SFconvertbot commited on
Commit
5daf548
1 Parent(s): 17f90c4

Adding `safetensors` variant of this model

Browse files

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08af9bf6e6410c00cde14b72d0e711eb632fa18bee960958c0223f2cef3857f
3
+ size 9927986042
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb167a03cad68b3e9e19b23b656dfc4be52559718ddcedba0f40cd943653429e
3
+ size 9980457712
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d838c68dcecf5e972adbb1ab17aefb3fcef2d9756d750318727238447d06d0e5
3
+ size 7761633516
model.safetensors.index.json ADDED
@@ -0,0 +1,1055 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27669951494
4
+ },
5
+ "weight_map": {
6
+ "clip_projector.cross_attn.k.weight": "model-00003-of-00003.safetensors",
7
+ "clip_projector.cross_attn.k_bias": "model-00003-of-00003.safetensors",
8
+ "clip_projector.cross_attn.proj.bias": "model-00003-of-00003.safetensors",
9
+ "clip_projector.cross_attn.proj.weight": "model-00003-of-00003.safetensors",
10
+ "clip_projector.cross_attn.q.weight": "model-00003-of-00003.safetensors",
11
+ "clip_projector.cross_attn.q_bias": "model-00003-of-00003.safetensors",
12
+ "clip_projector.cross_attn.v.weight": "model-00003-of-00003.safetensors",
13
+ "clip_projector.cross_attn.v_bias": "model-00003-of-00003.safetensors",
14
+ "clip_projector.norm1_k.bias": "model-00003-of-00003.safetensors",
15
+ "clip_projector.norm1_k.weight": "model-00003-of-00003.safetensors",
16
+ "clip_projector.norm1_q.bias": "model-00003-of-00003.safetensors",
17
+ "clip_projector.norm1_q.weight": "model-00003-of-00003.safetensors",
18
+ "clip_projector.norm1_v.bias": "model-00003-of-00003.safetensors",
19
+ "clip_projector.norm1_v.weight": "model-00003-of-00003.safetensors",
20
+ "clip_projector2.cross_attn.k.weight": "model-00003-of-00003.safetensors",
21
+ "clip_projector2.cross_attn.k_bias": "model-00003-of-00003.safetensors",
22
+ "clip_projector2.cross_attn.proj.bias": "model-00003-of-00003.safetensors",
23
+ "clip_projector2.cross_attn.proj.weight": "model-00003-of-00003.safetensors",
24
+ "clip_projector2.cross_attn.q.weight": "model-00003-of-00003.safetensors",
25
+ "clip_projector2.cross_attn.q_bias": "model-00003-of-00003.safetensors",
26
+ "clip_projector2.cross_attn.v.weight": "model-00003-of-00003.safetensors",
27
+ "clip_projector2.cross_attn.v_bias": "model-00003-of-00003.safetensors",
28
+ "clip_projector2.norm1_k.bias": "model-00003-of-00003.safetensors",
29
+ "clip_projector2.norm1_k.weight": "model-00003-of-00003.safetensors",
30
+ "clip_projector2.norm1_q.bias": "model-00003-of-00003.safetensors",
31
+ "clip_projector2.norm1_q.weight": "model-00003-of-00003.safetensors",
32
+ "clip_projector2.norm1_v.bias": "model-00003-of-00003.safetensors",
33
+ "clip_projector2.norm1_v.weight": "model-00003-of-00003.safetensors",
34
+ "itm_head.bias": "model-00003-of-00003.safetensors",
35
+ "itm_head.weight": "model-00003-of-00003.safetensors",
36
+ "logit_scale": "model-00001-of-00003.safetensors",
37
+ "qllama.lm_head.weight": "model-00003-of-00003.safetensors",
38
+ "qllama.model.embed_tokens.weight": "model-00002-of-00003.safetensors",
39
+ "qllama.model.layers.0.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "qllama.model.layers.0.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
41
+ "qllama.model.layers.0.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
42
+ "qllama.model.layers.0.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
43
+ "qllama.model.layers.0.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
44
+ "qllama.model.layers.0.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
45
+ "qllama.model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
46
+ "qllama.model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
47
+ "qllama.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
48
+ "qllama.model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
49
+ "qllama.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "qllama.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
51
+ "qllama.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
52
+ "qllama.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
53
+ "qllama.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
54
+ "qllama.model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors",
55
+ "qllama.model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
56
+ "qllama.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
57
+ "qllama.model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
58
+ "qllama.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
59
+ "qllama.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
60
+ "qllama.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
61
+ "qllama.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
62
+ "qllama.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
63
+ "qllama.model.layers.10.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
64
+ "qllama.model.layers.10.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
65
+ "qllama.model.layers.10.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
66
+ "qllama.model.layers.10.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
67
+ "qllama.model.layers.10.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
68
+ "qllama.model.layers.10.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
69
+ "qllama.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
70
+ "qllama.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
71
+ "qllama.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
72
+ "qllama.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
73
+ "qllama.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "qllama.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
75
+ "qllama.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
76
+ "qllama.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
77
+ "qllama.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
78
+ "qllama.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
79
+ "qllama.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
80
+ "qllama.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
81
+ "qllama.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
82
+ "qllama.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
83
+ "qllama.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
84
+ "qllama.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
85
+ "qllama.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
86
+ "qllama.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
87
+ "qllama.model.layers.12.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
88
+ "qllama.model.layers.12.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
89
+ "qllama.model.layers.12.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
90
+ "qllama.model.layers.12.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
91
+ "qllama.model.layers.12.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
92
+ "qllama.model.layers.12.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
93
+ "qllama.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "qllama.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
95
+ "qllama.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
96
+ "qllama.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
97
+ "qllama.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "qllama.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
99
+ "qllama.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
100
+ "qllama.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "qllama.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
102
+ "qllama.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "qllama.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
104
+ "qllama.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
105
+ "qllama.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
106
+ "qllama.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "qllama.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
108
+ "qllama.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
109
+ "qllama.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
110
+ "qllama.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
111
+ "qllama.model.layers.14.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
+ "qllama.model.layers.14.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
113
+ "qllama.model.layers.14.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
114
+ "qllama.model.layers.14.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
115
+ "qllama.model.layers.14.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
116
+ "qllama.model.layers.14.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
117
+ "qllama.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
118
+ "qllama.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
119
+ "qllama.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
120
+ "qllama.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
121
+ "qllama.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
122
+ "qllama.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
123
+ "qllama.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
124
+ "qllama.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
125
+ "qllama.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
126
+ "qllama.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
127
+ "qllama.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
128
+ "qllama.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
129
+ "qllama.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
130
+ "qllama.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
131
+ "qllama.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
132
+ "qllama.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
133
+ "qllama.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
134
+ "qllama.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
135
+ "qllama.model.layers.16.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
136
+ "qllama.model.layers.16.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
137
+ "qllama.model.layers.16.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
138
+ "qllama.model.layers.16.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
139
+ "qllama.model.layers.16.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
140
+ "qllama.model.layers.16.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
141
+ "qllama.model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
142
+ "qllama.model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
143
+ "qllama.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
144
+ "qllama.model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
145
+ "qllama.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
146
+ "qllama.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
147
+ "qllama.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
148
+ "qllama.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
149
+ "qllama.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
150
+ "qllama.model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
151
+ "qllama.model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
152
+ "qllama.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
153
+ "qllama.model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
154
+ "qllama.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
155
+ "qllama.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
156
+ "qllama.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
157
+ "qllama.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
158
+ "qllama.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
159
+ "qllama.model.layers.18.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
160
+ "qllama.model.layers.18.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
161
+ "qllama.model.layers.18.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
162
+ "qllama.model.layers.18.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
163
+ "qllama.model.layers.18.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
164
+ "qllama.model.layers.18.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
165
+ "qllama.model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "qllama.model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
167
+ "qllama.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
168
+ "qllama.model.layers.18.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
169
+ "qllama.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "qllama.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
171
+ "qllama.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
172
+ "qllama.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
173
+ "qllama.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
174
+ "qllama.model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "qllama.model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
176
+ "qllama.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
177
+ "qllama.model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
178
+ "qllama.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "qllama.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
180
+ "qllama.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
181
+ "qllama.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
182
+ "qllama.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
183
+ "qllama.model.layers.2.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
184
+ "qllama.model.layers.2.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
185
+ "qllama.model.layers.2.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
186
+ "qllama.model.layers.2.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
187
+ "qllama.model.layers.2.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
188
+ "qllama.model.layers.2.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
189
+ "qllama.model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
190
+ "qllama.model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
191
+ "qllama.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
192
+ "qllama.model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
193
+ "qllama.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
194
+ "qllama.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
195
+ "qllama.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
196
+ "qllama.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
197
+ "qllama.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
198
+ "qllama.model.layers.20.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
199
+ "qllama.model.layers.20.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
200
+ "qllama.model.layers.20.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
201
+ "qllama.model.layers.20.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
202
+ "qllama.model.layers.20.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
203
+ "qllama.model.layers.20.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
204
+ "qllama.model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
205
+ "qllama.model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
206
+ "qllama.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
207
+ "qllama.model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
208
+ "qllama.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
209
+ "qllama.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
210
+ "qllama.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
211
+ "qllama.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
212
+ "qllama.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
213
+ "qllama.model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
214
+ "qllama.model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
215
+ "qllama.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
216
+ "qllama.model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
217
+ "qllama.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
218
+ "qllama.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
219
+ "qllama.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
220
+ "qllama.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
221
+ "qllama.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
222
+ "qllama.model.layers.22.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
223
+ "qllama.model.layers.22.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
224
+ "qllama.model.layers.22.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
225
+ "qllama.model.layers.22.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
226
+ "qllama.model.layers.22.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
227
+ "qllama.model.layers.22.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
228
+ "qllama.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "qllama.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
230
+ "qllama.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
231
+ "qllama.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
232
+ "qllama.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
233
+ "qllama.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
234
+ "qllama.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
235
+ "qllama.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
236
+ "qllama.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
237
+ "qllama.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "qllama.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
239
+ "qllama.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
240
+ "qllama.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
241
+ "qllama.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
242
+ "qllama.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
243
+ "qllama.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
244
+ "qllama.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
245
+ "qllama.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
246
+ "qllama.model.layers.24.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
247
+ "qllama.model.layers.24.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
248
+ "qllama.model.layers.24.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
249
+ "qllama.model.layers.24.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
250
+ "qllama.model.layers.24.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
251
+ "qllama.model.layers.24.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
252
+ "qllama.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
253
+ "qllama.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
254
+ "qllama.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
255
+ "qllama.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
256
+ "qllama.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
257
+ "qllama.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
258
+ "qllama.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
259
+ "qllama.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
260
+ "qllama.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
261
+ "qllama.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
262
+ "qllama.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
263
+ "qllama.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
264
+ "qllama.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
265
+ "qllama.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
266
+ "qllama.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
267
+ "qllama.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
268
+ "qllama.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
269
+ "qllama.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
270
+ "qllama.model.layers.26.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
271
+ "qllama.model.layers.26.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
272
+ "qllama.model.layers.26.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
273
+ "qllama.model.layers.26.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
274
+ "qllama.model.layers.26.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
275
+ "qllama.model.layers.26.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
276
+ "qllama.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
277
+ "qllama.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
278
+ "qllama.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
279
+ "qllama.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
280
+ "qllama.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
281
+ "qllama.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
282
+ "qllama.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
283
+ "qllama.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
284
+ "qllama.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
285
+ "qllama.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
286
+ "qllama.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
287
+ "qllama.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
288
+ "qllama.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
289
+ "qllama.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
290
+ "qllama.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
291
+ "qllama.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
292
+ "qllama.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
293
+ "qllama.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
294
+ "qllama.model.layers.28.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
295
+ "qllama.model.layers.28.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
296
+ "qllama.model.layers.28.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
297
+ "qllama.model.layers.28.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
298
+ "qllama.model.layers.28.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
299
+ "qllama.model.layers.28.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
300
+ "qllama.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
301
+ "qllama.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
302
+ "qllama.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
303
+ "qllama.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
304
+ "qllama.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
305
+ "qllama.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
306
+ "qllama.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
307
+ "qllama.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
308
+ "qllama.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
309
+ "qllama.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
310
+ "qllama.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
311
+ "qllama.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
312
+ "qllama.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
313
+ "qllama.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
314
+ "qllama.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
315
+ "qllama.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
316
+ "qllama.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
317
+ "qllama.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
318
+ "qllama.model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
319
+ "qllama.model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
320
+ "qllama.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
321
+ "qllama.model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
322
+ "qllama.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
323
+ "qllama.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
324
+ "qllama.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
325
+ "qllama.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
326
+ "qllama.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
327
+ "qllama.model.layers.30.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
328
+ "qllama.model.layers.30.cross_attn.norm1.weight": "model-00003-of-00003.safetensors",
329
+ "qllama.model.layers.30.cross_attn.norm2.weight": "model-00003-of-00003.safetensors",
330
+ "qllama.model.layers.30.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
331
+ "qllama.model.layers.30.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
332
+ "qllama.model.layers.30.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
333
+ "qllama.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
334
+ "qllama.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
335
+ "qllama.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
336
+ "qllama.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
337
+ "qllama.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
338
+ "qllama.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
339
+ "qllama.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
340
+ "qllama.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
341
+ "qllama.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
342
+ "qllama.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
343
+ "qllama.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
344
+ "qllama.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
345
+ "qllama.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
346
+ "qllama.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
347
+ "qllama.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
348
+ "qllama.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
349
+ "qllama.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
350
+ "qllama.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
351
+ "qllama.model.layers.4.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
352
+ "qllama.model.layers.4.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
353
+ "qllama.model.layers.4.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
354
+ "qllama.model.layers.4.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
355
+ "qllama.model.layers.4.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
356
+ "qllama.model.layers.4.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
357
+ "qllama.model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
358
+ "qllama.model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
359
+ "qllama.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
360
+ "qllama.model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
361
+ "qllama.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
362
+ "qllama.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
363
+ "qllama.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
364
+ "qllama.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
365
+ "qllama.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
366
+ "qllama.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
367
+ "qllama.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
368
+ "qllama.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
369
+ "qllama.model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
370
+ "qllama.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
371
+ "qllama.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
372
+ "qllama.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
373
+ "qllama.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
374
+ "qllama.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
375
+ "qllama.model.layers.6.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
376
+ "qllama.model.layers.6.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
377
+ "qllama.model.layers.6.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
378
+ "qllama.model.layers.6.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
379
+ "qllama.model.layers.6.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
380
+ "qllama.model.layers.6.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
381
+ "qllama.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
382
+ "qllama.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
383
+ "qllama.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
384
+ "qllama.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
385
+ "qllama.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
386
+ "qllama.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
387
+ "qllama.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
388
+ "qllama.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
389
+ "qllama.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
390
+ "qllama.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
391
+ "qllama.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
392
+ "qllama.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
393
+ "qllama.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
394
+ "qllama.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
395
+ "qllama.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
396
+ "qllama.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
397
+ "qllama.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
398
+ "qllama.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
399
+ "qllama.model.layers.8.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
400
+ "qllama.model.layers.8.cross_attn.norm1.weight": "model-00002-of-00003.safetensors",
401
+ "qllama.model.layers.8.cross_attn.norm2.weight": "model-00002-of-00003.safetensors",
402
+ "qllama.model.layers.8.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
403
+ "qllama.model.layers.8.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
404
+ "qllama.model.layers.8.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
405
+ "qllama.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
406
+ "qllama.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
407
+ "qllama.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
408
+ "qllama.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
409
+ "qllama.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
410
+ "qllama.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
411
+ "qllama.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
412
+ "qllama.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
413
+ "qllama.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
414
+ "qllama.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
415
+ "qllama.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
416
+ "qllama.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
417
+ "qllama.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
418
+ "qllama.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
419
+ "qllama.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
420
+ "qllama.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
421
+ "qllama.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
422
+ "qllama.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
423
+ "qllama.model.norm.weight": "model-00003-of-00003.safetensors",
424
+ "query_tokens": "model-00001-of-00003.safetensors",
425
+ "text_projection": "model-00001-of-00003.safetensors",
426
+ "vision_model.embeddings.class_embedding": "model-00001-of-00003.safetensors",
427
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00003.safetensors",
428
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
429
+ "vision_model.embeddings.position_embedding": "model-00001-of-00003.safetensors",
430
+ "vision_model.encoder.layers.0.attn.k_norm.weight": "model-00001-of-00003.safetensors",
431
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00003.safetensors",
432
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00003.safetensors",
433
+ "vision_model.encoder.layers.0.attn.q_norm.weight": "model-00001-of-00003.safetensors",
434
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
435
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00003.safetensors",
436
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00003.safetensors",
437
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
438
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
439
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
440
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
441
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00003.safetensors",
442
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00003.safetensors",
443
+ "vision_model.encoder.layers.1.attn.k_norm.weight": "model-00001-of-00003.safetensors",
444
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00003.safetensors",
445
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00003.safetensors",
446
+ "vision_model.encoder.layers.1.attn.q_norm.weight": "model-00001-of-00003.safetensors",
447
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
448
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00003.safetensors",
449
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00003.safetensors",
450
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
451
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
452
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
453
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
454
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00003.safetensors",
455
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00003.safetensors",
456
+ "vision_model.encoder.layers.10.attn.k_norm.weight": "model-00001-of-00003.safetensors",
457
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00003.safetensors",
458
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00003.safetensors",
459
+ "vision_model.encoder.layers.10.attn.q_norm.weight": "model-00001-of-00003.safetensors",
460
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
461
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00003.safetensors",
462
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00003.safetensors",
463
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
464
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
465
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
466
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
467
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00003.safetensors",
468
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00003.safetensors",
469
+ "vision_model.encoder.layers.11.attn.k_norm.weight": "model-00001-of-00003.safetensors",
470
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00003.safetensors",
471
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00003.safetensors",
472
+ "vision_model.encoder.layers.11.attn.q_norm.weight": "model-00001-of-00003.safetensors",
473
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
474
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00003.safetensors",
475
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00003.safetensors",
476
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
477
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
478
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
479
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
480
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00003.safetensors",
481
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00003.safetensors",
482
+ "vision_model.encoder.layers.12.attn.k_norm.weight": "model-00001-of-00003.safetensors",
483
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00003.safetensors",
484
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00003.safetensors",
485
+ "vision_model.encoder.layers.12.attn.q_norm.weight": "model-00001-of-00003.safetensors",
486
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
487
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00003.safetensors",
488
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00003.safetensors",
489
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
490
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
491
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
492
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
493
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00003.safetensors",
494
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00003.safetensors",
495
+ "vision_model.encoder.layers.13.attn.k_norm.weight": "model-00001-of-00003.safetensors",
496
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00003.safetensors",
497
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00003.safetensors",
498
+ "vision_model.encoder.layers.13.attn.q_norm.weight": "model-00001-of-00003.safetensors",
499
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
500
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00003.safetensors",
501
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00003.safetensors",
502
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
503
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
504
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
505
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
506
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00003.safetensors",
507
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00003.safetensors",
508
+ "vision_model.encoder.layers.14.attn.k_norm.weight": "model-00001-of-00003.safetensors",
509
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00003.safetensors",
510
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00003.safetensors",
511
+ "vision_model.encoder.layers.14.attn.q_norm.weight": "model-00001-of-00003.safetensors",
512
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
513
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00003.safetensors",
514
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00003.safetensors",
515
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
516
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
517
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
518
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
519
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00003.safetensors",
520
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00003.safetensors",
521
+ "vision_model.encoder.layers.15.attn.k_norm.weight": "model-00001-of-00003.safetensors",
522
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00003.safetensors",
523
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00003.safetensors",
524
+ "vision_model.encoder.layers.15.attn.q_norm.weight": "model-00001-of-00003.safetensors",
525
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
526
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00003.safetensors",
527
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00003.safetensors",
528
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
529
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
530
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
531
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
532
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00003.safetensors",
533
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00003.safetensors",
534
+ "vision_model.encoder.layers.16.attn.k_norm.weight": "model-00001-of-00003.safetensors",
535
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00003.safetensors",
536
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00003.safetensors",
537
+ "vision_model.encoder.layers.16.attn.q_norm.weight": "model-00001-of-00003.safetensors",
538
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
539
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00003.safetensors",
540
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00003.safetensors",
541
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
542
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
543
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
544
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
545
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00003.safetensors",
546
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00003.safetensors",
547
+ "vision_model.encoder.layers.17.attn.k_norm.weight": "model-00001-of-00003.safetensors",
548
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00003.safetensors",
549
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00003.safetensors",
550
+ "vision_model.encoder.layers.17.attn.q_norm.weight": "model-00001-of-00003.safetensors",
551
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
552
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00003.safetensors",
553
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00003.safetensors",
554
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
555
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
556
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
557
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
558
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00003.safetensors",
559
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00003.safetensors",
560
+ "vision_model.encoder.layers.18.attn.k_norm.weight": "model-00001-of-00003.safetensors",
561
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00003.safetensors",
562
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00003.safetensors",
563
+ "vision_model.encoder.layers.18.attn.q_norm.weight": "model-00001-of-00003.safetensors",
564
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
565
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00003.safetensors",
566
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00003.safetensors",
567
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
568
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
569
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
570
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
571
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00003.safetensors",
572
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00003.safetensors",
573
+ "vision_model.encoder.layers.19.attn.k_norm.weight": "model-00001-of-00003.safetensors",
574
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00003.safetensors",
575
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00003.safetensors",
576
+ "vision_model.encoder.layers.19.attn.q_norm.weight": "model-00001-of-00003.safetensors",
577
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
578
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00003.safetensors",
579
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00003.safetensors",
580
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
581
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
582
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
583
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
584
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00003.safetensors",
585
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00003.safetensors",
586
+ "vision_model.encoder.layers.2.attn.k_norm.weight": "model-00001-of-00003.safetensors",
587
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00003.safetensors",
588
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00003.safetensors",
589
+ "vision_model.encoder.layers.2.attn.q_norm.weight": "model-00001-of-00003.safetensors",
590
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
591
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00003.safetensors",
592
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00003.safetensors",
593
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
594
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
595
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
596
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
597
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00003.safetensors",
598
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00003.safetensors",
599
+ "vision_model.encoder.layers.20.attn.k_norm.weight": "model-00001-of-00003.safetensors",
600
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00003.safetensors",
601
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00003.safetensors",
602
+ "vision_model.encoder.layers.20.attn.q_norm.weight": "model-00001-of-00003.safetensors",
603
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
604
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00003.safetensors",
605
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00003.safetensors",
606
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
607
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
608
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
609
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
610
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00003.safetensors",
611
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00003.safetensors",
612
+ "vision_model.encoder.layers.21.attn.k_norm.weight": "model-00001-of-00003.safetensors",
613
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00003.safetensors",
614
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00003.safetensors",
615
+ "vision_model.encoder.layers.21.attn.q_norm.weight": "model-00001-of-00003.safetensors",
616
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
617
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00003.safetensors",
618
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00003.safetensors",
619
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
620
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
621
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
622
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
623
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00003.safetensors",
624
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00003.safetensors",
625
+ "vision_model.encoder.layers.22.attn.k_norm.weight": "model-00001-of-00003.safetensors",
626
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00003.safetensors",
627
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00003.safetensors",
628
+ "vision_model.encoder.layers.22.attn.q_norm.weight": "model-00001-of-00003.safetensors",
629
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
630
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00003.safetensors",
631
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00003.safetensors",
632
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
633
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
634
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
635
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
636
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00003.safetensors",
637
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00003.safetensors",
638
+ "vision_model.encoder.layers.23.attn.k_norm.weight": "model-00001-of-00003.safetensors",
639
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00003.safetensors",
640
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00003.safetensors",
641
+ "vision_model.encoder.layers.23.attn.q_norm.weight": "model-00001-of-00003.safetensors",
642
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
643
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00003.safetensors",
644
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00003.safetensors",
645
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
646
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
647
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
648
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
649
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00003.safetensors",
650
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00003.safetensors",
651
+ "vision_model.encoder.layers.24.attn.k_norm.weight": "model-00001-of-00003.safetensors",
652
+ "vision_model.encoder.layers.24.attn.proj.bias": "model-00001-of-00003.safetensors",
653
+ "vision_model.encoder.layers.24.attn.proj.weight": "model-00001-of-00003.safetensors",
654
+ "vision_model.encoder.layers.24.attn.q_norm.weight": "model-00001-of-00003.safetensors",
655
+ "vision_model.encoder.layers.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
656
+ "vision_model.encoder.layers.24.ls1": "model-00001-of-00003.safetensors",
657
+ "vision_model.encoder.layers.24.ls2": "model-00001-of-00003.safetensors",
658
+ "vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
659
+ "vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
660
+ "vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
661
+ "vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
662
+ "vision_model.encoder.layers.24.norm1.weight": "model-00001-of-00003.safetensors",
663
+ "vision_model.encoder.layers.24.norm2.weight": "model-00001-of-00003.safetensors",
664
+ "vision_model.encoder.layers.25.attn.k_norm.weight": "model-00001-of-00003.safetensors",
665
+ "vision_model.encoder.layers.25.attn.proj.bias": "model-00001-of-00003.safetensors",
666
+ "vision_model.encoder.layers.25.attn.proj.weight": "model-00001-of-00003.safetensors",
667
+ "vision_model.encoder.layers.25.attn.q_norm.weight": "model-00001-of-00003.safetensors",
668
+ "vision_model.encoder.layers.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
669
+ "vision_model.encoder.layers.25.ls1": "model-00001-of-00003.safetensors",
670
+ "vision_model.encoder.layers.25.ls2": "model-00001-of-00003.safetensors",
671
+ "vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
672
+ "vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
673
+ "vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
674
+ "vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
675
+ "vision_model.encoder.layers.25.norm1.weight": "model-00001-of-00003.safetensors",
676
+ "vision_model.encoder.layers.25.norm2.weight": "model-00001-of-00003.safetensors",
677
+ "vision_model.encoder.layers.26.attn.k_norm.weight": "model-00001-of-00003.safetensors",
678
+ "vision_model.encoder.layers.26.attn.proj.bias": "model-00001-of-00003.safetensors",
679
+ "vision_model.encoder.layers.26.attn.proj.weight": "model-00001-of-00003.safetensors",
680
+ "vision_model.encoder.layers.26.attn.q_norm.weight": "model-00001-of-00003.safetensors",
681
+ "vision_model.encoder.layers.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
682
+ "vision_model.encoder.layers.26.ls1": "model-00001-of-00003.safetensors",
683
+ "vision_model.encoder.layers.26.ls2": "model-00001-of-00003.safetensors",
684
+ "vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
685
+ "vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
686
+ "vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
687
+ "vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
688
+ "vision_model.encoder.layers.26.norm1.weight": "model-00001-of-00003.safetensors",
689
+ "vision_model.encoder.layers.26.norm2.weight": "model-00001-of-00003.safetensors",
690
+ "vision_model.encoder.layers.27.attn.k_norm.weight": "model-00001-of-00003.safetensors",
691
+ "vision_model.encoder.layers.27.attn.proj.bias": "model-00001-of-00003.safetensors",
692
+ "vision_model.encoder.layers.27.attn.proj.weight": "model-00001-of-00003.safetensors",
693
+ "vision_model.encoder.layers.27.attn.q_norm.weight": "model-00001-of-00003.safetensors",
694
+ "vision_model.encoder.layers.27.attn.qkv.weight": "model-00001-of-00003.safetensors",
695
+ "vision_model.encoder.layers.27.ls1": "model-00001-of-00003.safetensors",
696
+ "vision_model.encoder.layers.27.ls2": "model-00001-of-00003.safetensors",
697
+ "vision_model.encoder.layers.27.mlp.fc1.bias": "model-00001-of-00003.safetensors",
698
+ "vision_model.encoder.layers.27.mlp.fc1.weight": "model-00001-of-00003.safetensors",
699
+ "vision_model.encoder.layers.27.mlp.fc2.bias": "model-00001-of-00003.safetensors",
700
+ "vision_model.encoder.layers.27.mlp.fc2.weight": "model-00001-of-00003.safetensors",
701
+ "vision_model.encoder.layers.27.norm1.weight": "model-00001-of-00003.safetensors",
702
+ "vision_model.encoder.layers.27.norm2.weight": "model-00001-of-00003.safetensors",
703
+ "vision_model.encoder.layers.28.attn.k_norm.weight": "model-00001-of-00003.safetensors",
704
+ "vision_model.encoder.layers.28.attn.proj.bias": "model-00001-of-00003.safetensors",
705
+ "vision_model.encoder.layers.28.attn.proj.weight": "model-00001-of-00003.safetensors",
706
+ "vision_model.encoder.layers.28.attn.q_norm.weight": "model-00001-of-00003.safetensors",
707
+ "vision_model.encoder.layers.28.attn.qkv.weight": "model-00001-of-00003.safetensors",
708
+ "vision_model.encoder.layers.28.ls1": "model-00001-of-00003.safetensors",
709
+ "vision_model.encoder.layers.28.ls2": "model-00001-of-00003.safetensors",
710
+ "vision_model.encoder.layers.28.mlp.fc1.bias": "model-00001-of-00003.safetensors",
711
+ "vision_model.encoder.layers.28.mlp.fc1.weight": "model-00001-of-00003.safetensors",
712
+ "vision_model.encoder.layers.28.mlp.fc2.bias": "model-00001-of-00003.safetensors",
713
+ "vision_model.encoder.layers.28.mlp.fc2.weight": "model-00001-of-00003.safetensors",
714
+ "vision_model.encoder.layers.28.norm1.weight": "model-00001-of-00003.safetensors",
715
+ "vision_model.encoder.layers.28.norm2.weight": "model-00001-of-00003.safetensors",
716
+ "vision_model.encoder.layers.29.attn.k_norm.weight": "model-00001-of-00003.safetensors",
717
+ "vision_model.encoder.layers.29.attn.proj.bias": "model-00001-of-00003.safetensors",
718
+ "vision_model.encoder.layers.29.attn.proj.weight": "model-00001-of-00003.safetensors",
719
+ "vision_model.encoder.layers.29.attn.q_norm.weight": "model-00001-of-00003.safetensors",
720
+ "vision_model.encoder.layers.29.attn.qkv.weight": "model-00001-of-00003.safetensors",
721
+ "vision_model.encoder.layers.29.ls1": "model-00001-of-00003.safetensors",
722
+ "vision_model.encoder.layers.29.ls2": "model-00001-of-00003.safetensors",
723
+ "vision_model.encoder.layers.29.mlp.fc1.bias": "model-00001-of-00003.safetensors",
724
+ "vision_model.encoder.layers.29.mlp.fc1.weight": "model-00001-of-00003.safetensors",
725
+ "vision_model.encoder.layers.29.mlp.fc2.bias": "model-00001-of-00003.safetensors",
726
+ "vision_model.encoder.layers.29.mlp.fc2.weight": "model-00001-of-00003.safetensors",
727
+ "vision_model.encoder.layers.29.norm1.weight": "model-00001-of-00003.safetensors",
728
+ "vision_model.encoder.layers.29.norm2.weight": "model-00001-of-00003.safetensors",
729
+ "vision_model.encoder.layers.3.attn.k_norm.weight": "model-00001-of-00003.safetensors",
730
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00003.safetensors",
731
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00003.safetensors",
732
+ "vision_model.encoder.layers.3.attn.q_norm.weight": "model-00001-of-00003.safetensors",
733
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
734
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00003.safetensors",
735
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00003.safetensors",
736
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
737
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
738
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
739
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
740
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00003.safetensors",
741
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00003.safetensors",
742
+ "vision_model.encoder.layers.30.attn.k_norm.weight": "model-00001-of-00003.safetensors",
743
+ "vision_model.encoder.layers.30.attn.proj.bias": "model-00001-of-00003.safetensors",
744
+ "vision_model.encoder.layers.30.attn.proj.weight": "model-00001-of-00003.safetensors",
745
+ "vision_model.encoder.layers.30.attn.q_norm.weight": "model-00001-of-00003.safetensors",
746
+ "vision_model.encoder.layers.30.attn.qkv.weight": "model-00001-of-00003.safetensors",
747
+ "vision_model.encoder.layers.30.ls1": "model-00001-of-00003.safetensors",
748
+ "vision_model.encoder.layers.30.ls2": "model-00001-of-00003.safetensors",
749
+ "vision_model.encoder.layers.30.mlp.fc1.bias": "model-00001-of-00003.safetensors",
750
+ "vision_model.encoder.layers.30.mlp.fc1.weight": "model-00001-of-00003.safetensors",
751
+ "vision_model.encoder.layers.30.mlp.fc2.bias": "model-00001-of-00003.safetensors",
752
+ "vision_model.encoder.layers.30.mlp.fc2.weight": "model-00001-of-00003.safetensors",
753
+ "vision_model.encoder.layers.30.norm1.weight": "model-00001-of-00003.safetensors",
754
+ "vision_model.encoder.layers.30.norm2.weight": "model-00001-of-00003.safetensors",
755
+ "vision_model.encoder.layers.31.attn.k_norm.weight": "model-00001-of-00003.safetensors",
756
+ "vision_model.encoder.layers.31.attn.proj.bias": "model-00001-of-00003.safetensors",
757
+ "vision_model.encoder.layers.31.attn.proj.weight": "model-00001-of-00003.safetensors",
758
+ "vision_model.encoder.layers.31.attn.q_norm.weight": "model-00001-of-00003.safetensors",
759
+ "vision_model.encoder.layers.31.attn.qkv.weight": "model-00001-of-00003.safetensors",
760
+ "vision_model.encoder.layers.31.ls1": "model-00001-of-00003.safetensors",
761
+ "vision_model.encoder.layers.31.ls2": "model-00001-of-00003.safetensors",
762
+ "vision_model.encoder.layers.31.mlp.fc1.bias": "model-00001-of-00003.safetensors",
763
+ "vision_model.encoder.layers.31.mlp.fc1.weight": "model-00001-of-00003.safetensors",
764
+ "vision_model.encoder.layers.31.mlp.fc2.bias": "model-00001-of-00003.safetensors",
765
+ "vision_model.encoder.layers.31.mlp.fc2.weight": "model-00001-of-00003.safetensors",
766
+ "vision_model.encoder.layers.31.norm1.weight": "model-00001-of-00003.safetensors",
767
+ "vision_model.encoder.layers.31.norm2.weight": "model-00001-of-00003.safetensors",
768
+ "vision_model.encoder.layers.32.attn.k_norm.weight": "model-00001-of-00003.safetensors",
769
+ "vision_model.encoder.layers.32.attn.proj.bias": "model-00001-of-00003.safetensors",
770
+ "vision_model.encoder.layers.32.attn.proj.weight": "model-00001-of-00003.safetensors",
771
+ "vision_model.encoder.layers.32.attn.q_norm.weight": "model-00001-of-00003.safetensors",
772
+ "vision_model.encoder.layers.32.attn.qkv.weight": "model-00001-of-00003.safetensors",
773
+ "vision_model.encoder.layers.32.ls1": "model-00001-of-00003.safetensors",
774
+ "vision_model.encoder.layers.32.ls2": "model-00001-of-00003.safetensors",
775
+ "vision_model.encoder.layers.32.mlp.fc1.bias": "model-00001-of-00003.safetensors",
776
+ "vision_model.encoder.layers.32.mlp.fc1.weight": "model-00001-of-00003.safetensors",
777
+ "vision_model.encoder.layers.32.mlp.fc2.bias": "model-00001-of-00003.safetensors",
778
+ "vision_model.encoder.layers.32.mlp.fc2.weight": "model-00001-of-00003.safetensors",
779
+ "vision_model.encoder.layers.32.norm1.weight": "model-00001-of-00003.safetensors",
780
+ "vision_model.encoder.layers.32.norm2.weight": "model-00001-of-00003.safetensors",
781
+ "vision_model.encoder.layers.33.attn.k_norm.weight": "model-00001-of-00003.safetensors",
782
+ "vision_model.encoder.layers.33.attn.proj.bias": "model-00001-of-00003.safetensors",
783
+ "vision_model.encoder.layers.33.attn.proj.weight": "model-00001-of-00003.safetensors",
784
+ "vision_model.encoder.layers.33.attn.q_norm.weight": "model-00001-of-00003.safetensors",
785
+ "vision_model.encoder.layers.33.attn.qkv.weight": "model-00001-of-00003.safetensors",
786
+ "vision_model.encoder.layers.33.ls1": "model-00001-of-00003.safetensors",
787
+ "vision_model.encoder.layers.33.ls2": "model-00001-of-00003.safetensors",
788
+ "vision_model.encoder.layers.33.mlp.fc1.bias": "model-00001-of-00003.safetensors",
789
+ "vision_model.encoder.layers.33.mlp.fc1.weight": "model-00001-of-00003.safetensors",
790
+ "vision_model.encoder.layers.33.mlp.fc2.bias": "model-00001-of-00003.safetensors",
791
+ "vision_model.encoder.layers.33.mlp.fc2.weight": "model-00001-of-00003.safetensors",
792
+ "vision_model.encoder.layers.33.norm1.weight": "model-00001-of-00003.safetensors",
793
+ "vision_model.encoder.layers.33.norm2.weight": "model-00001-of-00003.safetensors",
794
+ "vision_model.encoder.layers.34.attn.k_norm.weight": "model-00001-of-00003.safetensors",
795
+ "vision_model.encoder.layers.34.attn.proj.bias": "model-00001-of-00003.safetensors",
796
+ "vision_model.encoder.layers.34.attn.proj.weight": "model-00001-of-00003.safetensors",
797
+ "vision_model.encoder.layers.34.attn.q_norm.weight": "model-00001-of-00003.safetensors",
798
+ "vision_model.encoder.layers.34.attn.qkv.weight": "model-00001-of-00003.safetensors",
799
+ "vision_model.encoder.layers.34.ls1": "model-00001-of-00003.safetensors",
800
+ "vision_model.encoder.layers.34.ls2": "model-00001-of-00003.safetensors",
801
+ "vision_model.encoder.layers.34.mlp.fc1.bias": "model-00001-of-00003.safetensors",
802
+ "vision_model.encoder.layers.34.mlp.fc1.weight": "model-00001-of-00003.safetensors",
803
+ "vision_model.encoder.layers.34.mlp.fc2.bias": "model-00001-of-00003.safetensors",
804
+ "vision_model.encoder.layers.34.mlp.fc2.weight": "model-00001-of-00003.safetensors",
805
+ "vision_model.encoder.layers.34.norm1.weight": "model-00001-of-00003.safetensors",
806
+ "vision_model.encoder.layers.34.norm2.weight": "model-00001-of-00003.safetensors",
807
+ "vision_model.encoder.layers.35.attn.k_norm.weight": "model-00001-of-00003.safetensors",
808
+ "vision_model.encoder.layers.35.attn.proj.bias": "model-00001-of-00003.safetensors",
809
+ "vision_model.encoder.layers.35.attn.proj.weight": "model-00001-of-00003.safetensors",
810
+ "vision_model.encoder.layers.35.attn.q_norm.weight": "model-00001-of-00003.safetensors",
811
+ "vision_model.encoder.layers.35.attn.qkv.weight": "model-00001-of-00003.safetensors",
812
+ "vision_model.encoder.layers.35.ls1": "model-00001-of-00003.safetensors",
813
+ "vision_model.encoder.layers.35.ls2": "model-00001-of-00003.safetensors",
814
+ "vision_model.encoder.layers.35.mlp.fc1.bias": "model-00001-of-00003.safetensors",
815
+ "vision_model.encoder.layers.35.mlp.fc1.weight": "model-00001-of-00003.safetensors",
816
+ "vision_model.encoder.layers.35.mlp.fc2.bias": "model-00001-of-00003.safetensors",
817
+ "vision_model.encoder.layers.35.mlp.fc2.weight": "model-00001-of-00003.safetensors",
818
+ "vision_model.encoder.layers.35.norm1.weight": "model-00001-of-00003.safetensors",
819
+ "vision_model.encoder.layers.35.norm2.weight": "model-00001-of-00003.safetensors",
820
+ "vision_model.encoder.layers.36.attn.k_norm.weight": "model-00001-of-00003.safetensors",
821
+ "vision_model.encoder.layers.36.attn.proj.bias": "model-00001-of-00003.safetensors",
822
+ "vision_model.encoder.layers.36.attn.proj.weight": "model-00001-of-00003.safetensors",
823
+ "vision_model.encoder.layers.36.attn.q_norm.weight": "model-00001-of-00003.safetensors",
824
+ "vision_model.encoder.layers.36.attn.qkv.weight": "model-00001-of-00003.safetensors",
825
+ "vision_model.encoder.layers.36.ls1": "model-00001-of-00003.safetensors",
826
+ "vision_model.encoder.layers.36.ls2": "model-00001-of-00003.safetensors",
827
+ "vision_model.encoder.layers.36.mlp.fc1.bias": "model-00001-of-00003.safetensors",
828
+ "vision_model.encoder.layers.36.mlp.fc1.weight": "model-00001-of-00003.safetensors",
829
+ "vision_model.encoder.layers.36.mlp.fc2.bias": "model-00001-of-00003.safetensors",
830
+ "vision_model.encoder.layers.36.mlp.fc2.weight": "model-00001-of-00003.safetensors",
831
+ "vision_model.encoder.layers.36.norm1.weight": "model-00001-of-00003.safetensors",
832
+ "vision_model.encoder.layers.36.norm2.weight": "model-00001-of-00003.safetensors",
833
+ "vision_model.encoder.layers.37.attn.k_norm.weight": "model-00001-of-00003.safetensors",
834
+ "vision_model.encoder.layers.37.attn.proj.bias": "model-00001-of-00003.safetensors",
835
+ "vision_model.encoder.layers.37.attn.proj.weight": "model-00001-of-00003.safetensors",
836
+ "vision_model.encoder.layers.37.attn.q_norm.weight": "model-00001-of-00003.safetensors",
837
+ "vision_model.encoder.layers.37.attn.qkv.weight": "model-00001-of-00003.safetensors",
838
+ "vision_model.encoder.layers.37.ls1": "model-00001-of-00003.safetensors",
839
+ "vision_model.encoder.layers.37.ls2": "model-00001-of-00003.safetensors",
840
+ "vision_model.encoder.layers.37.mlp.fc1.bias": "model-00001-of-00003.safetensors",
841
+ "vision_model.encoder.layers.37.mlp.fc1.weight": "model-00001-of-00003.safetensors",
842
+ "vision_model.encoder.layers.37.mlp.fc2.bias": "model-00001-of-00003.safetensors",
843
+ "vision_model.encoder.layers.37.mlp.fc2.weight": "model-00001-of-00003.safetensors",
844
+ "vision_model.encoder.layers.37.norm1.weight": "model-00001-of-00003.safetensors",
845
+ "vision_model.encoder.layers.37.norm2.weight": "model-00001-of-00003.safetensors",
846
+ "vision_model.encoder.layers.38.attn.k_norm.weight": "model-00001-of-00003.safetensors",
847
+ "vision_model.encoder.layers.38.attn.proj.bias": "model-00001-of-00003.safetensors",
848
+ "vision_model.encoder.layers.38.attn.proj.weight": "model-00001-of-00003.safetensors",
849
+ "vision_model.encoder.layers.38.attn.q_norm.weight": "model-00001-of-00003.safetensors",
850
+ "vision_model.encoder.layers.38.attn.qkv.weight": "model-00001-of-00003.safetensors",
851
+ "vision_model.encoder.layers.38.ls1": "model-00001-of-00003.safetensors",
852
+ "vision_model.encoder.layers.38.ls2": "model-00001-of-00003.safetensors",
853
+ "vision_model.encoder.layers.38.mlp.fc1.bias": "model-00001-of-00003.safetensors",
854
+ "vision_model.encoder.layers.38.mlp.fc1.weight": "model-00001-of-00003.safetensors",
855
+ "vision_model.encoder.layers.38.mlp.fc2.bias": "model-00001-of-00003.safetensors",
856
+ "vision_model.encoder.layers.38.mlp.fc2.weight": "model-00001-of-00003.safetensors",
857
+ "vision_model.encoder.layers.38.norm1.weight": "model-00001-of-00003.safetensors",
858
+ "vision_model.encoder.layers.38.norm2.weight": "model-00001-of-00003.safetensors",
859
+ "vision_model.encoder.layers.39.attn.k_norm.weight": "model-00001-of-00003.safetensors",
860
+ "vision_model.encoder.layers.39.attn.proj.bias": "model-00001-of-00003.safetensors",
861
+ "vision_model.encoder.layers.39.attn.proj.weight": "model-00001-of-00003.safetensors",
862
+ "vision_model.encoder.layers.39.attn.q_norm.weight": "model-00001-of-00003.safetensors",
863
+ "vision_model.encoder.layers.39.attn.qkv.weight": "model-00001-of-00003.safetensors",
864
+ "vision_model.encoder.layers.39.ls1": "model-00001-of-00003.safetensors",
865
+ "vision_model.encoder.layers.39.ls2": "model-00001-of-00003.safetensors",
866
+ "vision_model.encoder.layers.39.mlp.fc1.bias": "model-00001-of-00003.safetensors",
867
+ "vision_model.encoder.layers.39.mlp.fc1.weight": "model-00001-of-00003.safetensors",
868
+ "vision_model.encoder.layers.39.mlp.fc2.bias": "model-00001-of-00003.safetensors",
869
+ "vision_model.encoder.layers.39.mlp.fc2.weight": "model-00001-of-00003.safetensors",
870
+ "vision_model.encoder.layers.39.norm1.weight": "model-00001-of-00003.safetensors",
871
+ "vision_model.encoder.layers.39.norm2.weight": "model-00001-of-00003.safetensors",
872
+ "vision_model.encoder.layers.4.attn.k_norm.weight": "model-00001-of-00003.safetensors",
873
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00003.safetensors",
874
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00003.safetensors",
875
+ "vision_model.encoder.layers.4.attn.q_norm.weight": "model-00001-of-00003.safetensors",
876
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
877
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00003.safetensors",
878
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00003.safetensors",
879
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
880
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
881
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
882
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
883
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00003.safetensors",
884
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00003.safetensors",
885
+ "vision_model.encoder.layers.40.attn.k_norm.weight": "model-00001-of-00003.safetensors",
886
+ "vision_model.encoder.layers.40.attn.proj.bias": "model-00001-of-00003.safetensors",
887
+ "vision_model.encoder.layers.40.attn.proj.weight": "model-00001-of-00003.safetensors",
888
+ "vision_model.encoder.layers.40.attn.q_norm.weight": "model-00001-of-00003.safetensors",
889
+ "vision_model.encoder.layers.40.attn.qkv.weight": "model-00001-of-00003.safetensors",
890
+ "vision_model.encoder.layers.40.ls1": "model-00001-of-00003.safetensors",
891
+ "vision_model.encoder.layers.40.ls2": "model-00001-of-00003.safetensors",
892
+ "vision_model.encoder.layers.40.mlp.fc1.bias": "model-00002-of-00003.safetensors",
893
+ "vision_model.encoder.layers.40.mlp.fc1.weight": "model-00002-of-00003.safetensors",
894
+ "vision_model.encoder.layers.40.mlp.fc2.bias": "model-00002-of-00003.safetensors",
895
+ "vision_model.encoder.layers.40.mlp.fc2.weight": "model-00002-of-00003.safetensors",
896
+ "vision_model.encoder.layers.40.norm1.weight": "model-00002-of-00003.safetensors",
897
+ "vision_model.encoder.layers.40.norm2.weight": "model-00002-of-00003.safetensors",
898
+ "vision_model.encoder.layers.41.attn.k_norm.weight": "model-00002-of-00003.safetensors",
899
+ "vision_model.encoder.layers.41.attn.proj.bias": "model-00002-of-00003.safetensors",
900
+ "vision_model.encoder.layers.41.attn.proj.weight": "model-00002-of-00003.safetensors",
901
+ "vision_model.encoder.layers.41.attn.q_norm.weight": "model-00002-of-00003.safetensors",
902
+ "vision_model.encoder.layers.41.attn.qkv.weight": "model-00002-of-00003.safetensors",
903
+ "vision_model.encoder.layers.41.ls1": "model-00002-of-00003.safetensors",
904
+ "vision_model.encoder.layers.41.ls2": "model-00002-of-00003.safetensors",
905
+ "vision_model.encoder.layers.41.mlp.fc1.bias": "model-00002-of-00003.safetensors",
906
+ "vision_model.encoder.layers.41.mlp.fc1.weight": "model-00002-of-00003.safetensors",
907
+ "vision_model.encoder.layers.41.mlp.fc2.bias": "model-00002-of-00003.safetensors",
908
+ "vision_model.encoder.layers.41.mlp.fc2.weight": "model-00002-of-00003.safetensors",
909
+ "vision_model.encoder.layers.41.norm1.weight": "model-00002-of-00003.safetensors",
910
+ "vision_model.encoder.layers.41.norm2.weight": "model-00002-of-00003.safetensors",
911
+ "vision_model.encoder.layers.42.attn.k_norm.weight": "model-00002-of-00003.safetensors",
912
+ "vision_model.encoder.layers.42.attn.proj.bias": "model-00002-of-00003.safetensors",
913
+ "vision_model.encoder.layers.42.attn.proj.weight": "model-00002-of-00003.safetensors",
914
+ "vision_model.encoder.layers.42.attn.q_norm.weight": "model-00002-of-00003.safetensors",
915
+ "vision_model.encoder.layers.42.attn.qkv.weight": "model-00002-of-00003.safetensors",
916
+ "vision_model.encoder.layers.42.ls1": "model-00002-of-00003.safetensors",
917
+ "vision_model.encoder.layers.42.ls2": "model-00002-of-00003.safetensors",
918
+ "vision_model.encoder.layers.42.mlp.fc1.bias": "model-00002-of-00003.safetensors",
919
+ "vision_model.encoder.layers.42.mlp.fc1.weight": "model-00002-of-00003.safetensors",
920
+ "vision_model.encoder.layers.42.mlp.fc2.bias": "model-00002-of-00003.safetensors",
921
+ "vision_model.encoder.layers.42.mlp.fc2.weight": "model-00002-of-00003.safetensors",
922
+ "vision_model.encoder.layers.42.norm1.weight": "model-00002-of-00003.safetensors",
923
+ "vision_model.encoder.layers.42.norm2.weight": "model-00002-of-00003.safetensors",
924
+ "vision_model.encoder.layers.43.attn.k_norm.weight": "model-00002-of-00003.safetensors",
925
+ "vision_model.encoder.layers.43.attn.proj.bias": "model-00002-of-00003.safetensors",
926
+ "vision_model.encoder.layers.43.attn.proj.weight": "model-00002-of-00003.safetensors",
927
+ "vision_model.encoder.layers.43.attn.q_norm.weight": "model-00002-of-00003.safetensors",
928
+ "vision_model.encoder.layers.43.attn.qkv.weight": "model-00002-of-00003.safetensors",
929
+ "vision_model.encoder.layers.43.ls1": "model-00002-of-00003.safetensors",
930
+ "vision_model.encoder.layers.43.ls2": "model-00002-of-00003.safetensors",
931
+ "vision_model.encoder.layers.43.mlp.fc1.bias": "model-00002-of-00003.safetensors",
932
+ "vision_model.encoder.layers.43.mlp.fc1.weight": "model-00002-of-00003.safetensors",
933
+ "vision_model.encoder.layers.43.mlp.fc2.bias": "model-00002-of-00003.safetensors",
934
+ "vision_model.encoder.layers.43.mlp.fc2.weight": "model-00002-of-00003.safetensors",
935
+ "vision_model.encoder.layers.43.norm1.weight": "model-00002-of-00003.safetensors",
936
+ "vision_model.encoder.layers.43.norm2.weight": "model-00002-of-00003.safetensors",
937
+ "vision_model.encoder.layers.44.attn.k_norm.weight": "model-00002-of-00003.safetensors",
938
+ "vision_model.encoder.layers.44.attn.proj.bias": "model-00002-of-00003.safetensors",
939
+ "vision_model.encoder.layers.44.attn.proj.weight": "model-00002-of-00003.safetensors",
940
+ "vision_model.encoder.layers.44.attn.q_norm.weight": "model-00002-of-00003.safetensors",
941
+ "vision_model.encoder.layers.44.attn.qkv.weight": "model-00002-of-00003.safetensors",
942
+ "vision_model.encoder.layers.44.ls1": "model-00002-of-00003.safetensors",
943
+ "vision_model.encoder.layers.44.ls2": "model-00002-of-00003.safetensors",
944
+ "vision_model.encoder.layers.44.mlp.fc1.bias": "model-00002-of-00003.safetensors",
945
+ "vision_model.encoder.layers.44.mlp.fc1.weight": "model-00002-of-00003.safetensors",
946
+ "vision_model.encoder.layers.44.mlp.fc2.bias": "model-00002-of-00003.safetensors",
947
+ "vision_model.encoder.layers.44.mlp.fc2.weight": "model-00002-of-00003.safetensors",
948
+ "vision_model.encoder.layers.44.norm1.weight": "model-00002-of-00003.safetensors",
949
+ "vision_model.encoder.layers.44.norm2.weight": "model-00002-of-00003.safetensors",
950
+ "vision_model.encoder.layers.45.attn.k_norm.weight": "model-00002-of-00003.safetensors",
951
+ "vision_model.encoder.layers.45.attn.proj.bias": "model-00002-of-00003.safetensors",
952
+ "vision_model.encoder.layers.45.attn.proj.weight": "model-00002-of-00003.safetensors",
953
+ "vision_model.encoder.layers.45.attn.q_norm.weight": "model-00002-of-00003.safetensors",
954
+ "vision_model.encoder.layers.45.attn.qkv.weight": "model-00002-of-00003.safetensors",
955
+ "vision_model.encoder.layers.45.ls1": "model-00002-of-00003.safetensors",
956
+ "vision_model.encoder.layers.45.ls2": "model-00002-of-00003.safetensors",
957
+ "vision_model.encoder.layers.45.mlp.fc1.bias": "model-00002-of-00003.safetensors",
958
+ "vision_model.encoder.layers.45.mlp.fc1.weight": "model-00002-of-00003.safetensors",
959
+ "vision_model.encoder.layers.45.mlp.fc2.bias": "model-00002-of-00003.safetensors",
960
+ "vision_model.encoder.layers.45.mlp.fc2.weight": "model-00002-of-00003.safetensors",
961
+ "vision_model.encoder.layers.45.norm1.weight": "model-00002-of-00003.safetensors",
962
+ "vision_model.encoder.layers.45.norm2.weight": "model-00002-of-00003.safetensors",
963
+ "vision_model.encoder.layers.46.attn.k_norm.weight": "model-00002-of-00003.safetensors",
964
+ "vision_model.encoder.layers.46.attn.proj.bias": "model-00002-of-00003.safetensors",
965
+ "vision_model.encoder.layers.46.attn.proj.weight": "model-00002-of-00003.safetensors",
966
+ "vision_model.encoder.layers.46.attn.q_norm.weight": "model-00002-of-00003.safetensors",
967
+ "vision_model.encoder.layers.46.attn.qkv.weight": "model-00002-of-00003.safetensors",
968
+ "vision_model.encoder.layers.46.ls1": "model-00002-of-00003.safetensors",
969
+ "vision_model.encoder.layers.46.ls2": "model-00002-of-00003.safetensors",
970
+ "vision_model.encoder.layers.46.mlp.fc1.bias": "model-00002-of-00003.safetensors",
971
+ "vision_model.encoder.layers.46.mlp.fc1.weight": "model-00002-of-00003.safetensors",
972
+ "vision_model.encoder.layers.46.mlp.fc2.bias": "model-00002-of-00003.safetensors",
973
+ "vision_model.encoder.layers.46.mlp.fc2.weight": "model-00002-of-00003.safetensors",
974
+ "vision_model.encoder.layers.46.norm1.weight": "model-00002-of-00003.safetensors",
975
+ "vision_model.encoder.layers.46.norm2.weight": "model-00002-of-00003.safetensors",
976
+ "vision_model.encoder.layers.47.attn.k_norm.weight": "model-00002-of-00003.safetensors",
977
+ "vision_model.encoder.layers.47.attn.proj.bias": "model-00002-of-00003.safetensors",
978
+ "vision_model.encoder.layers.47.attn.proj.weight": "model-00002-of-00003.safetensors",
979
+ "vision_model.encoder.layers.47.attn.q_norm.weight": "model-00002-of-00003.safetensors",
980
+ "vision_model.encoder.layers.47.attn.qkv.weight": "model-00002-of-00003.safetensors",
981
+ "vision_model.encoder.layers.47.ls1": "model-00002-of-00003.safetensors",
982
+ "vision_model.encoder.layers.47.ls2": "model-00002-of-00003.safetensors",
983
+ "vision_model.encoder.layers.47.mlp.fc1.bias": "model-00002-of-00003.safetensors",
984
+ "vision_model.encoder.layers.47.mlp.fc1.weight": "model-00002-of-00003.safetensors",
985
+ "vision_model.encoder.layers.47.mlp.fc2.bias": "model-00002-of-00003.safetensors",
986
+ "vision_model.encoder.layers.47.mlp.fc2.weight": "model-00002-of-00003.safetensors",
987
+ "vision_model.encoder.layers.47.norm1.weight": "model-00002-of-00003.safetensors",
988
+ "vision_model.encoder.layers.47.norm2.weight": "model-00002-of-00003.safetensors",
989
+ "vision_model.encoder.layers.5.attn.k_norm.weight": "model-00001-of-00003.safetensors",
990
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00003.safetensors",
991
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00003.safetensors",
992
+ "vision_model.encoder.layers.5.attn.q_norm.weight": "model-00001-of-00003.safetensors",
993
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
994
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00003.safetensors",
995
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00003.safetensors",
996
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
997
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
998
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
999
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
1000
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00003.safetensors",
1001
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00003.safetensors",
1002
+ "vision_model.encoder.layers.6.attn.k_norm.weight": "model-00001-of-00003.safetensors",
1003
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00003.safetensors",
1004
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00003.safetensors",
1005
+ "vision_model.encoder.layers.6.attn.q_norm.weight": "model-00001-of-00003.safetensors",
1006
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
1007
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00003.safetensors",
1008
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00003.safetensors",
1009
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
1010
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
1011
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
1012
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
1013
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00003.safetensors",
1014
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00003.safetensors",
1015
+ "vision_model.encoder.layers.7.attn.k_norm.weight": "model-00001-of-00003.safetensors",
1016
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00003.safetensors",
1017
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00003.safetensors",
1018
+ "vision_model.encoder.layers.7.attn.q_norm.weight": "model-00001-of-00003.safetensors",
1019
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
1020
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00003.safetensors",
1021
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00003.safetensors",
1022
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
1023
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
1024
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
1025
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
1026
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00003.safetensors",
1027
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00003.safetensors",
1028
+ "vision_model.encoder.layers.8.attn.k_norm.weight": "model-00001-of-00003.safetensors",
1029
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00003.safetensors",
1030
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00003.safetensors",
1031
+ "vision_model.encoder.layers.8.attn.q_norm.weight": "model-00001-of-00003.safetensors",
1032
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
1033
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00003.safetensors",
1034
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00003.safetensors",
1035
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
1036
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
1037
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
1038
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
1039
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00003.safetensors",
1040
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00003.safetensors",
1041
+ "vision_model.encoder.layers.9.attn.k_norm.weight": "model-00001-of-00003.safetensors",
1042
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00003.safetensors",
1043
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00003.safetensors",
1044
+ "vision_model.encoder.layers.9.attn.q_norm.weight": "model-00001-of-00003.safetensors",
1045
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
1046
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00003.safetensors",
1047
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00003.safetensors",
1048
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
1049
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
1050
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
1051
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
1052
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00003.safetensors",
1053
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00003.safetensors"
1054
+ }
1055
+ }