Hugging Face's logo

nvidia
/
Nemotron-Labs-Diffusion-8B-Base

Text Generation
Transformers
Safetensors
PyTorch
nemotron_labs_diffusion
feature-extraction
nvidia
conversational
custom_code
Model card Files
xet
 Community
1
YongganFu commited on
Commit
b4fbb98
·
verified ·
1 Parent(s): 987c652

Delete model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +0 -317
model.safetensors.index.json DELETED
@@ -1,317 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 8489553920,
4
- "total_size": 16979107840
5
- },
6
- "weight_map": {
7
- "diffusion_head.weight": "model-00004-of-00004.safetensors",
8
- "encoder.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "encoder.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "encoder.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "encoder.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "encoder.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
- "encoder.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
- "encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
- "encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
- "encoder.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
- "encoder.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
- "encoder.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
- "encoder.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
- "encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
- "encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
- "encoder.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
- "encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
- "encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
- "encoder.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
- "encoder.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
- "encoder.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
- "encoder.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
- "encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
- "encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
- "encoder.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
- "encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
- "encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
- "encoder.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
- "encoder.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
- "encoder.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
- "encoder.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
- "encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
- "encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
- "encoder.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
- "encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
- "encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
- "encoder.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
- "encoder.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
- "encoder.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
- "encoder.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
- "encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
- "encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
- "encoder.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
- "encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
- "encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
- "encoder.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
- "encoder.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
- "encoder.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
- "encoder.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
- "encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
- "encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
- "encoder.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
- "encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
- "encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
- "encoder.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
- "encoder.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
- "encoder.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
- "encoder.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
- "encoder.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
- "encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
- "encoder.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
- "encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
- "encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
- "encoder.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
- "encoder.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
- "encoder.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
- "encoder.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
- "encoder.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
- "encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
- "encoder.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
- "encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
- "encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
- "encoder.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
- "encoder.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
- "encoder.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
- "encoder.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
- "encoder.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
- "encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
- "encoder.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
- "encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
- "encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
- "encoder.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
- "encoder.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
- "encoder.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
- "encoder.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
- "encoder.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
- "encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
- "encoder.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
- "encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
- "encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
- "encoder.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
- "encoder.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
- "encoder.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
- "encoder.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
- "encoder.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
- "encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
- "encoder.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
- "encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
- "encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
- "encoder.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
- "encoder.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
- "encoder.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
- "encoder.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
- "encoder.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
- "encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
- "encoder.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
- "encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
- "encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
- "encoder.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
- "encoder.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
- "encoder.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
- "encoder.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
- "encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
- "encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
- "encoder.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
- "encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
- "encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
- "encoder.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
- "encoder.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
- "encoder.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
- "encoder.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
- "encoder.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
- "encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
- "encoder.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
- "encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
- "encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
- "encoder.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
- "encoder.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
- "encoder.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
- "encoder.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
- "encoder.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
- "encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
- "encoder.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
- "encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
- "encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
- "encoder.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
- "encoder.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
- "encoder.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
- "encoder.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
- "encoder.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
- "encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
- "encoder.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
- "encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
- "encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
- "encoder.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
- "encoder.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
- "encoder.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
- "encoder.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
- "encoder.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
- "encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
- "encoder.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
- "encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
- "encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
- "encoder.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
- "encoder.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
- "encoder.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
- "encoder.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
- "encoder.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
- "encoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
- "encoder.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
- "encoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
- "encoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
- "encoder.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
- "encoder.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
- "encoder.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
- "encoder.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
- "encoder.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
- "encoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
- "encoder.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
- "encoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
- "encoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
- "encoder.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
- "encoder.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
- "encoder.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
- "encoder.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
- "encoder.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
- "encoder.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
- "encoder.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
- "encoder.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
- "encoder.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
- "encoder.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "encoder.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
- "encoder.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
- "encoder.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
- "encoder.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
- "encoder.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
- "encoder.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
- "encoder.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
- "encoder.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
- "encoder.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
- "encoder.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
- "encoder.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
- "encoder.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
- "encoder.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
- "encoder.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
- "encoder.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
- "encoder.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
- "encoder.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
- "encoder.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
- "encoder.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
- "encoder.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
- "encoder.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
- "encoder.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
- "encoder.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
- "encoder.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
- "encoder.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
- "encoder.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
- "encoder.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
- "encoder.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
- "encoder.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
- "encoder.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
- "encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
- "encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
- "encoder.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
- "encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
- "encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
- "encoder.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
- "encoder.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
- "encoder.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
- "encoder.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
- "encoder.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "encoder.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
- "encoder.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
- "encoder.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
- "encoder.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
- "encoder.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
- "encoder.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
- "encoder.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
- "encoder.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
- "encoder.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
- "encoder.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
- "encoder.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
- "encoder.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
- "encoder.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
- "encoder.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
244
- "encoder.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
245
- "encoder.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
246
- "encoder.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
247
- "encoder.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
248
- "encoder.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
249
- "encoder.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
250
- "encoder.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
251
- "encoder.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
252
- "encoder.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
253
- "encoder.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
254
- "encoder.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
255
- "encoder.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
256
- "encoder.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
257
- "encoder.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
258
- "encoder.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
259
- "encoder.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
260
- "encoder.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
- "encoder.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
- "encoder.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
- "encoder.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
- "encoder.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
- "encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
- "encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
- "encoder.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
- "encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
- "encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
- "encoder.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
- "encoder.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
- "encoder.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
- "encoder.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
- "encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
- "encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
- "encoder.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
- "encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
- "encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
- "encoder.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
- "encoder.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
- "encoder.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
- "encoder.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
- "encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
- "encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
- "encoder.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
- "encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
- "encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
- "encoder.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
289
- "encoder.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
290
- "encoder.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
291
- "encoder.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
292
- "encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
293
- "encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
294
- "encoder.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
295
- "encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
296
- "encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
- "encoder.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
- "encoder.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
- "encoder.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
- "encoder.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
- "encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
- "encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
- "encoder.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
- "encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
305
- "encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
306
- "encoder.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
307
- "encoder.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
308
- "encoder.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
309
- "encoder.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
310
- "encoder.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
311
- "encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
312
- "encoder.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
313
- "encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
314
- "encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
315
- "encoder.norm.weight": "model-00004-of-00004.safetensors"
316
- }
317
- }