Hugging Face's logo

Santosh-Gupta
/
EncephalitisGPT

Text Generation
Transformers
Safetensors
biogpt
Inference Endpoints
Model card Files Community
Santosh-Gupta commited on
Commit
7462fd2
•
1 Parent(s): e4b4634

Upload model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +779 -0
model.safetensors.index.json ADDED
@@ -0,0 +1,779 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6284755200
4
+ },
5
+ "weight_map": {
6
+ "biogpt.embed_positions.weight": "model-00001-of-00002.safetensors",
7
+ "biogpt.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "biogpt.layer_norm.bias": "model-00002-of-00002.safetensors",
9
+ "biogpt.layer_norm.weight": "model-00002-of-00002.safetensors",
10
+ "biogpt.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
11
+ "biogpt.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
12
+ "biogpt.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
13
+ "biogpt.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
14
+ "biogpt.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
15
+ "biogpt.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
16
+ "biogpt.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
17
+ "biogpt.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
18
+ "biogpt.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
19
+ "biogpt.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
20
+ "biogpt.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
21
+ "biogpt.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
22
+ "biogpt.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
23
+ "biogpt.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
24
+ "biogpt.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
25
+ "biogpt.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
26
+ "biogpt.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
27
+ "biogpt.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
28
+ "biogpt.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
29
+ "biogpt.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
30
+ "biogpt.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
31
+ "biogpt.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
32
+ "biogpt.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
33
+ "biogpt.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
34
+ "biogpt.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
35
+ "biogpt.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
36
+ "biogpt.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
37
+ "biogpt.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
38
+ "biogpt.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
39
+ "biogpt.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
40
+ "biogpt.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
41
+ "biogpt.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
42
+ "biogpt.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
43
+ "biogpt.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
44
+ "biogpt.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
45
+ "biogpt.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
46
+ "biogpt.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
47
+ "biogpt.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
48
+ "biogpt.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "biogpt.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "biogpt.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
51
+ "biogpt.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
52
+ "biogpt.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "biogpt.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "biogpt.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "biogpt.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "biogpt.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
57
+ "biogpt.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
58
+ "biogpt.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
59
+ "biogpt.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
60
+ "biogpt.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
61
+ "biogpt.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
62
+ "biogpt.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
63
+ "biogpt.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
64
+ "biogpt.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
65
+ "biogpt.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
66
+ "biogpt.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
67
+ "biogpt.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
68
+ "biogpt.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
69
+ "biogpt.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "biogpt.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
71
+ "biogpt.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "biogpt.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
73
+ "biogpt.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
74
+ "biogpt.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
75
+ "biogpt.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
76
+ "biogpt.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
77
+ "biogpt.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
78
+ "biogpt.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
79
+ "biogpt.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
80
+ "biogpt.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
81
+ "biogpt.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "biogpt.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
83
+ "biogpt.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
84
+ "biogpt.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
85
+ "biogpt.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
86
+ "biogpt.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
87
+ "biogpt.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "biogpt.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
89
+ "biogpt.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
90
+ "biogpt.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
91
+ "biogpt.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
92
+ "biogpt.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
93
+ "biogpt.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
94
+ "biogpt.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
95
+ "biogpt.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
96
+ "biogpt.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "biogpt.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "biogpt.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
99
+ "biogpt.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
100
+ "biogpt.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "biogpt.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "biogpt.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "biogpt.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "biogpt.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
105
+ "biogpt.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
106
+ "biogpt.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
107
+ "biogpt.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
108
+ "biogpt.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
109
+ "biogpt.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
110
+ "biogpt.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
111
+ "biogpt.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
112
+ "biogpt.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
113
+ "biogpt.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "biogpt.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
115
+ "biogpt.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
116
+ "biogpt.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
117
+ "biogpt.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
118
+ "biogpt.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
119
+ "biogpt.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
120
+ "biogpt.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
121
+ "biogpt.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
122
+ "biogpt.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
123
+ "biogpt.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
124
+ "biogpt.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
125
+ "biogpt.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
126
+ "biogpt.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
127
+ "biogpt.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
128
+ "biogpt.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
129
+ "biogpt.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "biogpt.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
131
+ "biogpt.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
132
+ "biogpt.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
133
+ "biogpt.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "biogpt.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
135
+ "biogpt.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
136
+ "biogpt.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
137
+ "biogpt.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
138
+ "biogpt.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
139
+ "biogpt.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
140
+ "biogpt.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
141
+ "biogpt.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
142
+ "biogpt.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
143
+ "biogpt.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
144
+ "biogpt.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "biogpt.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "biogpt.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
147
+ "biogpt.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
148
+ "biogpt.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "biogpt.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "biogpt.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "biogpt.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "biogpt.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
153
+ "biogpt.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
154
+ "biogpt.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
155
+ "biogpt.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
156
+ "biogpt.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
157
+ "biogpt.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
158
+ "biogpt.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
159
+ "biogpt.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
160
+ "biogpt.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
161
+ "biogpt.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
162
+ "biogpt.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
163
+ "biogpt.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
164
+ "biogpt.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
165
+ "biogpt.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "biogpt.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
167
+ "biogpt.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "biogpt.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
169
+ "biogpt.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
170
+ "biogpt.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
171
+ "biogpt.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
172
+ "biogpt.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
173
+ "biogpt.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
174
+ "biogpt.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
175
+ "biogpt.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
176
+ "biogpt.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
177
+ "biogpt.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
178
+ "biogpt.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
179
+ "biogpt.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
180
+ "biogpt.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
181
+ "biogpt.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
+ "biogpt.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
183
+ "biogpt.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
184
+ "biogpt.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
185
+ "biogpt.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
186
+ "biogpt.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
187
+ "biogpt.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
188
+ "biogpt.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
189
+ "biogpt.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
190
+ "biogpt.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
191
+ "biogpt.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
192
+ "biogpt.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
193
+ "biogpt.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "biogpt.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
195
+ "biogpt.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
196
+ "biogpt.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
197
+ "biogpt.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
198
+ "biogpt.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
199
+ "biogpt.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
200
+ "biogpt.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
201
+ "biogpt.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
202
+ "biogpt.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
203
+ "biogpt.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
204
+ "biogpt.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
205
+ "biogpt.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
206
+ "biogpt.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
207
+ "biogpt.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
208
+ "biogpt.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
209
+ "biogpt.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
+ "biogpt.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
211
+ "biogpt.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
212
+ "biogpt.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
213
+ "biogpt.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "biogpt.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
215
+ "biogpt.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "biogpt.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
217
+ "biogpt.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
218
+ "biogpt.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
219
+ "biogpt.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
220
+ "biogpt.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
221
+ "biogpt.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
222
+ "biogpt.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
223
+ "biogpt.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
224
+ "biogpt.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
225
+ "biogpt.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
226
+ "biogpt.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
227
+ "biogpt.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
228
+ "biogpt.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
229
+ "biogpt.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
230
+ "biogpt.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
231
+ "biogpt.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "biogpt.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
233
+ "biogpt.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
234
+ "biogpt.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
235
+ "biogpt.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
236
+ "biogpt.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
237
+ "biogpt.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
238
+ "biogpt.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
239
+ "biogpt.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
240
+ "biogpt.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
241
+ "biogpt.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
242
+ "biogpt.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
243
+ "biogpt.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
244
+ "biogpt.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
245
+ "biogpt.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
+ "biogpt.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
247
+ "biogpt.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "biogpt.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
249
+ "biogpt.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
250
+ "biogpt.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
251
+ "biogpt.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
252
+ "biogpt.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
253
+ "biogpt.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
254
+ "biogpt.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
255
+ "biogpt.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
256
+ "biogpt.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
257
+ "biogpt.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "biogpt.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
259
+ "biogpt.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
260
+ "biogpt.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
261
+ "biogpt.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
262
+ "biogpt.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
263
+ "biogpt.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
264
+ "biogpt.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
265
+ "biogpt.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
266
+ "biogpt.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
267
+ "biogpt.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
268
+ "biogpt.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
269
+ "biogpt.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
270
+ "biogpt.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
271
+ "biogpt.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
272
+ "biogpt.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
273
+ "biogpt.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
274
+ "biogpt.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
275
+ "biogpt.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
276
+ "biogpt.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
277
+ "biogpt.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
278
+ "biogpt.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
279
+ "biogpt.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
280
+ "biogpt.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
281
+ "biogpt.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
282
+ "biogpt.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
283
+ "biogpt.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
284
+ "biogpt.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
285
+ "biogpt.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
286
+ "biogpt.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
287
+ "biogpt.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
288
+ "biogpt.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "biogpt.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "biogpt.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
291
+ "biogpt.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
292
+ "biogpt.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "biogpt.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "biogpt.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "biogpt.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "biogpt.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
297
+ "biogpt.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
298
+ "biogpt.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
299
+ "biogpt.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
300
+ "biogpt.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
301
+ "biogpt.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
302
+ "biogpt.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
303
+ "biogpt.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
304
+ "biogpt.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
305
+ "biogpt.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
306
+ "biogpt.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
307
+ "biogpt.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
308
+ "biogpt.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
309
+ "biogpt.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
310
+ "biogpt.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
311
+ "biogpt.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
312
+ "biogpt.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
313
+ "biogpt.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
314
+ "biogpt.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
315
+ "biogpt.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
316
+ "biogpt.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
317
+ "biogpt.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
318
+ "biogpt.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
319
+ "biogpt.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
320
+ "biogpt.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
321
+ "biogpt.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
322
+ "biogpt.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
323
+ "biogpt.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
324
+ "biogpt.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
325
+ "biogpt.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
326
+ "biogpt.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
327
+ "biogpt.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
328
+ "biogpt.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
329
+ "biogpt.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
330
+ "biogpt.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
331
+ "biogpt.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
332
+ "biogpt.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
333
+ "biogpt.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
334
+ "biogpt.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
335
+ "biogpt.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
336
+ "biogpt.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
337
+ "biogpt.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
338
+ "biogpt.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
339
+ "biogpt.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
340
+ "biogpt.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
341
+ "biogpt.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
342
+ "biogpt.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
343
+ "biogpt.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
344
+ "biogpt.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
345
+ "biogpt.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
346
+ "biogpt.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
347
+ "biogpt.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
348
+ "biogpt.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
349
+ "biogpt.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
350
+ "biogpt.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
351
+ "biogpt.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
352
+ "biogpt.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
353
+ "biogpt.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
354
+ "biogpt.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
355
+ "biogpt.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
356
+ "biogpt.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
357
+ "biogpt.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
358
+ "biogpt.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
359
+ "biogpt.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "biogpt.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
361
+ "biogpt.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
362
+ "biogpt.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
363
+ "biogpt.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
364
+ "biogpt.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
365
+ "biogpt.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
366
+ "biogpt.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
367
+ "biogpt.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
368
+ "biogpt.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
369
+ "biogpt.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
370
+ "biogpt.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
371
+ "biogpt.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
372
+ "biogpt.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
373
+ "biogpt.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
374
+ "biogpt.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
375
+ "biogpt.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
376
+ "biogpt.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
377
+ "biogpt.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
378
+ "biogpt.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
379
+ "biogpt.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
380
+ "biogpt.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
381
+ "biogpt.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
382
+ "biogpt.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
383
+ "biogpt.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
384
+ "biogpt.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
385
+ "biogpt.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "biogpt.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
387
+ "biogpt.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
388
+ "biogpt.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
389
+ "biogpt.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "biogpt.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
391
+ "biogpt.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "biogpt.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
393
+ "biogpt.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
394
+ "biogpt.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
395
+ "biogpt.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
396
+ "biogpt.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
397
+ "biogpt.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
398
+ "biogpt.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
399
+ "biogpt.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
400
+ "biogpt.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
401
+ "biogpt.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
402
+ "biogpt.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
403
+ "biogpt.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
404
+ "biogpt.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
405
+ "biogpt.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
406
+ "biogpt.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
407
+ "biogpt.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
408
+ "biogpt.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
409
+ "biogpt.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
410
+ "biogpt.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
411
+ "biogpt.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
412
+ "biogpt.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
413
+ "biogpt.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
414
+ "biogpt.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
415
+ "biogpt.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
416
+ "biogpt.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
417
+ "biogpt.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
418
+ "biogpt.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
419
+ "biogpt.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
420
+ "biogpt.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
421
+ "biogpt.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
422
+ "biogpt.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
423
+ "biogpt.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
424
+ "biogpt.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
425
+ "biogpt.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
426
+ "biogpt.layers.32.fc1.bias": "model-00001-of-00002.safetensors",
427
+ "biogpt.layers.32.fc1.weight": "model-00001-of-00002.safetensors",
428
+ "biogpt.layers.32.fc2.bias": "model-00001-of-00002.safetensors",
429
+ "biogpt.layers.32.fc2.weight": "model-00001-of-00002.safetensors",
430
+ "biogpt.layers.32.final_layer_norm.bias": "model-00001-of-00002.safetensors",
431
+ "biogpt.layers.32.final_layer_norm.weight": "model-00001-of-00002.safetensors",
432
+ "biogpt.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
433
+ "biogpt.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
+ "biogpt.layers.32.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
435
+ "biogpt.layers.32.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
436
+ "biogpt.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
437
+ "biogpt.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "biogpt.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
439
+ "biogpt.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "biogpt.layers.32.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
441
+ "biogpt.layers.32.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
442
+ "biogpt.layers.33.fc1.bias": "model-00001-of-00002.safetensors",
443
+ "biogpt.layers.33.fc1.weight": "model-00001-of-00002.safetensors",
444
+ "biogpt.layers.33.fc2.bias": "model-00001-of-00002.safetensors",
445
+ "biogpt.layers.33.fc2.weight": "model-00001-of-00002.safetensors",
446
+ "biogpt.layers.33.final_layer_norm.bias": "model-00001-of-00002.safetensors",
447
+ "biogpt.layers.33.final_layer_norm.weight": "model-00001-of-00002.safetensors",
448
+ "biogpt.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
449
+ "biogpt.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
450
+ "biogpt.layers.33.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
451
+ "biogpt.layers.33.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
452
+ "biogpt.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
453
+ "biogpt.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
454
+ "biogpt.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
455
+ "biogpt.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
456
+ "biogpt.layers.33.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
457
+ "biogpt.layers.33.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
458
+ "biogpt.layers.34.fc1.bias": "model-00001-of-00002.safetensors",
459
+ "biogpt.layers.34.fc1.weight": "model-00001-of-00002.safetensors",
460
+ "biogpt.layers.34.fc2.bias": "model-00001-of-00002.safetensors",
461
+ "biogpt.layers.34.fc2.weight": "model-00001-of-00002.safetensors",
462
+ "biogpt.layers.34.final_layer_norm.bias": "model-00001-of-00002.safetensors",
463
+ "biogpt.layers.34.final_layer_norm.weight": "model-00001-of-00002.safetensors",
464
+ "biogpt.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
465
+ "biogpt.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
+ "biogpt.layers.34.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
467
+ "biogpt.layers.34.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
468
+ "biogpt.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
469
+ "biogpt.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
+ "biogpt.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
471
+ "biogpt.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
+ "biogpt.layers.34.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
473
+ "biogpt.layers.34.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
474
+ "biogpt.layers.35.fc1.bias": "model-00001-of-00002.safetensors",
475
+ "biogpt.layers.35.fc1.weight": "model-00001-of-00002.safetensors",
476
+ "biogpt.layers.35.fc2.bias": "model-00001-of-00002.safetensors",
477
+ "biogpt.layers.35.fc2.weight": "model-00001-of-00002.safetensors",
478
+ "biogpt.layers.35.final_layer_norm.bias": "model-00001-of-00002.safetensors",
479
+ "biogpt.layers.35.final_layer_norm.weight": "model-00001-of-00002.safetensors",
480
+ "biogpt.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
481
+ "biogpt.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
+ "biogpt.layers.35.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
483
+ "biogpt.layers.35.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
484
+ "biogpt.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
485
+ "biogpt.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
+ "biogpt.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
487
+ "biogpt.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "biogpt.layers.35.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
489
+ "biogpt.layers.35.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
490
+ "biogpt.layers.36.fc1.bias": "model-00001-of-00002.safetensors",
491
+ "biogpt.layers.36.fc1.weight": "model-00001-of-00002.safetensors",
492
+ "biogpt.layers.36.fc2.bias": "model-00001-of-00002.safetensors",
493
+ "biogpt.layers.36.fc2.weight": "model-00001-of-00002.safetensors",
494
+ "biogpt.layers.36.final_layer_norm.bias": "model-00001-of-00002.safetensors",
495
+ "biogpt.layers.36.final_layer_norm.weight": "model-00001-of-00002.safetensors",
496
+ "biogpt.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
497
+ "biogpt.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
+ "biogpt.layers.36.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
499
+ "biogpt.layers.36.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
500
+ "biogpt.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
+ "biogpt.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "biogpt.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
+ "biogpt.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "biogpt.layers.36.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
505
+ "biogpt.layers.36.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
506
+ "biogpt.layers.37.fc1.bias": "model-00002-of-00002.safetensors",
507
+ "biogpt.layers.37.fc1.weight": "model-00002-of-00002.safetensors",
508
+ "biogpt.layers.37.fc2.bias": "model-00002-of-00002.safetensors",
509
+ "biogpt.layers.37.fc2.weight": "model-00002-of-00002.safetensors",
510
+ "biogpt.layers.37.final_layer_norm.bias": "model-00002-of-00002.safetensors",
511
+ "biogpt.layers.37.final_layer_norm.weight": "model-00002-of-00002.safetensors",
512
+ "biogpt.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
513
+ "biogpt.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
+ "biogpt.layers.37.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
515
+ "biogpt.layers.37.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
516
+ "biogpt.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
517
+ "biogpt.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
+ "biogpt.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
519
+ "biogpt.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
+ "biogpt.layers.37.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
521
+ "biogpt.layers.37.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
522
+ "biogpt.layers.38.fc1.bias": "model-00002-of-00002.safetensors",
523
+ "biogpt.layers.38.fc1.weight": "model-00002-of-00002.safetensors",
524
+ "biogpt.layers.38.fc2.bias": "model-00002-of-00002.safetensors",
525
+ "biogpt.layers.38.fc2.weight": "model-00002-of-00002.safetensors",
526
+ "biogpt.layers.38.final_layer_norm.bias": "model-00002-of-00002.safetensors",
527
+ "biogpt.layers.38.final_layer_norm.weight": "model-00002-of-00002.safetensors",
528
+ "biogpt.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
529
+ "biogpt.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
530
+ "biogpt.layers.38.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
531
+ "biogpt.layers.38.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
532
+ "biogpt.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
533
+ "biogpt.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
534
+ "biogpt.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
535
+ "biogpt.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
536
+ "biogpt.layers.38.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
537
+ "biogpt.layers.38.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
538
+ "biogpt.layers.39.fc1.bias": "model-00002-of-00002.safetensors",
539
+ "biogpt.layers.39.fc1.weight": "model-00002-of-00002.safetensors",
540
+ "biogpt.layers.39.fc2.bias": "model-00002-of-00002.safetensors",
541
+ "biogpt.layers.39.fc2.weight": "model-00002-of-00002.safetensors",
542
+ "biogpt.layers.39.final_layer_norm.bias": "model-00002-of-00002.safetensors",
543
+ "biogpt.layers.39.final_layer_norm.weight": "model-00002-of-00002.safetensors",
544
+ "biogpt.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
545
+ "biogpt.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
546
+ "biogpt.layers.39.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
547
+ "biogpt.layers.39.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
548
+ "biogpt.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
549
+ "biogpt.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
550
+ "biogpt.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
551
+ "biogpt.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
552
+ "biogpt.layers.39.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
553
+ "biogpt.layers.39.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
554
+ "biogpt.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
555
+ "biogpt.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
556
+ "biogpt.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
557
+ "biogpt.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
558
+ "biogpt.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
559
+ "biogpt.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
560
+ "biogpt.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
561
+ "biogpt.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
562
+ "biogpt.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
563
+ "biogpt.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
564
+ "biogpt.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
565
+ "biogpt.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
566
+ "biogpt.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
567
+ "biogpt.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
568
+ "biogpt.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
569
+ "biogpt.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
570
+ "biogpt.layers.40.fc1.bias": "model-00002-of-00002.safetensors",
571
+ "biogpt.layers.40.fc1.weight": "model-00002-of-00002.safetensors",
572
+ "biogpt.layers.40.fc2.bias": "model-00002-of-00002.safetensors",
573
+ "biogpt.layers.40.fc2.weight": "model-00002-of-00002.safetensors",
574
+ "biogpt.layers.40.final_layer_norm.bias": "model-00002-of-00002.safetensors",
575
+ "biogpt.layers.40.final_layer_norm.weight": "model-00002-of-00002.safetensors",
576
+ "biogpt.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
577
+ "biogpt.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
578
+ "biogpt.layers.40.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
579
+ "biogpt.layers.40.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
580
+ "biogpt.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
581
+ "biogpt.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
582
+ "biogpt.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
583
+ "biogpt.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
584
+ "biogpt.layers.40.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
585
+ "biogpt.layers.40.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
586
+ "biogpt.layers.41.fc1.bias": "model-00002-of-00002.safetensors",
587
+ "biogpt.layers.41.fc1.weight": "model-00002-of-00002.safetensors",
588
+ "biogpt.layers.41.fc2.bias": "model-00002-of-00002.safetensors",
589
+ "biogpt.layers.41.fc2.weight": "model-00002-of-00002.safetensors",
590
+ "biogpt.layers.41.final_layer_norm.bias": "model-00002-of-00002.safetensors",
591
+ "biogpt.layers.41.final_layer_norm.weight": "model-00002-of-00002.safetensors",
592
+ "biogpt.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
593
+ "biogpt.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
594
+ "biogpt.layers.41.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
595
+ "biogpt.layers.41.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
596
+ "biogpt.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
597
+ "biogpt.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
598
+ "biogpt.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
599
+ "biogpt.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
600
+ "biogpt.layers.41.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
601
+ "biogpt.layers.41.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
602
+ "biogpt.layers.42.fc1.bias": "model-00002-of-00002.safetensors",
603
+ "biogpt.layers.42.fc1.weight": "model-00002-of-00002.safetensors",
604
+ "biogpt.layers.42.fc2.bias": "model-00002-of-00002.safetensors",
605
+ "biogpt.layers.42.fc2.weight": "model-00002-of-00002.safetensors",
606
+ "biogpt.layers.42.final_layer_norm.bias": "model-00002-of-00002.safetensors",
607
+ "biogpt.layers.42.final_layer_norm.weight": "model-00002-of-00002.safetensors",
608
+ "biogpt.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
609
+ "biogpt.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
610
+ "biogpt.layers.42.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
611
+ "biogpt.layers.42.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
612
+ "biogpt.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
613
+ "biogpt.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
614
+ "biogpt.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
615
+ "biogpt.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
616
+ "biogpt.layers.42.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
617
+ "biogpt.layers.42.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
618
+ "biogpt.layers.43.fc1.bias": "model-00002-of-00002.safetensors",
619
+ "biogpt.layers.43.fc1.weight": "model-00002-of-00002.safetensors",
620
+ "biogpt.layers.43.fc2.bias": "model-00002-of-00002.safetensors",
621
+ "biogpt.layers.43.fc2.weight": "model-00002-of-00002.safetensors",
622
+ "biogpt.layers.43.final_layer_norm.bias": "model-00002-of-00002.safetensors",
623
+ "biogpt.layers.43.final_layer_norm.weight": "model-00002-of-00002.safetensors",
624
+ "biogpt.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
625
+ "biogpt.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
626
+ "biogpt.layers.43.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
627
+ "biogpt.layers.43.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
628
+ "biogpt.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
629
+ "biogpt.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
630
+ "biogpt.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
631
+ "biogpt.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
632
+ "biogpt.layers.43.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
633
+ "biogpt.layers.43.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
634
+ "biogpt.layers.44.fc1.bias": "model-00002-of-00002.safetensors",
635
+ "biogpt.layers.44.fc1.weight": "model-00002-of-00002.safetensors",
636
+ "biogpt.layers.44.fc2.bias": "model-00002-of-00002.safetensors",
637
+ "biogpt.layers.44.fc2.weight": "model-00002-of-00002.safetensors",
638
+ "biogpt.layers.44.final_layer_norm.bias": "model-00002-of-00002.safetensors",
639
+ "biogpt.layers.44.final_layer_norm.weight": "model-00002-of-00002.safetensors",
640
+ "biogpt.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
641
+ "biogpt.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
642
+ "biogpt.layers.44.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
643
+ "biogpt.layers.44.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
644
+ "biogpt.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
645
+ "biogpt.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
646
+ "biogpt.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
647
+ "biogpt.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
648
+ "biogpt.layers.44.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
649
+ "biogpt.layers.44.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
650
+ "biogpt.layers.45.fc1.bias": "model-00002-of-00002.safetensors",
651
+ "biogpt.layers.45.fc1.weight": "model-00002-of-00002.safetensors",
652
+ "biogpt.layers.45.fc2.bias": "model-00002-of-00002.safetensors",
653
+ "biogpt.layers.45.fc2.weight": "model-00002-of-00002.safetensors",
654
+ "biogpt.layers.45.final_layer_norm.bias": "model-00002-of-00002.safetensors",
655
+ "biogpt.layers.45.final_layer_norm.weight": "model-00002-of-00002.safetensors",
656
+ "biogpt.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
657
+ "biogpt.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
658
+ "biogpt.layers.45.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
659
+ "biogpt.layers.45.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
660
+ "biogpt.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
661
+ "biogpt.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
662
+ "biogpt.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
663
+ "biogpt.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
664
+ "biogpt.layers.45.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
665
+ "biogpt.layers.45.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
666
+ "biogpt.layers.46.fc1.bias": "model-00002-of-00002.safetensors",
667
+ "biogpt.layers.46.fc1.weight": "model-00002-of-00002.safetensors",
668
+ "biogpt.layers.46.fc2.bias": "model-00002-of-00002.safetensors",
669
+ "biogpt.layers.46.fc2.weight": "model-00002-of-00002.safetensors",
670
+ "biogpt.layers.46.final_layer_norm.bias": "model-00002-of-00002.safetensors",
671
+ "biogpt.layers.46.final_layer_norm.weight": "model-00002-of-00002.safetensors",
672
+ "biogpt.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
673
+ "biogpt.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
674
+ "biogpt.layers.46.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
675
+ "biogpt.layers.46.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
676
+ "biogpt.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
677
+ "biogpt.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
678
+ "biogpt.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
679
+ "biogpt.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
680
+ "biogpt.layers.46.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
681
+ "biogpt.layers.46.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
682
+ "biogpt.layers.47.fc1.bias": "model-00002-of-00002.safetensors",
683
+ "biogpt.layers.47.fc1.weight": "model-00002-of-00002.safetensors",
684
+ "biogpt.layers.47.fc2.bias": "model-00002-of-00002.safetensors",
685
+ "biogpt.layers.47.fc2.weight": "model-00002-of-00002.safetensors",
686
+ "biogpt.layers.47.final_layer_norm.bias": "model-00002-of-00002.safetensors",
687
+ "biogpt.layers.47.final_layer_norm.weight": "model-00002-of-00002.safetensors",
688
+ "biogpt.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
689
+ "biogpt.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
690
+ "biogpt.layers.47.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
691
+ "biogpt.layers.47.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
692
+ "biogpt.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
693
+ "biogpt.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
694
+ "biogpt.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
695
+ "biogpt.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
696
+ "biogpt.layers.47.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
697
+ "biogpt.layers.47.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
698
+ "biogpt.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
699
+ "biogpt.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
700
+ "biogpt.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
701
+ "biogpt.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
702
+ "biogpt.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
703
+ "biogpt.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
704
+ "biogpt.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
705
+ "biogpt.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
706
+ "biogpt.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
707
+ "biogpt.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
708
+ "biogpt.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
709
+ "biogpt.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
+ "biogpt.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
711
+ "biogpt.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
712
+ "biogpt.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
713
+ "biogpt.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
714
+ "biogpt.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
715
+ "biogpt.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
716
+ "biogpt.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
717
+ "biogpt.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
718
+ "biogpt.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
719
+ "biogpt.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
720
+ "biogpt.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
721
+ "biogpt.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
722
+ "biogpt.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
723
+ "biogpt.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
724
+ "biogpt.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
725
+ "biogpt.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
726
+ "biogpt.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
727
+ "biogpt.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
728
+ "biogpt.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
729
+ "biogpt.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
730
+ "biogpt.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
731
+ "biogpt.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
732
+ "biogpt.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
733
+ "biogpt.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
734
+ "biogpt.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
735
+ "biogpt.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
736
+ "biogpt.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
737
+ "biogpt.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
738
+ "biogpt.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
739
+ "biogpt.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
740
+ "biogpt.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
+ "biogpt.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
+ "biogpt.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
+ "biogpt.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
+ "biogpt.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
745
+ "biogpt.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
746
+ "biogpt.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
747
+ "biogpt.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
748
+ "biogpt.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
749
+ "biogpt.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
750
+ "biogpt.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
751
+ "biogpt.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
752
+ "biogpt.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
753
+ "biogpt.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
754
+ "biogpt.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
755
+ "biogpt.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
756
+ "biogpt.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
757
+ "biogpt.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
758
+ "biogpt.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
759
+ "biogpt.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
760
+ "biogpt.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
761
+ "biogpt.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
762
+ "biogpt.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
763
+ "biogpt.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
764
+ "biogpt.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
765
+ "biogpt.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
766
+ "biogpt.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
767
+ "biogpt.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
768
+ "biogpt.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
769
+ "biogpt.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
770
+ "biogpt.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
771
+ "biogpt.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
772
+ "biogpt.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
773
+ "biogpt.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
774
+ "biogpt.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
775
+ "biogpt.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
776
+ "biogpt.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
777
+ "biogpt.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
778
+ }
779
+ }