253
+ "vlm.vision_encoder.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
254
+ "vlm.vision_encoder.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
255
+ "vlm.vision_encoder.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
256
+ "vlm.vision_encoder.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
257
+ "vlm.vision_encoder.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
258
+ "vlm.vision_encoder.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
259
+ "vlm.vision_encoder.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
260
+ "vlm.vision_encoder.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
261
+ "vlm.vision_encoder.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
262
+ "vlm.vision_encoder.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
263
+ "vlm.vision_encoder.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
264
+ "vlm.vision_encoder.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
265
+ "vlm.vision_encoder.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "vlm.vision_encoder.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
267
+ "vlm.vision_encoder.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
268
+ "vlm.vision_encoder.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "vlm.vision_encoder.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "vlm.vision_encoder.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "vlm.vision_encoder.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "vlm.vision_encoder.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
273
+ "vlm.vision_encoder.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
274
+ "vlm.vision_encoder.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
275
+ "vlm.vision_encoder.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
276
+ "vlm.vision_encoder.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
277
+ "vlm.vision_encoder.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
278
+ "vlm.vision_encoder.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
279
+ "vlm.vision_encoder.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
280
+ "vlm.vision_encoder.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
281
+ "vlm.vision_encoder.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
282
+ "vlm.vision_encoder.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
283
+ "vlm.vision_encoder.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
284
+ "vlm.vision_encoder.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
285
+ "vlm.vision_encoder.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "vlm.vision_encoder.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
287
+ "vlm.vision_encoder.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "vlm.vision_encoder.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
289
+ "vlm.vision_encoder.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
290
+ "vlm.vision_encoder.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
291
+ "vlm.vision_encoder.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
292
+ "vlm.vision_encoder.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
293
+ "vlm.vision_encoder.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
294
+ "vlm.vision_encoder.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
295
+ "vlm.vision_encoder.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
296
+ "vlm.vision_encoder.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
297
+ "vlm.vision_encoder.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
298
+ "vlm.vision_encoder.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
299
+ "vlm.vision_encoder.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
300
+ "vlm.vision_encoder.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
301
+ "vlm.vision_encoder.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
302
+ "vlm.vision_encoder.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
303
+ "vlm.vision_encoder.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
304
+ "vlm.vision_encoder.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
305
+ "vlm.vision_encoder.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
306
+ "vlm.vision_encoder.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
307
+ "vlm.vision_encoder.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
308
+ "vlm.vision_encoder.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
309
+ "vlm.vision_encoder.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
310
+ "vlm.vision_encoder.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
311
+ "vlm.vision_encoder.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
312
+ "vlm.vision_encoder.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
313
+ "vlm.vision_encoder.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
314
+ "vlm.vision_encoder.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
315
+ "vlm.vision_encoder.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
316
+ "vlm.vision_encoder.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "vlm.vision_encoder.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "vlm.vision_encoder.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "vlm.vision_encoder.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "vlm.vision_encoder.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
321
+ "vlm.vision_encoder.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
322
+ "vlm.vision_encoder.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
323
+ "vlm.vision_encoder.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
324
+ "vlm.vision_encoder.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
325
+ "vlm.vision_encoder.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
326
+ "vlm.vision_encoder.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
327
+ "vlm.vision_encoder.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
328
+ "vlm.vision_encoder.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
329
+ "vlm.vision_encoder.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
330
+ "vlm.vision_encoder.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
331
+ "vlm.vision_encoder.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
332
+ "vlm.vision_encoder.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
333
+ "vlm.vision_encoder.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
334
+ "vlm.vision_encoder.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
335
+ "vlm.vision_encoder.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
336
+ "vlm.vision_encoder.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
337
+ "vlm.vision_encoder.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
338
+ "vlm.vision_encoder.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
339
+ "vlm.vision_encoder.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
340
+ "vlm.vision_encoder.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
341
+ "vlm.vision_encoder.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
342
+ "vlm.vision_encoder.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
343
+ "vlm.vision_encoder.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
344
+ "vlm.vision_encoder.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
345
+ "vlm.vision_encoder.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "vlm.vision_encoder.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
347
+ "vlm.vision_encoder.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
348
+ "vlm.vision_encoder.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
349
+ "vlm.vision_encoder.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
350
+ "vlm.vision_encoder.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
351
+ "vlm.vision_encoder.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
352
+ "vlm.vision_encoder.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
353
+ "vlm.vision_encoder.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
354
+ "vlm.vision_encoder.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
355
+ "vlm.vision_encoder.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
356
+ "vlm.vision_encoder.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
357
+ "vlm.vision_encoder.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
358
+ "vlm.vision_encoder.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
359
+ "vlm.vision_encoder.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
360
+ "vlm.vision_encoder.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
361
+ "vlm.vision_encoder.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
362
+ "vlm.vision_encoder.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
363
+ "vlm.vision_encoder.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
364
+ "vlm.vision_encoder.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
365
+ "vlm.vision_encoder.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
366
+ "vlm.vision_encoder.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
367
+ "vlm.vision_encoder.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
368
+ "vlm.vision_encoder.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
369
+ "vlm.vision_encoder.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
370
+ "vlm.vision_encoder.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
371
+ "vlm.vision_encoder.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
372
+ "vlm.vision_encoder.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
373
+ "vlm.vision_encoder.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
374
+ "vlm.vision_encoder.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
375
+ "vlm.vision_encoder.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
376
+ "vlm.vision_encoder.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
377
+ "vlm.vision_encoder.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
378
+ "vlm.vision_encoder.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
379
+ "vlm.vision_encoder.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
380
+ "vlm.vision_encoder.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
381
+ "vlm.vision_encoder.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
+ "vlm.vision_encoder.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
383
+ "vlm.vision_encoder.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
384
+ "vlm.vision_encoder.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
385
+ "vlm.vision_encoder.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
386
+ "vlm.vision_encoder.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
387
+ "vlm.vision_encoder.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
388
+ "vlm.vision_encoder.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
389
+ "vlm.vision_encoder.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
390
+ "vlm.vision_encoder.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
391
+ "vlm.vision_encoder.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
392
+ "vlm.vision_encoder.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
393
+ "vlm.vision_encoder.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
394
+ "vlm.vision_encoder.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
395
+ "vlm.vision_encoder.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
396
+ "vlm.vision_encoder.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
397
+ "vlm.vision_encoder.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
398
+ "vlm.vision_encoder.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
399
+ "vlm.vision_encoder.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
400
+ "vlm.vision_encoder.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
401
+ "vlm.vision_encoder.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
402
+ "vlm.vision_encoder.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
403
+ "vlm.vision_encoder.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
404
+ "vlm.vision_encoder.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
405
+ "vlm.vision_encoder.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
406
+ "vlm.vision_encoder.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
407
+ "vlm.vision_encoder.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
408
+ "vlm.vision_encoder.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
409
+ "vlm.vision_encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
410
+ "vlm.vision_encoder.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
411
+ "vlm.vision_encoder.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
412
+ "vlm.vision_encoder.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
413
+ "vlm.vision_encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
414
+ "vlm.vision_encoder.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
415
+ "vlm.vision_encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
416
+ "vlm.vision_encoder.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
417
+ "vlm.vision_encoder.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
418
+ "vlm.vision_encoder.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
419
+ "vlm.vision_encoder.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
420
+ "vlm.vision_encoder.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
421
+ "vlm.vision_encoder.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
422
+ "vlm.vision_encoder.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
423
+ "vlm.vision_encoder.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
424
+ "vlm.vision_encoder.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
425
+ "vlm.vision_encoder.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
426
+ "vlm.vision_encoder.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
427
+ "vlm.vision_encoder.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
428
+ "vlm.vision_encoder.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
429
+ "vlm.vision_encoder.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
430
+ "vlm.vision_encoder.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
431
+ "vlm.vision_encoder.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
432
+ "vlm.vision_encoder.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
433
+ "vlm.vision_encoder.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
434
+ "vlm.vision_encoder.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
435
+ "vlm.vision_encoder.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
436
+ "vlm.vision_encoder.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
437
+ "vlm.vision_encoder.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
438
+ "vlm.vision_encoder.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
439
+ "vlm.vision_encoder.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
440
+ "vlm.vision_encoder.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
441
+ "vlm.vision_encoder.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
442
+ "vlm.vision_encoder.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
443
+ "vlm.vision_encoder.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
444
+ "vlm.vision_encoder.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
445
+ "vlm.vision_encoder.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
446
+ "vlm.vision_encoder.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
447
+ "vlm.vision_encoder.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
448
+ "vlm.vision_encoder.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
449
+ "vlm.vision_encoder.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
450
+ "vlm.vision_encoder.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
451
+ "vlm.vision_encoder.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
452
+ "vlm.vision_encoder.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
453
+ "vlm.vision_encoder.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
454
+ "vlm.vision_encoder.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
455
+ "vlm.vision_encoder.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
456
+ "vlm.vision_encoder.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
457
+ "vlm.vision_encoder.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
458
+ "vlm.vision_encoder.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
459
+ "vlm.vision_encoder.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
460
+ "vlm.vision_encoder.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
461
+ "vlm.vision_encoder.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
462
+ "vlm.vision_encoder.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
463
+ "vlm.vision_encoder.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
464
+ "vlm.vision_encoder.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
465
+ "vlm.vision_encoder.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
466
+ "vlm.vision_encoder.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
467
+ "vlm.vision_encoder.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
468
+ "vlm.vision_encoder.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
469
+ "vlm.vision_encoder.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
470
+ "vlm.vision_encoder.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
471
+ "vlm.vision_encoder.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
472
+ "vlm.vision_encoder.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
473
+ "vlm.vision_encoder.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
474
+ "vlm.vision_encoder.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
475
+ "vlm.vision_encoder.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
476
+ "vlm.vision_encoder.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
477
+ "vlm.vision_encoder.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
478
+ "vlm.vision_encoder.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
479
+ "vlm.vision_encoder.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
480
+ "vlm.vision_encoder.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
481
+ "vlm.vision_encoder.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
482
+ "vlm.vision_encoder.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
483
+ "vlm.vision_encoder.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
484
+ "vlm.vision_encoder.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
485
+ "vlm.vision_encoder.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
486
+ "vlm.vision_encoder.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
487
+ "vlm.vision_encoder.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
488
+ "vlm.vision_encoder.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
489
+ "vlm.vision_encoder.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
490
+ "vlm.vision_encoder.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
491
+ "vlm.vision_encoder.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
492
+ "vlm.vision_encoder.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
493
+ "vlm.vision_encoder.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
494
+ "vlm.vision_encoder.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
495
+ "vlm.vision_encoder.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
496
+ "vlm.vision_encoder.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
497
+ "vlm.vision_encoder.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
498
+ "vlm.vision_encoder.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
499
+ "vlm.vision_encoder.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
500
+ "vlm.vision_encoder.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
501
+ "vlm.vision_encoder.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
502
+ "vlm.vision_encoder.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
503
+ "vlm.vision_encoder.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
504
+ "vlm.vision_encoder.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
505
+ "vlm.vision_encoder.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
506
+ "vlm.vision_encoder.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
507
+ "vlm.vision_encoder.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
508
+ "vlm.vision_encoder.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
509
+ "vlm.vision_encoder.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
510
+ "vlm.vision_encoder.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
511
+ "vlm.vision_encoder.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
512
+ "vlm.vision_encoder.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
513
+ "vlm.vision_encoder.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
514
+ "vlm.vision_encoder.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
515
+ "vlm.vision_encoder.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
516
+ "vlm.vision_encoder.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
517
+ "vlm.vision_encoder.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
518
+ "vlm.vision_encoder.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
519
+ "vlm.vision_encoder.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
520
+ "vlm.vision_encoder.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
521
+ "vlm.vision_encoder.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
522
+ "vlm.vision_encoder.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
523
+ "vlm.vision_encoder.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
524
+ "vlm.vision_encoder.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
525
+ "vlm.vision_encoder.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
526
+ "vlm.vision_encoder.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
527
+ "vlm.vision_encoder.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
528
+ "vlm.vision_encoder.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
529
+ "vlm.vision_encoder.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
530
+ "vlm.vision_encoder.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
531
+ "vlm.vision_encoder.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
532
+ "vlm.vision_encoder.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
533
+ "vlm.vision_encoder.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
534
+ "vlm.vision_encoder.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
535
+ "vlm.vision_encoder.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
536
+ "vlm.vision_encoder.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
537
+ "vlm.vision_encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
538
+ "vlm.vision_encoder.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
539
+ "vlm.vision_encoder.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
540
+ "vlm.vision_encoder.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
541
+ "vlm.vision_encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
542
+ "vlm.vision_encoder.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
543
+ "vlm.vision_encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
544
+ "vlm.vision_encoder.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
545
+ "vlm.vision_encoder.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
546
+ "vlm.vision_encoder.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
547
+ "vlm.vision_encoder.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
548
+ "vlm.vision_encoder.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
549
+ "vlm.vision_encoder.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
550
+ "vlm.vision_encoder.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
551
+ "vlm.vision_encoder.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
552
+ "vlm.vision_encoder.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
553
+ "vlm.vision_encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
554
+ "vlm.vision_encoder.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
555
+ "vlm.vision_encoder.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
556
+ "vlm.vision_encoder.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
557
+ "vlm.vision_encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
558
+ "vlm.vision_encoder.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
559
+ "vlm.vision_encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
560
+ "vlm.vision_encoder.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
561
+ "vlm.vision_encoder.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
562
+ "vlm.vision_encoder.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
563
+ "vlm.vision_encoder.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
564
+ "vlm.vision_encoder.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
565
+ "vlm.vision_encoder.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
566
+ "vlm.vision_encoder.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
567
+ "vlm.vision_encoder.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
568
+ "vlm.vision_encoder.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
569
+ "vlm.vision_encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
570
+ "vlm.vision_encoder.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
571
+ "vlm.vision_encoder.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
572
+ "vlm.vision_encoder.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
573
+ "vlm.vision_encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
574
+ "vlm.vision_encoder.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
575
+ "vlm.vision_encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
576
+ "vlm.vision_encoder.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
577
+ "vlm.vision_encoder.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
578
+ "vlm.vision_encoder.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
579
+ "vlm.vision_encoder.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
580
+ "vlm.vision_encoder.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
581
+ "vlm.vision_encoder.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
582
+ "vlm.vision_encoder.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
583
+ "vlm.vision_encoder.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
584
+ "vlm.vision_encoder.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
585
+ "vlm.vision_encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
586
+ "vlm.vision_encoder.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
587
+ "vlm.vision_encoder.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
588
+ "vlm.vision_encoder.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
589
+ "vlm.vision_encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
590
+ "vlm.vision_encoder.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
591
+ "vlm.vision_encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
592
+ "vlm.vision_encoder.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
593
+ "vlm.vision_encoder.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
594
+ "vlm.vision_encoder.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
595
+ "vlm.vision_encoder.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
596
+ "vlm.vision_encoder.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
597
+ "vlm.vision_encoder.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
598
+ "vlm.vision_encoder.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
599
+ "vlm.vision_encoder.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
600
+ "vlm.vision_encoder.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
601
+ "vlm.vision_encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
602
+ "vlm.vision_encoder.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
603
+ "vlm.vision_encoder.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
604
+ "vlm.vision_encoder.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
605
+ "vlm.vision_encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
606
+ "vlm.vision_encoder.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
607
+ "vlm.vision_encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
608
+ "vlm.vision_encoder.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
609
+ "vlm.vision_encoder.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
610
+ "vlm.vision_encoder.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
611
+ "vlm.vision_encoder.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
612
+ "vlm.vision_encoder.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
613
+ "vlm.vision_encoder.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
614
+ "vlm.vision_encoder.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
615
+ "vlm.vision_encoder.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
616
+ "vlm.vision_encoder.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
617
+ "vlm.vision_encoder.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
618
+ "vlm.vision_encoder.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
619
+ "vlm.vision_encoder.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
620
+ "vlm.vision_encoder.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
621
+ "vlm.vision_encoder.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
622
+ "vlm.vision_encoder.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
623
+ "vlm.vision_encoder.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
624
+ "vlm.vision_encoder.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
625
+ "vlm.vision_encoder.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
626
+ "vlm.vision_encoder.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
627
+ "vlm.vision_encoder.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
628
+ "vlm.vision_encoder.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
629
+ "vlm.vision_encoder.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
630
+ "vlm.vision_encoder.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
631
+ "vlm.vision_encoder.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
632
+ "vlm.vision_encoder.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
633
+ "vlm.vision_encoder.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
634
+ "vlm.vision_encoder.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
635
+ "vlm.vision_encoder.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
636
+ "vlm.vision_encoder.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
637
+ "vlm.vision_encoder.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
638
+ "vlm.vision_encoder.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
639
+ "vlm.vision_encoder.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
640
+ "vlm.vision_encoder.head.attention.in_proj_bias": "model-00001-of-00004.safetensors",
641
+ "vlm.vision_encoder.head.attention.in_proj_weight": "model-00001-of-00004.safetensors",
642
+ "vlm.vision_encoder.head.attention.out_proj.bias": "model-00001-of-00004.safetensors",
643
+ "vlm.vision_encoder.head.attention.out_proj.weight": "model-00001-of-00004.safetensors",
644
+ "vlm.vision_encoder.head.layernorm.bias": "model-00001-of-00004.safetensors",
645
+ "vlm.vision_encoder.head.layernorm.weight": "model-00001-of-00004.safetensors",
646
+ "vlm.vision_encoder.head.mlp.fc1.bias": "model-00001-of-00004.safetensors",
647
+ "vlm.vision_encoder.head.mlp.fc1.weight": "model-00001-of-00004.safetensors",
648
+ "vlm.vision_encoder.head.mlp.fc2.bias": "model-00001-of-00004.safetensors",
649
+ "vlm.vision_encoder.head.mlp.fc2.weight": "model-00001-of-00004.safetensors",
650
+ "vlm.vision_encoder.head.probe": "model-00001-of-00004.safetensors",
651
+ "vlm.vision_encoder.post_layernorm.bias": "model-00001-of-00004.safetensors",
652
+ "vlm.vision_encoder.post_layernorm.weight": "model-00001-of-00004.safetensors",
653
+ "vlm.vision_tokenizer.latents": "model-00001-of-00004.safetensors",
654
+ "vlm.vision_tokenizer.layers.0.0.norm_latents.bias": "model-00001-of-00004.safetensors",
655
+ "vlm.vision_tokenizer.layers.0.0.norm_latents.weight": "model-00001-of-00004.safetensors",
656
+ "vlm.vision_tokenizer.layers.0.0.norm_media.bias": "model-00001-of-00004.safetensors",
657
+ "vlm.vision_tokenizer.layers.0.0.norm_media.weight": "model-00001-of-00004.safetensors",
658
+ "vlm.vision_tokenizer.layers.0.0.to_kv.weight": "model-00001-of-00004.safetensors",
659
+ "vlm.vision_tokenizer.layers.0.0.to_out.weight": "model-00001-of-00004.safetensors",
660
+ "vlm.vision_tokenizer.layers.0.0.to_q.weight": "model-00001-of-00004.safetensors",
661
+ "vlm.vision_tokenizer.layers.0.1.0.bias": "model-00001-of-00004.safetensors",
662
+ "vlm.vision_tokenizer.layers.0.1.0.weight": "model-00001-of-00004.safetensors",
663
+ "vlm.vision_tokenizer.layers.0.1.1.weight": "model-00001-of-00004.safetensors",
664
+ "vlm.vision_tokenizer.layers.0.1.3.weight": "model-00001-of-00004.safetensors",
665
+ "vlm.vision_tokenizer.layers.1.0.norm_latents.bias": "model-00001-of-00004.safetensors",
666
+ "vlm.vision_tokenizer.layers.1.0.norm_latents.weight": "model-00001-of-00004.safetensors",
667
+ "vlm.vision_tokenizer.layers.1.0.norm_media.bias": "model-00001-of-00004.safetensors",
668
+ "vlm.vision_tokenizer.layers.1.0.norm_media.weight": "model-00001-of-00004.safetensors",
669
+ "vlm.vision_tokenizer.layers.1.0.to_kv.weight": "model-00001-of-00004.safetensors",
670
+ "vlm.vision_tokenizer.layers.1.0.to_out.weight": "model-00001-of-00004.safetensors",
671
+ "vlm.vision_tokenizer.layers.1.0.to_q.weight": "model-00001-of-00004.safetensors",
672
+ "vlm.vision_tokenizer.layers.1.1.0.bias": "model-00001-of-00004.safetensors",
673
+ "vlm.vision_tokenizer.layers.1.1.0.weight": "model-00001-of-00004.safetensors",
674
+ "vlm.vision_tokenizer.layers.1.1.1.weight": "model-00001-of-00004.safetensors",
675
+ "vlm.vision_tokenizer.layers.1.1.3.weight": "model-00001-of-00004.safetensors",
676
+ "vlm.vision_tokenizer.layers.2.0.norm_latents.bias": "model-00001-of-00004.safetensors",
677
+ "vlm.vision_tokenizer.layers.2.0.norm_latents.weight": "model-00001-of-00004.safetensors",
678
+ "vlm.vision_tokenizer.layers.2.0.norm_media.bias": "model-00001-of-00004.safetensors",
679
+ "vlm.vision_tokenizer.layers.2.0.norm_media.weight": "model-00001-of-00004.safetensors",
680
+ "vlm.vision_tokenizer.layers.2.0.to_kv.weight": "model-00001-of-00004.safetensors",
681
+ "vlm.vision_tokenizer.layers.2.0.to_out.weight": "model-00001-of-00004.safetensors",
682
+ "vlm.vision_tokenizer.layers.2.0.to_q.weight": "model-00001-of-00004.safetensors",
683
+ "vlm.vision_tokenizer.layers.2.1.0.bias": "model-00001-of-00004.safetensors",
684
+ "vlm.vision_tokenizer.layers.2.1.0.weight": "model-00001-of-00004.safetensors",
685
+ "vlm.vision_tokenizer.layers.2.1.1.weight": "model-00001-of-00004.safetensors",
686
+ "vlm.vision_tokenizer.layers.2.1.3.weight": "model-00001-of-00004.safetensors",
687
+ "vlm.vision_tokenizer.layers.3.0.norm_latents.bias": "model-00001-of-00004.safetensors",
688
+ "vlm.vision_tokenizer.layers.3.0.norm_latents.weight": "model-00001-of-00004.safetensors",
689
+ "vlm.vision_tokenizer.layers.3.0.norm_media.bias": "model-00001-of-00004.safetensors",
690
+ "vlm.vision_tokenizer.layers.3.0.norm_media.weight": "model-00001-of-00004.safetensors",
691
+ "vlm.vision_tokenizer.layers.3.0.to_kv.weight": "model-00001-of-00004.safetensors",
692
+ "vlm.vision_tokenizer.layers.3.0.to_out.weight": "model-00001-of-00004.safetensors",
693
+ "vlm.vision_tokenizer.layers.3.0.to_q.weight": "model-00001-of-00004.safetensors",
694
+ "vlm.vision_tokenizer.layers.3.1.0.bias": "model-00001-of-00004.safetensors",
695
+ "vlm.vision_tokenizer.layers.3.1.0.weight": "model-00001-of-00004.safetensors",
696
+ "vlm.vision_tokenizer.layers.3.1.1.weight": "model-00001-of-00004.safetensors",
697
+ "vlm.vision_tokenizer.layers.3.1.3.weight": "model-00001-of-00004.safetensors",
698
+ "vlm.vision_tokenizer.layers.4.0.norm_latents.bias": "model-00001-of-00004.safetensors",
699
+ "vlm.vision_tokenizer.layers.4.0.norm_latents.weight": "model-00001-of-00004.safetensors",
700
+ "vlm.vision_tokenizer.layers.4.0.norm_media.bias": "model-00001-of-00004.safetensors",
701
+ "vlm.vision_tokenizer.layers.4.0.norm_media.weight": "model-00001-of-00004.safetensors",
702
+ "vlm.vision_tokenizer.layers.4.0.to_kv.weight": "model-00001-of-00004.safetensors",
703
+ "vlm.vision_tokenizer.layers.4.0.to_out.weight": "model-00001-of-00004.safetensors",
704
+ "vlm.vision_tokenizer.layers.4.0.to_q.weight": "model-00001-of-00004.safetensors",
705
+ "vlm.vision_tokenizer.layers.4.1.0.bias": "model-00001-of-00004.safetensors",
706
+ "vlm.vision_tokenizer.layers.4.1.0.weight": "model-00001-of-00004.safetensors",
707
+ "vlm.vision_tokenizer.layers.4.1.1.weight": "model-00001-of-00004.safetensors",
708
+ "vlm.vision_tokenizer.layers.4.1.3.weight": "model-00001-of-00004.safetensors",
709
+ "vlm.vision_tokenizer.layers.5.0.norm_latents.bias": "model-00001-of-00004.safetensors",
710
+ "vlm.vision_tokenizer.layers.5.0.norm_latents.weight": "model-00001-of-00004.safetensors",
711
+ "vlm.vision_tokenizer.layers.5.0.norm_media.bias": "model-00001-of-00004.safetensors",
712
+ "vlm.vision_tokenizer.layers.5.0.norm_media.weight": "model-00001-of-00004.safetensors",
713
+ "vlm.vision_tokenizer.layers.5.0.to_kv.weight": "model-00001-of-00004.safetensors",
714
+ "vlm.vision_tokenizer.layers.5.0.to_out.weight": "model-00001-of-00004.safetensors",
715
+ "vlm.vision_tokenizer.layers.5.0.to_q.weight": "model-00001-of-00004.safetensors",
716
+ "vlm.vision_tokenizer.layers.5.1.0.bias": "model-00001-of-00004.safetensors",
717
+ "vlm.vision_tokenizer.layers.5.1.0.weight": "model-00001-of-00004.safetensors",
718
+ "vlm.vision_tokenizer.layers.5.1.1.weight": "model-00001-of-00004.safetensors",
719
+ "vlm.vision_tokenizer.layers.5.1.3.weight": "model-00001-of-00004.safetensors",
720
+ "vlm.vision_tokenizer.norm.bias": "model-00001-of-00004.safetensors",
721
+ "vlm.vision_tokenizer.norm.weight": "model-00001-of-00004.safetensors",
722
+ "vlm.vision_tokenizer.projection.bias": "model-00001-of-00004.safetensors",
723
+ "vlm.vision_tokenizer.projection.weight": "model-00001-of-00004.safetensors"
724
+ }
725
+ }