Hugging Face's logo

EZCon
/
Huihui-Qwen3-VL-2B-Instruct-abliterated-mlx

Image-Text-to-Text
Transformers
Safetensors
MLX
qwen3_vl
image-to-text
abliterated
uncensored
conversational
Model card Files
xet
Community
hermeschen-ezcon commited on
Commit
cbf27a3
·
verified ·
1 Parent(s): f5b7c8d

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +0 -10
  2. model.safetensors +2 -2
  3. model.safetensors.index.json +1 -395
config.json CHANGED
@@ -4,16 +4,6 @@
4
  ],
5
  "image_token_id": 151655,
6
  "model_type": "qwen3_vl",
7
- "quantization": {
8
- "group_size": 64,
9
- "bits": 8,
10
- "mode": "affine"
11
- },
12
- "quantization_config": {
13
- "group_size": 64,
14
- "bits": 8,
15
- "mode": "affine"
16
- },
17
  "text_config": {
18
  "attention_bias": false,
19
  "attention_dropout": 0.0,
 
4
  ],
5
  "image_token_id": 151655,
6
  "model_type": "qwen3_vl",
 
 
 
 
 
 
 
 
 
 
7
  "text_config": {
8
  "attention_bias": false,
9
  "attention_dropout": 0.0,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d2c05d94275e2e65176693ba1b69005f4f298b70518ddbecd3bdcd6d14bd665
3
- size 2642266883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6667b8ca5b934c4038ed98b5ccd3d77819f3d4f77f23ce3977548e397386a585
3
+ size 4255140149
model.safetensors.index.json CHANGED
@@ -1,710 +1,316 @@
1
  {
2
  "metadata": {
3
- "total_size": 2642141184
4
  },
5
  "weight_map": {
6
- "language_model.model.embed_tokens.biases": "model.safetensors",
7
- "language_model.model.embed_tokens.scales": "model.safetensors",
8
  "language_model.model.embed_tokens.weight": "model.safetensors",
9
  "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
10
- "language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
11
- "language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
12
  "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
13
- "language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
14
- "language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
15
  "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
16
- "language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
17
- "language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
18
  "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
19
  "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
20
  "language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
21
- "language_model.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
22
- "language_model.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
23
  "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
24
- "language_model.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
25
- "language_model.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
26
  "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
27
  "language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
28
- "language_model.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
29
- "language_model.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
30
  "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
31
- "language_model.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
32
- "language_model.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
33
  "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
34
  "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
35
- "language_model.model.layers.1.mlp.down_proj.biases": "model.safetensors",
36
- "language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
37
  "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
38
- "language_model.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
39
- "language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
40
  "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
41
- "language_model.model.layers.1.mlp.up_proj.biases": "model.safetensors",
42
- "language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
43
  "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
44
  "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
45
  "language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
46
- "language_model.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
47
- "language_model.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
48
  "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
49
- "language_model.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
50
- "language_model.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
51
  "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
52
  "language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
53
- "language_model.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
54
- "language_model.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
55
  "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
56
- "language_model.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
57
- "language_model.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
58
  "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
59
  "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
60
- "language_model.model.layers.10.mlp.down_proj.biases": "model.safetensors",
61
- "language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
62
  "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
63
- "language_model.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
64
- "language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
65
  "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
66
- "language_model.model.layers.10.mlp.up_proj.biases": "model.safetensors",
67
- "language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
68
  "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
69
  "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
70
  "language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
71
- "language_model.model.layers.10.self_attn.k_proj.biases": "model.safetensors",
72
- "language_model.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
73
  "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
74
- "language_model.model.layers.10.self_attn.o_proj.biases": "model.safetensors",
75
- "language_model.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
76
  "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
77
  "language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
78
- "language_model.model.layers.10.self_attn.q_proj.biases": "model.safetensors",
79
- "language_model.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
80
  "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
81
- "language_model.model.layers.10.self_attn.v_proj.biases": "model.safetensors",
82
- "language_model.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
83
  "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
84
  "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
85
- "language_model.model.layers.11.mlp.down_proj.biases": "model.safetensors",
86
- "language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
87
  "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
88
- "language_model.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
89
- "language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
90
  "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
91
- "language_model.model.layers.11.mlp.up_proj.biases": "model.safetensors",
92
- "language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
93
  "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
94
  "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
95
  "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
96
- "language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
97
- "language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
98
  "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
99
- "language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
100
- "language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
101
  "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
102
  "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
103
- "language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
104
- "language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
105
  "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
106
- "language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
107
- "language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
108
  "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
109
  "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
110
- "language_model.model.layers.12.mlp.down_proj.biases": "model.safetensors",
111
- "language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
112
  "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
113
- "language_model.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
114
- "language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
115
  "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
116
- "language_model.model.layers.12.mlp.up_proj.biases": "model.safetensors",
117
- "language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
118
  "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
119
  "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
120
  "language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
121
- "language_model.model.layers.12.self_attn.k_proj.biases": "model.safetensors",
122
- "language_model.model.layers.12.self_attn.k_proj.scales": "model.safetensors",
123
  "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
124
- "language_model.model.layers.12.self_attn.o_proj.biases": "model.safetensors",
125
- "language_model.model.layers.12.self_attn.o_proj.scales": "model.safetensors",
126
  "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
127
  "language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
128
- "language_model.model.layers.12.self_attn.q_proj.biases": "model.safetensors",
129
- "language_model.model.layers.12.self_attn.q_proj.scales": "model.safetensors",
130
  "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
131
- "language_model.model.layers.12.self_attn.v_proj.biases": "model.safetensors",
132
- "language_model.model.layers.12.self_attn.v_proj.scales": "model.safetensors",
133
  "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
134
  "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
135
- "language_model.model.layers.13.mlp.down_proj.biases": "model.safetensors",
136
- "language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
137
  "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
138
- "language_model.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
139
- "language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
140
  "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
141
- "language_model.model.layers.13.mlp.up_proj.biases": "model.safetensors",
142
- "language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
143
  "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
144
  "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
145
  "language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
146
- "language_model.model.layers.13.self_attn.k_proj.biases": "model.safetensors",
147
- "language_model.model.layers.13.self_attn.k_proj.scales": "model.safetensors",
148
  "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
149
- "language_model.model.layers.13.self_attn.o_proj.biases": "model.safetensors",
150
- "language_model.model.layers.13.self_attn.o_proj.scales": "model.safetensors",
151
  "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
152
  "language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
153
- "language_model.model.layers.13.self_attn.q_proj.biases": "model.safetensors",
154
- "language_model.model.layers.13.self_attn.q_proj.scales": "model.safetensors",
155
  "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
156
- "language_model.model.layers.13.self_attn.v_proj.biases": "model.safetensors",
157
- "language_model.model.layers.13.self_attn.v_proj.scales": "model.safetensors",
158
  "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
159
  "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
160
- "language_model.model.layers.14.mlp.down_proj.biases": "model.safetensors",
161
- "language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
162
  "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
163
- "language_model.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
164
- "language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
165
  "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
166
- "language_model.model.layers.14.mlp.up_proj.biases": "model.safetensors",
167
- "language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
168
  "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
169
  "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
170
  "language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
171
- "language_model.model.layers.14.self_attn.k_proj.biases": "model.safetensors",
172
- "language_model.model.layers.14.self_attn.k_proj.scales": "model.safetensors",
173
  "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
174
- "language_model.model.layers.14.self_attn.o_proj.biases": "model.safetensors",
175
- "language_model.model.layers.14.self_attn.o_proj.scales": "model.safetensors",
176
  "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
177
  "language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
178
- "language_model.model.layers.14.self_attn.q_proj.biases": "model.safetensors",
179
- "language_model.model.layers.14.self_attn.q_proj.scales": "model.safetensors",
180
  "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
181
- "language_model.model.layers.14.self_attn.v_proj.biases": "model.safetensors",
182
- "language_model.model.layers.14.self_attn.v_proj.scales": "model.safetensors",
183
  "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
184
  "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
185
- "language_model.model.layers.15.mlp.down_proj.biases": "model.safetensors",
186
- "language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
187
  "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
188
- "language_model.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
189
- "language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
190
  "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
191
- "language_model.model.layers.15.mlp.up_proj.biases": "model.safetensors",
192
- "language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
193
  "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
194
  "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
195
  "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
196
- "language_model.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
197
- "language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
198
  "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
199
- "language_model.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
200
- "language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
201
  "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
202
  "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
203
- "language_model.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
204
- "language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
205
  "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
206
- "language_model.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
207
- "language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
208
  "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
209
  "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
210
- "language_model.model.layers.16.mlp.down_proj.biases": "model.safetensors",
211
- "language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
212
  "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
213
- "language_model.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
214
- "language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
215
  "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
216
- "language_model.model.layers.16.mlp.up_proj.biases": "model.safetensors",
217
- "language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
218
  "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
219
  "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
220
  "language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
221
- "language_model.model.layers.16.self_attn.k_proj.biases": "model.safetensors",
222
- "language_model.model.layers.16.self_attn.k_proj.scales": "model.safetensors",
223
  "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
224
- "language_model.model.layers.16.self_attn.o_proj.biases": "model.safetensors",
225
- "language_model.model.layers.16.self_attn.o_proj.scales": "model.safetensors",
226
  "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
227
  "language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
228
- "language_model.model.layers.16.self_attn.q_proj.biases": "model.safetensors",
229
- "language_model.model.layers.16.self_attn.q_proj.scales": "model.safetensors",
230
  "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
231
- "language_model.model.layers.16.self_attn.v_proj.biases": "model.safetensors",
232
- "language_model.model.layers.16.self_attn.v_proj.scales": "model.safetensors",
233
  "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
234
  "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
235
- "language_model.model.layers.17.mlp.down_proj.biases": "model.safetensors",
236
- "language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
237
  "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
238
- "language_model.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
239
- "language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
240
  "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
241
- "language_model.model.layers.17.mlp.up_proj.biases": "model.safetensors",
242
- "language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
243
  "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
244
  "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
245
  "language_model.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
246
- "language_model.model.layers.17.self_attn.k_proj.biases": "model.safetensors",
247
- "language_model.model.layers.17.self_attn.k_proj.scales": "model.safetensors",
248
  "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
249
- "language_model.model.layers.17.self_attn.o_proj.biases": "model.safetensors",
250
- "language_model.model.layers.17.self_attn.o_proj.scales": "model.safetensors",
251
  "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
252
  "language_model.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
253
- "language_model.model.layers.17.self_attn.q_proj.biases": "model.safetensors",
254
- "language_model.model.layers.17.self_attn.q_proj.scales": "model.safetensors",
255
  "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
256
- "language_model.model.layers.17.self_attn.v_proj.biases": "model.safetensors",
257
- "language_model.model.layers.17.self_attn.v_proj.scales": "model.safetensors",
258
  "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
259
  "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
260
- "language_model.model.layers.18.mlp.down_proj.biases": "model.safetensors",
261
- "language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
262
  "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
263
- "language_model.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
264
- "language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
265
  "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
266
- "language_model.model.layers.18.mlp.up_proj.biases": "model.safetensors",
267
- "language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
268
  "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
269
  "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
270
  "language_model.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
271
- "language_model.model.layers.18.self_attn.k_proj.biases": "model.safetensors",
272
- "language_model.model.layers.18.self_attn.k_proj.scales": "model.safetensors",
273
  "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
274
- "language_model.model.layers.18.self_attn.o_proj.biases": "model.safetensors",
275
- "language_model.model.layers.18.self_attn.o_proj.scales": "model.safetensors",
276
  "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
277
  "language_model.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
278
- "language_model.model.layers.18.self_attn.q_proj.biases": "model.safetensors",
279
- "language_model.model.layers.18.self_attn.q_proj.scales": "model.safetensors",
280
  "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
281
- "language_model.model.layers.18.self_attn.v_proj.biases": "model.safetensors",
282
- "language_model.model.layers.18.self_attn.v_proj.scales": "model.safetensors",
283
  "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
284
  "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
285
- "language_model.model.layers.19.mlp.down_proj.biases": "model.safetensors",
286
- "language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
287
  "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
288
- "language_model.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
289
- "language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
290
  "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
291
- "language_model.model.layers.19.mlp.up_proj.biases": "model.safetensors",
292
- "language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
293
  "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
294
  "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
295
  "language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
296
- "language_model.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
297
- "language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
298
  "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
299
- "language_model.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
300
- "language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
301
  "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
302
  "language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
303
- "language_model.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
304
- "language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
305
  "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
306
- "language_model.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
307
- "language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
308
  "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
309
  "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
310
- "language_model.model.layers.2.mlp.down_proj.biases": "model.safetensors",
311
- "language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
312
  "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
313
- "language_model.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
314
- "language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
315
  "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
316
- "language_model.model.layers.2.mlp.up_proj.biases": "model.safetensors",
317
- "language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
318
  "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
319
  "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
320
  "language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
321
- "language_model.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
322
- "language_model.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
323
  "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
324
- "language_model.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
325
- "language_model.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
326
  "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
327
  "language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
328
- "language_model.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
329
- "language_model.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
330
  "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
331
- "language_model.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
332
- "language_model.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
333
  "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
334
  "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
335
- "language_model.model.layers.20.mlp.down_proj.biases": "model.safetensors",
336
- "language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
337
  "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
338
- "language_model.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
339
- "language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
340
  "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
341
- "language_model.model.layers.20.mlp.up_proj.biases": "model.safetensors",
342
- "language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
343
  "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
344
  "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
345
  "language_model.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
346
- "language_model.model.layers.20.self_attn.k_proj.biases": "model.safetensors",
347
- "language_model.model.layers.20.self_attn.k_proj.scales": "model.safetensors",
348
  "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
349
- "language_model.model.layers.20.self_attn.o_proj.biases": "model.safetensors",
350
- "language_model.model.layers.20.self_attn.o_proj.scales": "model.safetensors",
351
  "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
352
  "language_model.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
353
- "language_model.model.layers.20.self_attn.q_proj.biases": "model.safetensors",
354
- "language_model.model.layers.20.self_attn.q_proj.scales": "model.safetensors",
355
  "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
356
- "language_model.model.layers.20.self_attn.v_proj.biases": "model.safetensors",
357
- "language_model.model.layers.20.self_attn.v_proj.scales": "model.safetensors",
358
  "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
359
  "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
360
- "language_model.model.layers.21.mlp.down_proj.biases": "model.safetensors",
361
- "language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
362
  "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
363
- "language_model.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
364
- "language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
365
  "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
366
- "language_model.model.layers.21.mlp.up_proj.biases": "model.safetensors",
367
- "language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
368
  "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
369
  "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
370
  "language_model.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
371
- "language_model.model.layers.21.self_attn.k_proj.biases": "model.safetensors",
372
- "language_model.model.layers.21.self_attn.k_proj.scales": "model.safetensors",
373
  "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
374
- "language_model.model.layers.21.self_attn.o_proj.biases": "model.safetensors",
375
- "language_model.model.layers.21.self_attn.o_proj.scales": "model.safetensors",
376
  "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
377
  "language_model.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
378
- "language_model.model.layers.21.self_attn.q_proj.biases": "model.safetensors",
379
- "language_model.model.layers.21.self_attn.q_proj.scales": "model.safetensors",
380
  "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
381
- "language_model.model.layers.21.self_attn.v_proj.biases": "model.safetensors",
382
- "language_model.model.layers.21.self_attn.v_proj.scales": "model.safetensors",
383
  "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
384
  "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
385
- "language_model.model.layers.22.mlp.down_proj.biases": "model.safetensors",
386
- "language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
387
  "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
388
- "language_model.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
389
- "language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
390
  "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
391
- "language_model.model.layers.22.mlp.up_proj.biases": "model.safetensors",
392
- "language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
393
  "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
394
  "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
395
  "language_model.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
396
- "language_model.model.layers.22.self_attn.k_proj.biases": "model.safetensors",
397
- "language_model.model.layers.22.self_attn.k_proj.scales": "model.safetensors",
398
  "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
399
- "language_model.model.layers.22.self_attn.o_proj.biases": "model.safetensors",
400
- "language_model.model.layers.22.self_attn.o_proj.scales": "model.safetensors",
401
  "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
402
  "language_model.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
403
- "language_model.model.layers.22.self_attn.q_proj.biases": "model.safetensors",
404
- "language_model.model.layers.22.self_attn.q_proj.scales": "model.safetensors",
405
  "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
406
- "language_model.model.layers.22.self_attn.v_proj.biases": "model.safetensors",
407
- "language_model.model.layers.22.self_attn.v_proj.scales": "model.safetensors",
408
  "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
409
  "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
410
- "language_model.model.layers.23.mlp.down_proj.biases": "model.safetensors",
411
- "language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
412
  "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
413
- "language_model.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
414
- "language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
415
  "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
416
- "language_model.model.layers.23.mlp.up_proj.biases": "model.safetensors",
417
- "language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
418
  "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
419
  "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
420
  "language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
421
- "language_model.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
422
- "language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
423
  "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
424
- "language_model.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
425
- "language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
426
  "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
427
  "language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
428
- "language_model.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
429
- "language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
430
  "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
431
- "language_model.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
432
- "language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
433
  "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
434
  "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
435
- "language_model.model.layers.24.mlp.down_proj.biases": "model.safetensors",
436
- "language_model.model.layers.24.mlp.down_proj.scales": "model.safetensors",
437
  "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
438
- "language_model.model.layers.24.mlp.gate_proj.biases": "model.safetensors",
439
- "language_model.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
440
  "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
441
- "language_model.model.layers.24.mlp.up_proj.biases": "model.safetensors",
442
- "language_model.model.layers.24.mlp.up_proj.scales": "model.safetensors",
443
  "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
444
  "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
445
  "language_model.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
446
- "language_model.model.layers.24.self_attn.k_proj.biases": "model.safetensors",
447
- "language_model.model.layers.24.self_attn.k_proj.scales": "model.safetensors",
448
  "language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
449
- "language_model.model.layers.24.self_attn.o_proj.biases": "model.safetensors",
450
- "language_model.model.layers.24.self_attn.o_proj.scales": "model.safetensors",
451
  "language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
452
  "language_model.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
453
- "language_model.model.layers.24.self_attn.q_proj.biases": "model.safetensors",
454
- "language_model.model.layers.24.self_attn.q_proj.scales": "model.safetensors",
455
  "language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
456
- "language_model.model.layers.24.self_attn.v_proj.biases": "model.safetensors",
457
- "language_model.model.layers.24.self_attn.v_proj.scales": "model.safetensors",
458
  "language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
459
  "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
460
- "language_model.model.layers.25.mlp.down_proj.biases": "model.safetensors",
461
- "language_model.model.layers.25.mlp.down_proj.scales": "model.safetensors",
462
  "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
463
- "language_model.model.layers.25.mlp.gate_proj.biases": "model.safetensors",
464
- "language_model.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
465
  "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
466
- "language_model.model.layers.25.mlp.up_proj.biases": "model.safetensors",
467
- "language_model.model.layers.25.mlp.up_proj.scales": "model.safetensors",
468
  "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
469
  "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
470
  "language_model.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
471
- "language_model.model.layers.25.self_attn.k_proj.biases": "model.safetensors",
472
- "language_model.model.layers.25.self_attn.k_proj.scales": "model.safetensors",
473
  "language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
474
- "language_model.model.layers.25.self_attn.o_proj.biases": "model.safetensors",
475
- "language_model.model.layers.25.self_attn.o_proj.scales": "model.safetensors",
476
  "language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
477
  "language_model.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
478
- "language_model.model.layers.25.self_attn.q_proj.biases": "model.safetensors",
479
- "language_model.model.layers.25.self_attn.q_proj.scales": "model.safetensors",
480
  "language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
481
- "language_model.model.layers.25.self_attn.v_proj.biases": "model.safetensors",
482
- "language_model.model.layers.25.self_attn.v_proj.scales": "model.safetensors",
483
  "language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
484
  "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
485
- "language_model.model.layers.26.mlp.down_proj.biases": "model.safetensors",
486
- "language_model.model.layers.26.mlp.down_proj.scales": "model.safetensors",
487
  "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
488
- "language_model.model.layers.26.mlp.gate_proj.biases": "model.safetensors",
489
- "language_model.model.layers.26.mlp.gate_proj.scales": "model.safetensors",
490
  "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
491
- "language_model.model.layers.26.mlp.up_proj.biases": "model.safetensors",
492
- "language_model.model.layers.26.mlp.up_proj.scales": "model.safetensors",
493
  "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
494
  "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
495
  "language_model.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
496
- "language_model.model.layers.26.self_attn.k_proj.biases": "model.safetensors",
497
- "language_model.model.layers.26.self_attn.k_proj.scales": "model.safetensors",
498
  "language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
499
- "language_model.model.layers.26.self_attn.o_proj.biases": "model.safetensors",
500
- "language_model.model.layers.26.self_attn.o_proj.scales": "model.safetensors",
501
  "language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
502
  "language_model.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
503
- "language_model.model.layers.26.self_attn.q_proj.biases": "model.safetensors",
504
- "language_model.model.layers.26.self_attn.q_proj.scales": "model.safetensors",
505
  "language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
506
- "language_model.model.layers.26.self_attn.v_proj.biases": "model.safetensors",
507
- "language_model.model.layers.26.self_attn.v_proj.scales": "model.safetensors",
508
  "language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
509
  "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
510
- "language_model.model.layers.27.mlp.down_proj.biases": "model.safetensors",
511
- "language_model.model.layers.27.mlp.down_proj.scales": "model.safetensors",
512
  "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
513
- "language_model.model.layers.27.mlp.gate_proj.biases": "model.safetensors",
514
- "language_model.model.layers.27.mlp.gate_proj.scales": "model.safetensors",
515
  "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
516
- "language_model.model.layers.27.mlp.up_proj.biases": "model.safetensors",
517
- "language_model.model.layers.27.mlp.up_proj.scales": "model.safetensors",
518
  "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
519
  "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
520
  "language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
521
- "language_model.model.layers.27.self_attn.k_proj.biases": "model.safetensors",
522
- "language_model.model.layers.27.self_attn.k_proj.scales": "model.safetensors",
523
  "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
524
- "language_model.model.layers.27.self_attn.o_proj.biases": "model.safetensors",
525
- "language_model.model.layers.27.self_attn.o_proj.scales": "model.safetensors",
526
  "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
527
  "language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
528
- "language_model.model.layers.27.self_attn.q_proj.biases": "model.safetensors",
529
- "language_model.model.layers.27.self_attn.q_proj.scales": "model.safetensors",
530
  "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
531
- "language_model.model.layers.27.self_attn.v_proj.biases": "model.safetensors",
532
- "language_model.model.layers.27.self_attn.v_proj.scales": "model.safetensors",
533
  "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
534
  "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
535
- "language_model.model.layers.3.mlp.down_proj.biases": "model.safetensors",
536
- "language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
537
  "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
538
- "language_model.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
539
- "language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
540
  "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
541
- "language_model.model.layers.3.mlp.up_proj.biases": "model.safetensors",
542
- "language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
543
  "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
544
  "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
545
  "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
546
- "language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
547
- "language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
548
  "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
549
- "language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
550
- "language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
551
  "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
552
  "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
553
- "language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
554
- "language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
555
  "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
556
- "language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
557
- "language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
558
  "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
559
  "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
560
- "language_model.model.layers.4.mlp.down_proj.biases": "model.safetensors",
561
- "language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
562
  "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
563
- "language_model.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
564
- "language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
565
  "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
566
- "language_model.model.layers.4.mlp.up_proj.biases": "model.safetensors",
567
- "language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
568
  "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
569
  "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
570
  "language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
571
- "language_model.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
572
- "language_model.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
573
  "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
574
- "language_model.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
575
- "language_model.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
576
  "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
577
  "language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
578
- "language_model.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
579
- "language_model.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
580
  "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
581
- "language_model.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
582
- "language_model.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
583
  "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
584
  "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
585
- "language_model.model.layers.5.mlp.down_proj.biases": "model.safetensors",
586
- "language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
587
  "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
588
- "language_model.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
589
- "language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
590
  "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
591
- "language_model.model.layers.5.mlp.up_proj.biases": "model.safetensors",
592
- "language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
593
  "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
594
  "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
595
  "language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
596
- "language_model.model.layers.5.self_attn.k_proj.biases": "model.safetensors",
597
- "language_model.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
598
  "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
599
- "language_model.model.layers.5.self_attn.o_proj.biases": "model.safetensors",
600
- "language_model.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
601
  "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
602
  "language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
603
- "language_model.model.layers.5.self_attn.q_proj.biases": "model.safetensors",
604
- "language_model.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
605
  "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
606
- "language_model.model.layers.5.self_attn.v_proj.biases": "model.safetensors",
607
- "language_model.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
608
  "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
609
  "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
610
- "language_model.model.layers.6.mlp.down_proj.biases": "model.safetensors",
611
- "language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
612
  "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
613
- "language_model.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
614
- "language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
615
  "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
616
- "language_model.model.layers.6.mlp.up_proj.biases": "model.safetensors",
617
- "language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
618
  "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
619
  "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
620
  "language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
621
- "language_model.model.layers.6.self_attn.k_proj.biases": "model.safetensors",
622
- "language_model.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
623
  "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
624
- "language_model.model.layers.6.self_attn.o_proj.biases": "model.safetensors",
625
- "language_model.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
626
  "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
627
  "language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
628
- "language_model.model.layers.6.self_attn.q_proj.biases": "model.safetensors",
629
- "language_model.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
630
  "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
631
- "language_model.model.layers.6.self_attn.v_proj.biases": "model.safetensors",
632
- "language_model.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
633
  "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
634
  "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
635
- "language_model.model.layers.7.mlp.down_proj.biases": "model.safetensors",
636
- "language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
637
  "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
638
- "language_model.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
639
- "language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
640
  "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
641
- "language_model.model.layers.7.mlp.up_proj.biases": "model.safetensors",
642
- "language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
643
  "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
644
  "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
645
  "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
646
- "language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
647
- "language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
648
  "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
649
- "language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
650
- "language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
651
  "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
652
  "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
653
- "language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
654
- "language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
655
  "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
656
- "language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
657
- "language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
658
  "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
659
  "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
660
- "language_model.model.layers.8.mlp.down_proj.biases": "model.safetensors",
661
- "language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
662
  "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
663
- "language_model.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
664
- "language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
665
  "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
666
- "language_model.model.layers.8.mlp.up_proj.biases": "model.safetensors",
667
- "language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
668
  "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
669
  "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
670
  "language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
671
- "language_model.model.layers.8.self_attn.k_proj.biases": "model.safetensors",
672
- "language_model.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
673
  "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
674
- "language_model.model.layers.8.self_attn.o_proj.biases": "model.safetensors",
675
- "language_model.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
676
  "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
677
  "language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
678
- "language_model.model.layers.8.self_attn.q_proj.biases": "model.safetensors",
679
- "language_model.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
680
  "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
681
- "language_model.model.layers.8.self_attn.v_proj.biases": "model.safetensors",
682
- "language_model.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
683
  "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
684
  "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
685
- "language_model.model.layers.9.mlp.down_proj.biases": "model.safetensors",
686
- "language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
687
  "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
688
- "language_model.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
689
- "language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
690
  "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
691
- "language_model.model.layers.9.mlp.up_proj.biases": "model.safetensors",
692
- "language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
693
  "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
694
  "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
695
  "language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
696
- "language_model.model.layers.9.self_attn.k_proj.biases": "model.safetensors",
697
- "language_model.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
698
  "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
699
- "language_model.model.layers.9.self_attn.o_proj.biases": "model.safetensors",
700
- "language_model.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
701
  "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
702
  "language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
703
- "language_model.model.layers.9.self_attn.q_proj.biases": "model.safetensors",
704
- "language_model.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
705
  "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
706
- "language_model.model.layers.9.self_attn.v_proj.biases": "model.safetensors",
707
- "language_model.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
708
  "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
709
  "language_model.model.norm.weight": "model.safetensors",
710
  "vision_tower.blocks.0.attn.proj.bias": "model.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 4255064064
4
  },
5
  "weight_map": {
 
 
6
  "language_model.model.embed_tokens.weight": "model.safetensors",
7
  "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
 
 
8
  "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
 
 
9
  "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
 
 
10
  "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
  "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
  "language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
 
 
13
  "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
 
 
14
  "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
15
  "language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
 
 
16
  "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
 
 
17
  "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
18
  "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
 
 
19
  "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
 
 
20
  "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
 
 
21
  "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
22
  "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
23
  "language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
 
 
24
  "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
 
 
25
  "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
26
  "language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
 
 
27
  "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
 
 
28
  "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
29
  "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
 
 
30
  "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
 
 
31
  "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
 
 
32
  "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
33
  "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
34
  "language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
 
 
35
  "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
 
 
36
  "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
37
  "language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
 
 
38
  "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
 
 
39
  "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
40
  "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
 
 
41
  "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
 
 
42
  "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
 
 
43
  "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
44
  "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
45
  "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
 
 
46
  "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
 
 
47
  "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
48
  "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
 
 
49
  "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
 
 
50
  "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
51
  "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
 
 
52
  "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
 
 
53
  "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
 
 
54
  "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
55
  "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
56
  "language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
 
 
57
  "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
 
 
58
  "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
59
  "language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
 
 
60
  "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
 
 
61
  "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
62
  "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
 
 
63
  "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
 
 
64
  "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
 
 
65
  "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
66
  "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
67
  "language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
 
 
68
  "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
 
 
69
  "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
70
  "language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
 
 
71
  "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
 
 
72
  "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
73
  "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
 
 
74
  "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
 
 
75
  "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
 
 
76
  "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
77
  "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
78
  "language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
 
 
79
  "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
 
 
80
  "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
81
  "language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
 
 
82
  "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
 
 
83
  "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
84
  "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
 
 
85
  "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
 
 
86
  "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
 
 
87
  "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
88
  "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
89
  "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
 
 
90
  "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
 
 
91
  "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
92
  "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
 
 
93
  "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
 
 
94
  "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
95
  "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
 
 
96
  "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
 
 
97
  "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
 
 
98
  "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
99
  "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
100
  "language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
 
 
101
  "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
 
 
102
  "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
103
  "language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
 
 
104
  "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
 
 
105
  "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
106
  "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
 
 
107
  "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
 
 
108
  "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
 
 
109
  "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
110
  "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
111
  "language_model.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
 
 
112
  "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
 
 
113
  "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
114
  "language_model.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
 
 
115
  "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
 
 
116
  "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
117
  "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
 
 
118
  "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
 
 
119
  "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
 
 
120
  "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
121
  "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
122
  "language_model.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
 
 
123
  "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
 
 
124
  "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
125
  "language_model.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
 
 
126
  "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
 
 
127
  "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
128
  "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
 
 
129
  "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
 
 
130
  "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
 
 
131
  "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
132
  "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
133
  "language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
 
 
134
  "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
 
 
135
  "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
136
  "language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
 
 
137
  "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
 
 
138
  "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
139
  "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
 
 
140
  "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
 
 
141
  "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
 
 
142
  "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
143
  "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
144
  "language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
 
 
145
  "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
 
 
146
  "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
147
  "language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
 
 
148
  "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
 
 
149
  "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
150
  "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
 
 
151
  "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
 
 
152
  "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
 
 
153
  "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
154
  "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
155
  "language_model.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
 
 
156
  "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
 
 
157
  "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
158
  "language_model.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
 
 
159
  "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
 
 
160
  "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
161
  "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
 
 
162
  "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
 
 
163
  "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
 
 
164
  "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
165
  "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
166
  "language_model.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
 
 
167
  "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
 
 
168
  "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
169
  "language_model.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
 
 
170
  "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
 
 
171
  "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
172
  "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
 
 
173
  "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
 
 
174
  "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
 
 
175
  "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
176
  "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
177
  "language_model.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
 
 
178
  "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
 
 
179
  "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
180
  "language_model.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
 
 
181
  "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
 
 
182
  "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
183
  "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
 
 
184
  "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
 
 
185
  "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
 
 
186
  "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
187
  "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
188
  "language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
 
 
189
  "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
 
 
190
  "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
191
  "language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
 
 
192
  "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
 
 
193
  "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
194
  "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
 
 
195
  "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
 
 
196
  "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
 
 
197
  "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
198
  "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
199
  "language_model.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
 
 
200
  "language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
 
 
201
  "language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
202
  "language_model.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
 
 
203
  "language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
 
 
204
  "language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
205
  "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
 
 
206
  "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
 
 
207
  "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
 
 
208
  "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
209
  "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
210
  "language_model.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
 
 
211
  "language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
 
 
212
  "language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
213
  "language_model.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
 
 
214
  "language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
 
 
215
  "language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
216
  "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
 
 
217
  "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
 
 
218
  "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
 
 
219
  "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
220
  "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
221
  "language_model.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
 
 
222
  "language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
 
 
223
  "language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
224
  "language_model.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
 
 
225
  "language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
 
 
226
  "language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
227
  "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
 
 
228
  "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
 
 
229
  "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
 
 
230
  "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
231
  "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
232
  "language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
 
 
233
  "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
 
 
234
  "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
235
  "language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
 
 
236
  "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
 
 
237
  "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
238
  "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
 
 
239
  "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
 
 
240
  "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
 
 
241
  "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
242
  "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
243
  "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
 
 
244
  "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
 
 
245
  "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
246
  "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
 
 
247
  "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
 
 
248
  "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
249
  "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
 
 
250
  "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
 
 
251
  "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
 
 
252
  "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
253
  "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
254
  "language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
 
 
255
  "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
 
 
256
  "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
257
  "language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
 
 
258
  "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
 
 
259
  "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
260
  "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
 
 
261
  "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
 
 
262
  "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
 
 
263
  "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
264
  "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
265
  "language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
 
 
266
  "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
 
 
267
  "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
268
  "language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
 
 
269
  "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
 
 
270
  "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
271
  "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
 
 
272
  "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
 
 
273
  "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
 
 
274
  "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
275
  "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
276
  "language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
 
 
277
  "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
 
 
278
  "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
279
  "language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
 
 
280
  "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
 
 
281
  "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
282
  "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
 
 
283
  "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
 
 
284
  "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
 
 
285
  "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
286
  "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
287
  "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
 
 
288
  "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
 
 
289
  "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
290
  "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
 
 
291
  "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
 
 
292
  "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
293
  "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
 
 
294
  "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
 
 
295
  "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
 
 
296
  "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
297
  "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
298
  "language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
 
 
299
  "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
 
 
300
  "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
301
  "language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
 
 
302
  "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
 
 
303
  "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
304
  "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
 
 
305
  "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
 
 
306
  "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
 
 
307
  "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
308
  "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
309
  "language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
 
 
310
  "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
 
 
311
  "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
312
  "language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
 
 
313
  "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
 
 
314
  "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
315
  "language_model.model.norm.weight": "model.safetensors",
316
  "vision_tower.blocks.0.attn.proj.bias": "model.safetensors",