Hugging Face's logo

saim1212
/
qwen2b_upload

Safetensors
qwen2_vl
Model card Files
xet
 Community
saim1212 commited on
Commit
2882a64
·
verified ·
1 Parent(s): 53cb3f4

Upload model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +195 -219
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 8835942400
4
  },
5
  "weight_map": {
6
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -28,126 +28,126 @@
28
  "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
  "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
  "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
32
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
33
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
34
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
35
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
36
- "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
37
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
38
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
39
- "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
40
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
41
- "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
42
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
43
- "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
44
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
45
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
46
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
47
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
48
- "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
49
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
50
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
51
- "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
52
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
53
- "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
54
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
55
- "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
56
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
57
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
58
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
59
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
60
- "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
61
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
62
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
63
- "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
64
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
65
- "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
66
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
67
- "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
68
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
69
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
70
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
71
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
72
- "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
73
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
74
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
75
- "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
76
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
77
- "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
78
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
79
- "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
80
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
81
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
82
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
83
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
84
- "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
85
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
86
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
87
- "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
88
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
89
- "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
90
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
91
- "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
92
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
93
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
94
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
95
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
- "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
97
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
98
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
99
- "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
100
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
101
- "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
102
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
103
- "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
105
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
106
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
107
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
- "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
109
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
110
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
111
- "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
112
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
113
- "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
114
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
115
- "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
117
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
118
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
119
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
- "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
121
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
122
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
123
- "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
124
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
125
- "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
126
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
127
- "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
129
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
130
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
131
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
- "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
133
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
134
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
135
- "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
136
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
- "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
138
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
139
- "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
142
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
143
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
- "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
145
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
146
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
147
- "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
148
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
149
- "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
150
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
  "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
  "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
  "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
@@ -160,54 +160,54 @@
160
  "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
  "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
  "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
169
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
170
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
171
- "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
172
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
173
- "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
174
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
179
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
180
- "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
181
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
182
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
183
- "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
184
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
186
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
- "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
193
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
196
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
- "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
198
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
199
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
200
  "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
201
  "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
202
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
203
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
204
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
205
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
206
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
207
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
208
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
209
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
210
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
211
  "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
212
  "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
  "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
@@ -304,11 +304,11 @@
304
  "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
305
  "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
306
  "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
307
- "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
308
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
309
  "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
311
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
312
  "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
313
  "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
  "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -316,30 +316,30 @@
316
  "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
  "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
  "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
- "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
320
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
322
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
323
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
324
- "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
325
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
327
- "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
- "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
- "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
332
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
333
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
- "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
337
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
339
- "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
340
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
341
- "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
342
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
343
  "model.norm.weight": "model-00002-of-00002.safetensors",
344
  "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
345
  "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
@@ -629,30 +629,6 @@
629
  "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
630
  "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
631
  "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
632
- "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
633
- "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
634
- "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
635
- "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
636
- "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
637
- "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00002.safetensors",
638
- "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00002.safetensors",
639
- "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00002.safetensors",
640
- "visual.blocks.30.norm1.bias": "model-00001-of-00002.safetensors",
641
- "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
642
- "visual.blocks.30.norm2.bias": "model-00001-of-00002.safetensors",
643
- "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
644
- "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
645
- "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
646
- "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
647
- "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
648
- "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
649
- "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00002.safetensors",
650
- "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00002.safetensors",
651
- "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00002.safetensors",
652
- "visual.blocks.31.norm1.bias": "model-00001-of-00002.safetensors",
653
- "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
654
- "visual.blocks.31.norm2.bias": "model-00001-of-00002.safetensors",
655
- "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
656
  "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
657
  "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
658
  "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 4417971200
4
  },
5
  "weight_map": {
6
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
 
28
  "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
  "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
  "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
  "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
  "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
  "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
 
160
  "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
  "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
  "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
200
  "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
201
  "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
211
  "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
212
  "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
  "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
 
304
  "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
305
  "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
306
  "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
308
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
309
  "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
312
  "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
313
  "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
  "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
 
316
  "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
  "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
  "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
325
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
328
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
337
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
340
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
343
  "model.norm.weight": "model-00002-of-00002.safetensors",
344
  "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
345
  "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
 
629
  "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
630
  "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
631
  "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
632
  "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
633
  "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
634
  "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",