juberti commited on
Commit
17ec4d3
1 Parent(s): 1832388

Upload model

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/Users/juberti/src/github/ultravox/artifacts/model-llama3_whisper_s__30K_cont_boolq__cont_soda:v1",
3
  "architectures": [
4
  "UltravoxModel"
5
  ],
@@ -172,7 +172,7 @@
172
  "vocab_size": 128256
173
  },
174
  "text_model_id": null,
175
- "torch_dtype": "float32",
176
  "transformers_version": "4.41.2",
177
  "vocab_size": 128256
178
  }
 
1
  {
2
+ "_name_or_path": "/Users/juberti/src/github/ultravox/artifacts/model-llama3_whisper_s__30K__cont_gs_ai_bq_soda:v0",
3
  "architectures": [
4
  "UltravoxModel"
5
  ],
 
172
  "vocab_size": 128256
173
  },
174
  "text_model_id": null,
175
+ "torch_dtype": "bfloat16",
176
  "transformers_version": "4.41.2",
177
  "vocab_size": 128256
178
  }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86e285d2c33776e79709cc4fff91219181e8d497894fbc0e32a7e6c3b79eaad
3
+ size 4926372408
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0801ec8c1fc3d0948218d28056e800546e50249db02d6fbe292c93baa1fb7aa
3
+ size 4999820920
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bac3e82175137d06b8e2af6ce8bdfe8f5ab19983a8625e5d33db935e63491d
3
+ size 4915917680
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e617f67bdbc5b0abaf568624a50cc389064b5483b783cfa796f952230552b9
3
+ size 1285579528
model.safetensors.index.json CHANGED
@@ -1,302 +1,302 @@
1
  {
2
  "metadata": {
3
- "total_size": 32255303680
4
  },
5
  "weight_map": {
6
- "language_model.lm_head.weight": "model-00007-of-00007.safetensors",
7
- "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
- "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
- "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
- "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
- "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
- "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
- "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
- "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
- "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
- "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
- "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
- "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
- "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
- "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
- "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
- "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
- "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
- "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
- "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
- "language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
27
- "language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
28
- "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
29
- "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
30
- "language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
31
- "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
32
- "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
33
- "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
34
- "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
35
- "language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
36
- "language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
37
- "language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
38
- "language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
39
- "language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
40
- "language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
41
- "language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
42
- "language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
- "language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
44
- "language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
45
- "language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
46
- "language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
47
- "language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
48
- "language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
49
- "language_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
50
- "language_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
51
- "language_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
52
- "language_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
53
- "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
54
- "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
55
- "language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
56
- "language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
57
- "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
58
- "language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
59
- "language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
60
- "language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
61
- "language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
62
- "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
63
- "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
64
- "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
65
- "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
66
- "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
67
- "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
68
- "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
69
- "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
70
- "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
71
- "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
72
- "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
73
- "language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
74
- "language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
75
- "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
76
- "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
77
- "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
78
- "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
79
- "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
80
- "language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
81
- "language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
82
- "language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
83
- "language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
84
- "language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
85
- "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
86
- "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
87
- "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
88
- "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
89
- "language_model.model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
90
- "language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
91
- "language_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
92
- "language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
93
- "language_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
94
- "language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
95
- "language_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
96
- "language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
97
- "language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
98
- "language_model.model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
99
- "language_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
100
- "language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
101
- "language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
102
- "language_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
103
- "language_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
104
- "language_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
105
- "language_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
106
- "language_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
107
- "language_model.model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
108
- "language_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
109
- "language_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
110
- "language_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
111
- "language_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
112
- "language_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
113
- "language_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
114
- "language_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
- "language_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
116
- "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
- "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
- "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
- "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
- "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
- "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
- "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
- "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
- "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
- "language_model.model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
126
- "language_model.model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
127
- "language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
128
- "language_model.model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
129
- "language_model.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
130
- "language_model.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
131
- "language_model.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
132
- "language_model.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
133
- "language_model.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
134
- "language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
135
- "language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
136
- "language_model.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
137
- "language_model.model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
138
- "language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
139
- "language_model.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
140
- "language_model.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
141
- "language_model.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
142
- "language_model.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
143
- "language_model.model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
144
- "language_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
145
- "language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
146
- "language_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
147
- "language_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
148
- "language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
149
- "language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
150
- "language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
- "language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
152
- "language_model.model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
153
- "language_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
154
- "language_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
155
- "language_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
156
- "language_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
157
- "language_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
158
- "language_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
159
- "language_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
160
- "language_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
161
- "language_model.model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
162
- "language_model.model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
163
- "language_model.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
164
- "language_model.model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
165
- "language_model.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
166
- "language_model.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
167
- "language_model.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
168
- "language_model.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
169
- "language_model.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
170
- "language_model.model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
171
- "language_model.model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
172
- "language_model.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
173
- "language_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
174
- "language_model.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
175
- "language_model.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
176
- "language_model.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
177
- "language_model.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
178
- "language_model.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
179
- "language_model.model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
180
- "language_model.model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
181
- "language_model.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
182
- "language_model.model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
183
- "language_model.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
184
- "language_model.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
185
- "language_model.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
186
- "language_model.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
187
- "language_model.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
188
- "language_model.model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
189
- "language_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
190
- "language_model.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
191
- "language_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
192
- "language_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
193
- "language_model.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
194
- "language_model.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
195
- "language_model.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
196
- "language_model.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
197
- "language_model.model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
198
- "language_model.model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
199
- "language_model.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
200
- "language_model.model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
201
- "language_model.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
202
- "language_model.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
203
- "language_model.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
204
- "language_model.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
205
- "language_model.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
206
- "language_model.model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
207
- "language_model.model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
208
- "language_model.model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
209
- "language_model.model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
210
- "language_model.model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
211
- "language_model.model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
212
- "language_model.model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
213
- "language_model.model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
214
- "language_model.model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
215
- "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
216
- "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
217
- "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
218
- "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
219
- "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
220
- "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
- "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
222
- "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
- "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
- "language_model.model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
225
- "language_model.model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
226
- "language_model.model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
227
- "language_model.model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
228
- "language_model.model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
229
- "language_model.model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
230
- "language_model.model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
231
- "language_model.model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
232
- "language_model.model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
233
- "language_model.model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
234
- "language_model.model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
235
- "language_model.model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
236
- "language_model.model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
237
- "language_model.model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
238
- "language_model.model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
239
- "language_model.model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
240
- "language_model.model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
241
- "language_model.model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
242
- "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
243
- "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
244
- "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
245
- "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
246
- "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
247
- "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
248
- "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
249
- "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
250
- "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
251
- "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
252
- "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
253
- "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
254
- "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
255
- "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
256
- "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
257
- "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
258
- "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
259
- "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
260
- "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
261
- "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
262
- "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
263
- "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
264
- "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
265
- "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
266
- "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
267
- "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
268
- "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
269
- "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
270
- "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
271
- "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
272
- "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
273
- "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
274
- "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
275
- "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
276
- "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
277
- "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
278
- "language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
279
- "language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
280
- "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
281
- "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
282
- "language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
283
- "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
284
- "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
285
- "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
286
- "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
287
- "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
288
- "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
289
- "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
290
- "language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
291
- "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
292
- "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
293
- "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
294
- "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
295
- "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
296
- "language_model.model.norm.weight": "model-00007-of-00007.safetensors",
297
- "multi_modal_projector.linear_1.weight": "model-00001-of-00007.safetensors",
298
- "multi_modal_projector.linear_2.weight": "model-00001-of-00007.safetensors",
299
- "multi_modal_projector.ln_post.weight": "model-00001-of-00007.safetensors",
300
- "multi_modal_projector.ln_pre.weight": "model-00001-of-00007.safetensors"
301
  }
302
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 16127651840
4
  },
5
  "weight_map": {
6
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
237
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
279
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
280
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
283
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
297
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
298
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
299
+ "multi_modal_projector.ln_post.weight": "model-00001-of-00004.safetensors",
300
+ "multi_modal_projector.ln_pre.weight": "model-00001-of-00004.safetensors"
301
  }
302
  }