Desm0nt commited on
Commit
d60d47e
1 Parent(s): 3b33cae

UPD. New chekpoint. Safetensor

Browse files
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0807f43c073e941583d649eac76fa06b448e5b761824464efb3d1e0558d2f186
3
+ size 4944121600
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8fb4210c1910dc311987343e81586186d1d0a2e1f403945a6e65adbcb2402a3
3
+ size 3349208696
model.safetensors.index.json ADDED
@@ -0,0 +1,600 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8293242880
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.vision_embed_tokens.glb_GN": "model-00001-of-00002.safetensors",
202
+ "model.vision_embed_tokens.img_processor.vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
203
+ "model.vision_embed_tokens.img_processor.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
204
+ "model.vision_embed_tokens.img_processor.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
205
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
206
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
207
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
208
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
209
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
210
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
211
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
212
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
213
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
214
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
222
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
223
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
224
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
225
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
226
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
227
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
228
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
229
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
236
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
238
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
239
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
240
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
241
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
242
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
243
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
244
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
245
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
248
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
250
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
252
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
254
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
255
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
256
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
257
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
258
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
259
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
260
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
261
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
262
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
264
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
266
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
268
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
270
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
271
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
272
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
273
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
274
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
275
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
276
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
277
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
278
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
280
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
286
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
287
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
288
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
289
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
290
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
291
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
292
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
293
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
296
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
298
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
300
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
302
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
303
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
304
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
305
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
306
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
307
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
308
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
309
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
310
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
312
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
316
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
318
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
319
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
320
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
321
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
322
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
323
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
324
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
325
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
326
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
327
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
328
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
334
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
335
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
336
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
337
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
338
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
339
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
340
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
341
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
346
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
348
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
350
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
351
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
352
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
353
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
354
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
355
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
356
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
357
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
358
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
360
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
362
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
364
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
365
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
366
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
367
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
368
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
369
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
370
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
371
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
372
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
373
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
374
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
376
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
380
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
382
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
383
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
384
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
385
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
386
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
387
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
388
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
389
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
392
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
394
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
396
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
398
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
399
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
400
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
401
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
402
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
403
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
404
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
405
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
406
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
408
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
409
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
414
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
415
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
416
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
417
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
418
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
419
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
420
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
421
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
430
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
431
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
432
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
433
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
446
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
447
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
448
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
449
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
450
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
451
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
452
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
453
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
460
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
462
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
463
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
464
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
465
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
466
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
467
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
468
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
469
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
470
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
471
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
472
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
473
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
474
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
475
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
476
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
477
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
478
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
479
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
480
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
481
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
482
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
483
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
484
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
485
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
486
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
488
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
489
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
490
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
492
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
493
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
494
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
495
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
496
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
497
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
498
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
499
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
500
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
501
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
502
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
504
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
505
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
506
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
507
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
508
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
509
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
510
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
511
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
512
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
513
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
514
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
515
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
516
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
517
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
518
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
519
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
520
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
521
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
522
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
523
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
524
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
525
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
526
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
527
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
528
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
529
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
530
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
531
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
532
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
533
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
534
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
535
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
536
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
537
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
538
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
539
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
540
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
541
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
542
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
543
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
544
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
545
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
546
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
547
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
548
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
549
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
550
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
551
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
552
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
553
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
554
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
555
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
556
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
557
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
558
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
559
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
560
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
561
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
562
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
563
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
564
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
565
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
566
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
567
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
568
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
569
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
570
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
571
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
572
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
573
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
574
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
575
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
576
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
577
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
578
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
579
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
580
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
581
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
582
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
583
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
584
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
585
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
586
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
587
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
588
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
589
+ "model.vision_embed_tokens.img_processor.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
590
+ "model.vision_embed_tokens.img_processor.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors",
591
+ "model.vision_embed_tokens.img_processor.vision_model.pre_layrnorm.bias": "model-00001-of-00002.safetensors",
592
+ "model.vision_embed_tokens.img_processor.vision_model.pre_layrnorm.weight": "model-00001-of-00002.safetensors",
593
+ "model.vision_embed_tokens.img_projection.0.bias": "model-00001-of-00002.safetensors",
594
+ "model.vision_embed_tokens.img_projection.0.weight": "model-00001-of-00002.safetensors",
595
+ "model.vision_embed_tokens.img_projection.2.bias": "model-00001-of-00002.safetensors",
596
+ "model.vision_embed_tokens.img_projection.2.weight": "model-00001-of-00002.safetensors",
597
+ "model.vision_embed_tokens.sub_GN": "model-00001-of-00002.safetensors",
598
+ "model.vision_embed_tokens.wte.weight": "model-00001-of-00002.safetensors"
599
+ }
600
+ }
modeling_phi3_v.py CHANGED
@@ -40,7 +40,6 @@ from transformers.utils import (
40
  add_code_sample_docstrings,
41
  add_start_docstrings,
42
  add_start_docstrings_to_model_forward,
43
- is_flash_attn_2_available,
44
  is_flash_attn_greater_or_equal_2_10,
45
  logging,
46
  replace_return_docstrings,
@@ -49,11 +48,13 @@ from .configuration_phi3_v import Phi3VConfig
49
  from .image_embedding_phi3_v import Phi3ImageEmbedding
50
 
51
 
52
- if is_flash_attn_2_available():
53
  from flash_attn import flash_attn_func, flash_attn_varlen_func
54
  from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa
55
 
56
  _flash_supports_window_size = "window_size" in list(inspect.signature(flash_attn_func).parameters)
 
 
57
 
58
  logger = logging.get_logger(__name__)
59
 
@@ -1000,8 +1001,8 @@ PHI3V_INPUTS_DOCSTRING = r"""
1000
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
1001
  model's internal embedding lookup matrix.
1002
  pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)):
1003
- The tensors corresponding to the input images. Pixel values can be obtained using [`AutoImageProcessor`].
1004
- See [`Phi3ImageProcessor.__call__`] for details.
1005
  image_sizes (`torch.LongTensor` of shape `(batch_size, 2)`, *optional*):
1006
  The sizes of the images in the batch, being (height, width) for each image.
1007
  use_cache (`bool`, *optional*):
@@ -1046,7 +1047,7 @@ class Phi3VModel(Phi3VPreTrainedModel):
1046
  **config.embd_layer
1047
  }
1048
  self.vision_embed_tokens = Phi3ImageEmbedding(config, wte=self.embed_tokens, **embedding_config)
1049
- # # set wte the same for vision embedding
1050
  # self.vision_embed_tokens.wte.weight = self.embed_tokens.weight
1051
 
1052
  self.layers = nn.ModuleList(
@@ -1629,4 +1630,4 @@ class Phi3VForTokenClassification(Phi3VPreTrainedModel):
1629
  logits=logits,
1630
  hidden_states=model_outputs.hidden_states,
1631
  attentions=model_outputs.attentions,
1632
- )
 
40
  add_code_sample_docstrings,
41
  add_start_docstrings,
42
  add_start_docstrings_to_model_forward,
 
43
  is_flash_attn_greater_or_equal_2_10,
44
  logging,
45
  replace_return_docstrings,
 
48
  from .image_embedding_phi3_v import Phi3ImageEmbedding
49
 
50
 
51
+ try:
52
  from flash_attn import flash_attn_func, flash_attn_varlen_func
53
  from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input # noqa
54
 
55
  _flash_supports_window_size = "window_size" in list(inspect.signature(flash_attn_func).parameters)
56
+ except ImportError:
57
+ pass
58
 
59
  logger = logging.get_logger(__name__)
60
 
 
1001
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
1002
  model's internal embedding lookup matrix.
1003
  pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)):
1004
+ The tensors corresponding to the input images. Pixel values can be obtained using [`AutoImageProcessor`].
1005
+ See [`Phi3ImageProcessor.__call__`] for details.
1006
  image_sizes (`torch.LongTensor` of shape `(batch_size, 2)`, *optional*):
1007
  The sizes of the images in the batch, being (height, width) for each image.
1008
  use_cache (`bool`, *optional*):
 
1047
  **config.embd_layer
1048
  }
1049
  self.vision_embed_tokens = Phi3ImageEmbedding(config, wte=self.embed_tokens, **embedding_config)
1050
+ # # set wte the same for vision embedding
1051
  # self.vision_embed_tokens.wte.weight = self.embed_tokens.weight
1052
 
1053
  self.layers = nn.ModuleList(
 
1630
  logits=logits,
1631
  hidden_states=model_outputs.hidden_states,
1632
  attentions=model_outputs.attentions,
1633
+ )
sample_inference.py ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+ from PIL import Image
4
+ import requests
5
+ import torch
6
+ from transformers import AutoModelForCausalLM
7
+ from transformers import AutoProcessor
8
+ model_path = "./"
9
+
10
+ kwargs = {}
11
+ kwargs['torch_dtype'] = torch.bfloat16
12
+
13
+ processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
14
+ model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype="auto").cuda()
15
+
16
+ user_prompt = '<|user|>\n'
17
+ assistant_prompt = '<|assistant|>\n'
18
+ prompt_suffix = "<|end|>\n"
19
+
20
+ #################################################### text-only ####################################################
21
+ # single-image prompt
22
+ prompt = f"{user_prompt}what is the answer for 1+1? Explain it.{prompt_suffix}{assistant_prompt}"
23
+ print(f">>> Prompt\n{prompt}")
24
+ inputs = processor(prompt, images=None, return_tensors="pt").to("cuda:0")
25
+ generate_ids = model.generate(**inputs,
26
+ max_new_tokens=1000,
27
+ eos_token_id=processor.tokenizer.eos_token_id,
28
+ )
29
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
30
+ response = processor.batch_decode(generate_ids,
31
+ skip_special_tokens=True,
32
+ clean_up_tokenization_spaces=False)[0]
33
+ print(f'>>> Response\n{response}')
34
+
35
+ #################################################### text-only 2 ####################################################
36
+ # single-image prompt
37
+ prompt = f"{user_prompt}Give me the code for sloving two-sum problem.{prompt_suffix}{assistant_prompt}"
38
+ print(f">>> Prompt\n{prompt}")
39
+ inputs = processor(prompt, images=None, return_tensors="pt").to("cuda:0")
40
+ generate_ids = model.generate(**inputs,
41
+ max_new_tokens=1000,
42
+ eos_token_id=processor.tokenizer.eos_token_id,
43
+ )
44
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
45
+ response = processor.batch_decode(generate_ids,
46
+ skip_special_tokens=True,
47
+ clean_up_tokenization_spaces=False)[0]
48
+ print(f'>>> Response\n{response}')
49
+
50
+
51
+ #################################################### EXAMPLE 1 ####################################################
52
+ # single-image prompt
53
+ prompt = f"{user_prompt}<|image_1|>\nWhat is shown in this image?{prompt_suffix}{assistant_prompt}"
54
+ url = "https://www.ilankelman.org/stopsigns/australia.jpg"
55
+ print(f">>> Prompt\n{prompt}")
56
+ image = Image.open(requests.get(url, stream=True).raw)
57
+ inputs = processor(prompt, image, return_tensors="pt").to("cuda:0")
58
+ generate_ids = model.generate(**inputs,
59
+ max_new_tokens=1000,
60
+ eos_token_id=processor.tokenizer.eos_token_id,
61
+ )
62
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
63
+ response = processor.batch_decode(generate_ids,
64
+ skip_special_tokens=True,
65
+ clean_up_tokenization_spaces=False)[0]
66
+ print(f'>>> Response\n{response}')
67
+
68
+ #################################################### EXAMPLE 2 ####################################################
69
+ # multiple image prompt
70
+ # Note: image tokens must start from <|image_1|>
71
+ prompt = f"{user_prompt}<|image_1|>\n<|image_2|>\n What is shown in this two images?{prompt_suffix}{assistant_prompt}"
72
+ print(f">>> Prompt\n{prompt}")
73
+ url = "https://www.ilankelman.org/stopsigns/australia.jpg"
74
+ image_1 = Image.open(requests.get(url, stream=True).raw)
75
+ url = "https://img.freepik.com/free-photo/painting-mountain-lake-with-mountain-background_188544-9126.jpg?w=2000"
76
+ image_2 = Image.open(requests.get(url, stream=True).raw)
77
+ images = [image_1, image_2]
78
+ inputs = processor(prompt, images, return_tensors="pt").to("cuda:0")
79
+ generate_ids = model.generate(**inputs,
80
+ max_new_tokens=1000,
81
+ eos_token_id=processor.tokenizer.eos_token_id,
82
+ )
83
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
84
+ response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
85
+ print(f'>>> Response\n{response}')
86
+
87
+ #################################################### EXAMPLE 3 ####################################################
88
+ # chat template
89
+ chat = [
90
+ {"role": "user", "content": "<|image_1|>\nWhat is shown in this image?"},
91
+ {"role": "assistant", "content": "The image depicts a street scene with a prominent red stop sign in the foreground. The background showcases a building with traditional Chinese architecture, characterized by its red roof and ornate decorations. There are also several statues of lions, which are common in Chinese culture, positioned in front of the building. The street is lined with various shops and businesses, and there's a car passing by."},
92
+ {"role": "user", "content": "What is so special about this image"}
93
+ ]
94
+ url = "https://www.ilankelman.org/stopsigns/australia.jpg"
95
+ image = Image.open(requests.get(url, stream=True).raw)
96
+ prompt = processor.tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
97
+ # need to remove last <|endoftext|> if it is there, which is used for training, not inference. For training, make sure to add <|endoftext|> in the end.
98
+ if prompt.endswith("<|endoftext|>"):
99
+ prompt = prompt.rstrip("<|endoftext|>")
100
+
101
+ print(f">>> Prompt\n{prompt}")
102
+
103
+ inputs = processor(prompt, [image], return_tensors="pt").to("cuda:0")
104
+ generate_ids = model.generate(**inputs,
105
+ max_new_tokens=1000,
106
+ eos_token_id=processor.tokenizer.eos_token_id,
107
+ )
108
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
109
+ response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
110
+ print(f'>>> Response\n{response}')
111
+
112
+
113
+ ############################# to markdown #############################
114
+ # single-image prompt
115
+ prompt = f"{user_prompt}<|image_1|>\nCan you convert the table to markdown format?{prompt_suffix}{assistant_prompt}"
116
+ url = "https://support.content.office.net/en-us/media/3dd2b79b-9160-403d-9967-af893d17b580.png"
117
+ image = Image.open(requests.get(url, stream=True).raw)
118
+ inputs = processor(prompt, image, return_tensors="pt").to("cuda:0")
119
+
120
+ print(f">>> Prompt\n{prompt}")
121
+ generate_ids = model.generate(**inputs,
122
+ max_new_tokens=1000,
123
+ eos_token_id=processor.tokenizer.eos_token_id,
124
+ )
125
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
126
+ response = processor.batch_decode(generate_ids,
127
+ skip_special_tokens=False,
128
+ clean_up_tokenization_spaces=False)[0]
129
+ print(f'>>> Response\n{response}')
sft_args.json CHANGED
@@ -7,7 +7,7 @@
7
  "additional_trainable_parameters": [],
8
  "tuner_backend": "peft",
9
  "template_type": "phi3-vl",
10
- "output_dir": "D:\\_____NEW_NN\\LLM\\MiniCPM-V\\finetune\\output\\phi3-vision-128k-instruct\\v0-20240531-071942",
11
  "add_output_dir_suffix": true,
12
  "ddp_backend": null,
13
  "ddp_find_unused_parameters": null,
@@ -45,21 +45,21 @@
45
  "bnb_4bit_use_double_quant": true,
46
  "bnb_4bit_quant_storage": null,
47
  "lora_target_modules": [
48
- "v_proj",
49
- "q_proj",
50
- "out_proj",
51
- "gate_up_proj",
52
  "img_projection.0",
53
  "qkv_proj",
54
- "img_projection.2",
 
55
  "fc1",
56
- "k_proj",
 
57
  "fc2",
58
- "o_proj",
59
- "down_proj"
 
60
  ],
61
- "lora_rank": 64,
62
- "lora_alpha": 64,
63
  "lora_dropout_p": 0.05,
64
  "lora_bias_trainable": "none",
65
  "lora_modules_to_save": [],
@@ -115,24 +115,24 @@
115
  "lisa_step_interval": 20,
116
  "gradient_checkpointing": true,
117
  "deepspeed": null,
118
- "batch_size": 1,
119
- "eval_batch_size": 1,
120
  "num_train_epochs": 4,
121
  "max_steps": -1,
122
  "optim": "adamw_torch",
123
  "adam_beta1": 0.9,
124
- "adam_beta2": 0.999,
125
- "learning_rate": 0.00015,
126
  "weight_decay": 0.1,
127
  "gradient_accumulation_steps": 2,
128
  "max_grad_norm": 0.5,
129
  "predict_with_generate": false,
130
- "lr_scheduler_type": "linear",
131
  "warmup_ratio": 0.05,
132
  "eval_steps": 50,
133
- "save_steps": 369,
134
  "save_only_model": false,
135
- "save_total_limit": 2,
136
  "logging_steps": 5,
137
  "dataloader_num_workers": 1,
138
  "dataloader_pin_memory": true,
@@ -149,7 +149,7 @@
149
  "use_flash_attn": null,
150
  "ignore_args_error": false,
151
  "check_model_is_latest": true,
152
- "logging_dir": "D:\\_____NEW_NN\\LLM\\MiniCPM-V\\finetune\\output\\phi3-vision-128k-instruct\\v0-20240531-071942/runs",
153
  "report_to": [
154
  "tensorboard"
155
  ],
@@ -205,5 +205,5 @@
205
  "load_in_4bit": false,
206
  "load_in_8bit": false,
207
  "train_sampler_random": true,
208
- "training_args": "Seq2SeqTrainingArguments(output_dir='D:\\\\_____NEW_NN\\\\LLM\\\\MiniCPM-V\\\\finetune\\\\output\\\\phi3-vision-128k-instruct\\\\v0-20240531-071942', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, evaluation_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.00015, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=4, max_steps=-1, lr_scheduler_type=<SchedulerType.LINEAR: 'linear'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='D:\\\\_____NEW_NN\\\\LLM\\\\MiniCPM-V\\\\finetune\\\\output\\\\phi3-vision-128k-instruct\\\\v0-20240531-071942/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=369, save_total_limit=2, save_safetensors=True, save_on_each_node=True, save_only_model=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='D:\\\\_____NEW_NN\\\\LLM\\\\MiniCPM-V\\\\finetune\\\\output\\\\phi3-vision-128k-instruct\\\\v0-20240531-071942', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, gradient_accumulation_kwargs=None), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"do_sample\": true,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000,\n \"temperature\": 0.3,\n \"top_k\": 20,\n \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=738)"
209
  }
 
7
  "additional_trainable_parameters": [],
8
  "tuner_backend": "peft",
9
  "template_type": "phi3-vl",
10
+ "output_dir": "D:\\_____NEW_NN\\LLM\\MiniCPM-V\\finetune\\output\\phi3-vision-128k-instruct\\v4-20240619-010346",
11
  "add_output_dir_suffix": true,
12
  "ddp_backend": null,
13
  "ddp_find_unused_parameters": null,
 
45
  "bnb_4bit_use_double_quant": true,
46
  "bnb_4bit_quant_storage": null,
47
  "lora_target_modules": [
48
+ "k_proj",
 
 
 
49
  "img_projection.0",
50
  "qkv_proj",
51
+ "down_proj",
52
+ "o_proj",
53
  "fc1",
54
+ "q_proj",
55
+ "out_proj",
56
  "fc2",
57
+ "gate_up_proj",
58
+ "img_projection.2",
59
+ "v_proj"
60
  ],
61
+ "lora_rank": 128,
62
+ "lora_alpha": 128,
63
  "lora_dropout_p": 0.05,
64
  "lora_bias_trainable": "none",
65
  "lora_modules_to_save": [],
 
115
  "lisa_step_interval": 20,
116
  "gradient_checkpointing": true,
117
  "deepspeed": null,
118
+ "batch_size": 2,
119
+ "eval_batch_size": 2,
120
  "num_train_epochs": 4,
121
  "max_steps": -1,
122
  "optim": "adamw_torch",
123
  "adam_beta1": 0.9,
124
+ "adam_beta2": 0.95,
125
+ "learning_rate": 0.00014,
126
  "weight_decay": 0.1,
127
  "gradient_accumulation_steps": 2,
128
  "max_grad_norm": 0.5,
129
  "predict_with_generate": false,
130
+ "lr_scheduler_type": "cosine",
131
  "warmup_ratio": 0.05,
132
  "eval_steps": 50,
133
+ "save_steps": 389,
134
  "save_only_model": false,
135
+ "save_total_limit": 8,
136
  "logging_steps": 5,
137
  "dataloader_num_workers": 1,
138
  "dataloader_pin_memory": true,
 
149
  "use_flash_attn": null,
150
  "ignore_args_error": false,
151
  "check_model_is_latest": true,
152
+ "logging_dir": "D:\\_____NEW_NN\\LLM\\MiniCPM-V\\finetune\\output\\phi3-vision-128k-instruct\\v4-20240619-010346/runs",
153
  "report_to": [
154
  "tensorboard"
155
  ],
 
205
  "load_in_4bit": false,
206
  "load_in_8bit": false,
207
  "train_sampler_random": true,
208
+ "training_args": "Seq2SeqTrainingArguments(output_dir='D:\\\\_____NEW_NN\\\\LLM\\\\MiniCPM-V\\\\finetune\\\\output\\\\phi3-vision-128k-instruct\\\\v4-20240619-010346', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, evaluation_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, learning_rate=0.00014, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=4, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='D:\\\\_____NEW_NN\\\\LLM\\\\MiniCPM-V\\\\finetune\\\\output\\\\phi3-vision-128k-instruct\\\\v4-20240619-010346/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=389, save_total_limit=8, save_safetensors=True, save_on_each_node=True, save_only_model=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='D:\\\\_____NEW_NN\\\\LLM\\\\MiniCPM-V\\\\finetune\\\\output\\\\phi3-vision-128k-instruct\\\\v4-20240619-010346', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, gradient_accumulation_kwargs=None), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"do_sample\": true,\n \"eos_token_id\": 32000,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32000,\n \"temperature\": 0.3,\n \"top_k\": 20,\n \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=797)"
209
  }