wpferrell commited on
Commit
a83ca09
·
verified ·
1 Parent(s): 8e8b97a

Upload bigsmall.index.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. bigsmall.index.json +486 -0
bigsmall.index.json ADDED
@@ -0,0 +1,486 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "bigsmall_version": "2.0.1",
4
+ "container_version": 1,
5
+ "format": "bf16",
6
+ "mode": "balanced",
7
+ "model_type": "llm",
8
+ "total_size": 12140499619,
9
+ "total_raw_size": 18483411968,
10
+ "ratio_pct": 65.68321714637226,
11
+ "shard_count": 4,
12
+ "tensor_count": 464,
13
+ "shards": [
14
+ "model-00001-of-00004.bs",
15
+ "model-00002-of-00004.bs",
16
+ "model-00003-of-00004.bs",
17
+ "model-00004-of-00004.bs"
18
+ ]
19
+ },
20
+ "weight_map": {
21
+ "model.embed_tokens.weight": "model-00001-of-00004.bs",
22
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.bs",
23
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.bs",
24
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.bs",
25
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.bs",
26
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.bs",
27
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
28
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
29
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.bs",
30
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.bs",
31
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.bs",
32
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.bs",
33
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.bs",
34
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.bs",
35
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.bs",
36
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.bs",
37
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.bs",
38
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
39
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
40
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.bs",
41
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.bs",
42
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.bs",
43
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.bs",
44
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.bs",
45
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.bs",
46
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.bs",
47
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.bs",
48
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.bs",
49
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
50
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
51
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.bs",
52
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.bs",
53
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.bs",
54
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.bs",
55
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.bs",
56
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.bs",
57
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.bs",
58
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.bs",
59
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.bs",
60
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
61
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
62
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.bs",
63
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.bs",
64
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.bs",
65
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.bs",
66
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.bs",
67
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.bs",
68
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.bs",
69
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.bs",
70
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.bs",
71
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
72
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
73
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.bs",
74
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.bs",
75
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.bs",
76
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.bs",
77
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.bs",
78
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.bs",
79
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.bs",
80
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.bs",
81
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.bs",
82
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
83
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
84
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.bs",
85
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.bs",
86
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.bs",
87
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.bs",
88
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.bs",
89
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.bs",
90
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.bs",
91
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.bs",
92
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.bs",
93
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.bs",
94
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.bs",
95
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.bs",
96
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.bs",
97
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.bs",
98
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.bs",
99
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.bs",
100
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.bs",
101
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.bs",
102
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.bs",
103
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.bs",
104
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.bs",
105
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.bs",
106
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.bs",
107
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.bs",
108
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.bs",
109
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.bs",
110
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
111
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
112
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.bs",
113
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.bs",
114
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.bs",
115
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.bs",
116
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.bs",
117
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.bs",
118
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.bs",
119
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.bs",
120
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.bs",
121
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
122
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
123
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.bs",
124
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.bs",
125
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.bs",
126
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.bs",
127
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.bs",
128
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.bs",
129
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.bs",
130
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.bs",
131
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.bs",
132
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
133
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
134
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.bs",
135
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.bs",
136
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.bs",
137
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.bs",
138
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.bs",
139
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.bs",
140
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.bs",
141
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.bs",
142
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.bs",
143
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
144
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
145
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.bs",
146
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.bs",
147
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.bs",
148
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.bs",
149
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.bs",
150
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.bs",
151
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.bs",
152
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.bs",
153
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.bs",
154
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
155
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
156
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.bs",
157
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.bs",
158
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.bs",
159
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.bs",
160
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.bs",
161
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.bs",
162
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.bs",
163
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.bs",
164
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.bs",
165
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
166
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
167
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.bs",
168
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.bs",
169
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.bs",
170
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.bs",
171
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.bs",
172
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.bs",
173
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.bs",
174
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.bs",
175
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.bs",
176
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
177
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
178
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.bs",
179
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.bs",
180
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.bs",
181
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.bs",
182
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.bs",
183
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.bs",
184
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.bs",
185
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.bs",
186
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.bs",
187
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
188
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
189
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.bs",
190
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.bs",
191
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.bs",
192
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.bs",
193
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.bs",
194
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.bs",
195
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.bs",
196
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.bs",
197
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.bs",
198
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
199
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
200
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.bs",
201
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.bs",
202
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.bs",
203
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.bs",
204
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.bs",
205
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.bs",
206
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.bs",
207
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.bs",
208
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.bs",
209
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
210
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
211
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.bs",
212
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.bs",
213
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.bs",
214
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.bs",
215
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.bs",
216
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.bs",
217
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.bs",
218
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.bs",
219
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.bs",
220
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.bs",
221
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.bs",
222
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
223
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
224
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.bs",
225
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.bs",
226
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.bs",
227
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.bs",
228
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.bs",
229
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
230
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
231
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.bs",
232
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.bs",
233
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.bs",
234
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.bs",
235
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.bs",
236
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.bs",
237
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.bs",
238
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.bs",
239
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.bs",
240
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.bs",
241
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.bs",
242
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.bs",
243
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.bs",
244
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.bs",
245
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.bs",
246
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.bs",
247
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.bs",
248
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.bs",
249
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.bs",
250
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.bs",
251
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
252
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
253
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.bs",
254
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.bs",
255
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.bs",
256
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.bs",
257
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.bs",
258
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
259
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
260
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.bs",
261
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.bs",
262
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.bs",
263
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.bs",
264
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.bs",
265
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.bs",
266
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.bs",
267
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.bs",
268
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.bs",
269
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
270
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
271
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.bs",
272
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.bs",
273
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.bs",
274
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.bs",
275
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.bs",
276
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.bs",
277
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.bs",
278
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.bs",
279
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.bs",
280
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
281
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
282
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.bs",
283
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.bs",
284
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.bs",
285
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.bs",
286
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.bs",
287
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.bs",
288
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.bs",
289
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.bs",
290
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.bs",
291
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
292
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
293
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.bs",
294
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.bs",
295
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.bs",
296
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.bs",
297
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.bs",
298
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.bs",
299
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.bs",
300
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.bs",
301
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.bs",
302
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
303
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
304
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.bs",
305
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.bs",
306
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.bs",
307
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.bs",
308
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.bs",
309
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.bs",
310
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.bs",
311
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.bs",
312
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.bs",
313
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
314
+ "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
315
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.bs",
316
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.bs",
317
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.bs",
318
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.bs",
319
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.bs",
320
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.bs",
321
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.bs",
322
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.bs",
323
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.bs",
324
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
325
+ "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
326
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.bs",
327
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.bs",
328
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.bs",
329
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.bs",
330
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.bs",
331
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.bs",
332
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.bs",
333
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.bs",
334
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.bs",
335
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
336
+ "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
337
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.bs",
338
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.bs",
339
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.bs",
340
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.bs",
341
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.bs",
342
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.bs",
343
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.bs",
344
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.bs",
345
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.bs",
346
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
347
+ "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
348
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.bs",
349
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.bs",
350
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.bs",
351
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.bs",
352
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.bs",
353
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.bs",
354
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.bs",
355
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.bs",
356
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.bs",
357
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
358
+ "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
359
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.bs",
360
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.bs",
361
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.bs",
362
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.bs",
363
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.bs",
364
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.bs",
365
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.bs",
366
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.bs",
367
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.bs",
368
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.bs",
369
+ "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.bs",
370
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.bs",
371
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.bs",
372
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.bs",
373
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.bs",
374
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.bs",
375
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.bs",
376
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.bs",
377
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.bs",
378
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.bs",
379
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.bs",
380
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00004.bs",
381
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.bs",
382
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.bs",
383
+ "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
384
+ "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
385
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.bs",
386
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.bs",
387
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.bs",
388
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.bs",
389
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.bs",
390
+ "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
391
+ "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
392
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.bs",
393
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.bs",
394
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.bs",
395
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.bs",
396
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.bs",
397
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.bs",
398
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.bs",
399
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.bs",
400
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.bs",
401
+ "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
402
+ "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
403
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.bs",
404
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.bs",
405
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.bs",
406
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.bs",
407
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.bs",
408
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.bs",
409
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.bs",
410
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.bs",
411
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.bs",
412
+ "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
413
+ "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
414
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.bs",
415
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.bs",
416
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.bs",
417
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.bs",
418
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.bs",
419
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.bs",
420
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.bs",
421
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.bs",
422
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.bs",
423
+ "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
424
+ "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
425
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.bs",
426
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.bs",
427
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.bs",
428
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.bs",
429
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.bs",
430
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.bs",
431
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.bs",
432
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.bs",
433
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.bs",
434
+ "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
435
+ "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
436
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.bs",
437
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.bs",
438
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.bs",
439
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.bs",
440
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.bs",
441
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.bs",
442
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.bs",
443
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.bs",
444
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.bs",
445
+ "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
446
+ "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
447
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.bs",
448
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.bs",
449
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.bs",
450
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.bs",
451
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.bs",
452
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.bs",
453
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.bs",
454
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.bs",
455
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.bs",
456
+ "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
457
+ "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
458
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.bs",
459
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.bs",
460
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.bs",
461
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.bs",
462
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00004.bs",
463
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.bs",
464
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.bs",
465
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.bs",
466
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.bs",
467
+ "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
468
+ "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
469
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.bs",
470
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.bs",
471
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.bs",
472
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.bs",
473
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00004.bs",
474
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.bs",
475
+ "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.bs",
476
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.bs",
477
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.bs",
478
+ "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.bs",
479
+ "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.bs",
480
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.bs",
481
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.bs",
482
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.bs",
483
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.bs",
484
+ "model.norm.weight": "model-00004-of-00004.bs"
485
+ }
486
+ }