Hilbertmeng commited on
Commit
c69b327
·
1 Parent(s): 78bf0cf

add model weights

Browse files
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:449ef5cdc2d3f2e7f70a4b1dbce7c1aff5141990e3694e6754321674eb575f8b
3
+ size 4966974296
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d9a5eb9e529f8a98bbb714bebfa07f3b9ac0e0303b6229a5b0287c4f1102a6
3
+ size 642822090
model.safetensors.index.json ADDED
@@ -0,0 +1,520 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5609743418
4
+ },
5
+ "weight_map": {
6
+ "dense_bs.0": "model-00002-of-00002.safetensors",
7
+ "dense_bs.1": "model-00002-of-00002.safetensors",
8
+ "dense_bs.10": "model-00002-of-00002.safetensors",
9
+ "dense_bs.11": "model-00002-of-00002.safetensors",
10
+ "dense_bs.12": "model-00002-of-00002.safetensors",
11
+ "dense_bs.13": "model-00002-of-00002.safetensors",
12
+ "dense_bs.14": "model-00002-of-00002.safetensors",
13
+ "dense_bs.15": "model-00002-of-00002.safetensors",
14
+ "dense_bs.16": "model-00002-of-00002.safetensors",
15
+ "dense_bs.17": "model-00002-of-00002.safetensors",
16
+ "dense_bs.18": "model-00002-of-00002.safetensors",
17
+ "dense_bs.19": "model-00002-of-00002.safetensors",
18
+ "dense_bs.2": "model-00002-of-00002.safetensors",
19
+ "dense_bs.20": "model-00002-of-00002.safetensors",
20
+ "dense_bs.21": "model-00002-of-00002.safetensors",
21
+ "dense_bs.22": "model-00002-of-00002.safetensors",
22
+ "dense_bs.23": "model-00002-of-00002.safetensors",
23
+ "dense_bs.24": "model-00002-of-00002.safetensors",
24
+ "dense_bs.25": "model-00002-of-00002.safetensors",
25
+ "dense_bs.26": "model-00002-of-00002.safetensors",
26
+ "dense_bs.27": "model-00002-of-00002.safetensors",
27
+ "dense_bs.28": "model-00002-of-00002.safetensors",
28
+ "dense_bs.29": "model-00002-of-00002.safetensors",
29
+ "dense_bs.3": "model-00002-of-00002.safetensors",
30
+ "dense_bs.30": "model-00002-of-00002.safetensors",
31
+ "dense_bs.31": "model-00002-of-00002.safetensors",
32
+ "dense_bs.4": "model-00002-of-00002.safetensors",
33
+ "dense_bs.5": "model-00002-of-00002.safetensors",
34
+ "dense_bs.6": "model-00002-of-00002.safetensors",
35
+ "dense_bs.7": "model-00002-of-00002.safetensors",
36
+ "dense_bs.8": "model-00002-of-00002.safetensors",
37
+ "dense_bs.9": "model-00002-of-00002.safetensors",
38
+ "dynamic_dense.0.w1.weight": "model-00002-of-00002.safetensors",
39
+ "dynamic_dense.0.w2.weight": "model-00002-of-00002.safetensors",
40
+ "dynamic_dense.1.w1.weight": "model-00002-of-00002.safetensors",
41
+ "dynamic_dense.1.w2.weight": "model-00002-of-00002.safetensors",
42
+ "dynamic_dense.10.w1.weight": "model-00002-of-00002.safetensors",
43
+ "dynamic_dense.10.w2.weight": "model-00002-of-00002.safetensors",
44
+ "dynamic_dense.11.w1.weight": "model-00002-of-00002.safetensors",
45
+ "dynamic_dense.11.w2.weight": "model-00002-of-00002.safetensors",
46
+ "dynamic_dense.12.w1.weight": "model-00002-of-00002.safetensors",
47
+ "dynamic_dense.12.w2.weight": "model-00002-of-00002.safetensors",
48
+ "dynamic_dense.13.w1.weight": "model-00002-of-00002.safetensors",
49
+ "dynamic_dense.13.w2.weight": "model-00002-of-00002.safetensors",
50
+ "dynamic_dense.14.w1.weight": "model-00002-of-00002.safetensors",
51
+ "dynamic_dense.14.w2.weight": "model-00002-of-00002.safetensors",
52
+ "dynamic_dense.15.w1.weight": "model-00002-of-00002.safetensors",
53
+ "dynamic_dense.15.w2.weight": "model-00002-of-00002.safetensors",
54
+ "dynamic_dense.16.w1.weight": "model-00002-of-00002.safetensors",
55
+ "dynamic_dense.16.w2.weight": "model-00002-of-00002.safetensors",
56
+ "dynamic_dense.17.w1.weight": "model-00002-of-00002.safetensors",
57
+ "dynamic_dense.17.w2.weight": "model-00002-of-00002.safetensors",
58
+ "dynamic_dense.18.w1.weight": "model-00002-of-00002.safetensors",
59
+ "dynamic_dense.18.w2.weight": "model-00002-of-00002.safetensors",
60
+ "dynamic_dense.19.w1.weight": "model-00002-of-00002.safetensors",
61
+ "dynamic_dense.19.w2.weight": "model-00002-of-00002.safetensors",
62
+ "dynamic_dense.2.w1.weight": "model-00002-of-00002.safetensors",
63
+ "dynamic_dense.2.w2.weight": "model-00002-of-00002.safetensors",
64
+ "dynamic_dense.20.w1.weight": "model-00002-of-00002.safetensors",
65
+ "dynamic_dense.20.w2.weight": "model-00002-of-00002.safetensors",
66
+ "dynamic_dense.21.w1.weight": "model-00002-of-00002.safetensors",
67
+ "dynamic_dense.21.w2.weight": "model-00002-of-00002.safetensors",
68
+ "dynamic_dense.22.w1.weight": "model-00002-of-00002.safetensors",
69
+ "dynamic_dense.22.w2.weight": "model-00002-of-00002.safetensors",
70
+ "dynamic_dense.23.w1.weight": "model-00002-of-00002.safetensors",
71
+ "dynamic_dense.23.w2.weight": "model-00002-of-00002.safetensors",
72
+ "dynamic_dense.24.w1.weight": "model-00002-of-00002.safetensors",
73
+ "dynamic_dense.24.w2.weight": "model-00002-of-00002.safetensors",
74
+ "dynamic_dense.25.w1.weight": "model-00002-of-00002.safetensors",
75
+ "dynamic_dense.25.w2.weight": "model-00002-of-00002.safetensors",
76
+ "dynamic_dense.26.w1.weight": "model-00002-of-00002.safetensors",
77
+ "dynamic_dense.26.w2.weight": "model-00002-of-00002.safetensors",
78
+ "dynamic_dense.27.w1.weight": "model-00002-of-00002.safetensors",
79
+ "dynamic_dense.27.w2.weight": "model-00002-of-00002.safetensors",
80
+ "dynamic_dense.28.w1.weight": "model-00002-of-00002.safetensors",
81
+ "dynamic_dense.28.w2.weight": "model-00002-of-00002.safetensors",
82
+ "dynamic_dense.29.w1.weight": "model-00002-of-00002.safetensors",
83
+ "dynamic_dense.29.w2.weight": "model-00002-of-00002.safetensors",
84
+ "dynamic_dense.3.w1.weight": "model-00002-of-00002.safetensors",
85
+ "dynamic_dense.3.w2.weight": "model-00002-of-00002.safetensors",
86
+ "dynamic_dense.30.w1.weight": "model-00002-of-00002.safetensors",
87
+ "dynamic_dense.30.w2.weight": "model-00002-of-00002.safetensors",
88
+ "dynamic_dense.31.w1.weight": "model-00002-of-00002.safetensors",
89
+ "dynamic_dense.31.w2.weight": "model-00002-of-00002.safetensors",
90
+ "dynamic_dense.4.w1.weight": "model-00002-of-00002.safetensors",
91
+ "dynamic_dense.4.w2.weight": "model-00002-of-00002.safetensors",
92
+ "dynamic_dense.5.w1.weight": "model-00002-of-00002.safetensors",
93
+ "dynamic_dense.5.w2.weight": "model-00002-of-00002.safetensors",
94
+ "dynamic_dense.6.w1.weight": "model-00002-of-00002.safetensors",
95
+ "dynamic_dense.6.w2.weight": "model-00002-of-00002.safetensors",
96
+ "dynamic_dense.7.w1.weight": "model-00002-of-00002.safetensors",
97
+ "dynamic_dense.7.w2.weight": "model-00002-of-00002.safetensors",
98
+ "dynamic_dense.8.w1.weight": "model-00002-of-00002.safetensors",
99
+ "dynamic_dense.8.w2.weight": "model-00002-of-00002.safetensors",
100
+ "dynamic_dense.9.w1.weight": "model-00002-of-00002.safetensors",
101
+ "dynamic_dense.9.w2.weight": "model-00002-of-00002.safetensors",
102
+ "layers.0.attention.k_norm.weight": "model-00001-of-00002.safetensors",
103
+ "layers.0.attention.q_norm.weight": "model-00001-of-00002.safetensors",
104
+ "layers.0.attention.wk.weight": "model-00001-of-00002.safetensors",
105
+ "layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
106
+ "layers.0.attention.wq.weight": "model-00001-of-00002.safetensors",
107
+ "layers.0.attention.wv.weight": "model-00001-of-00002.safetensors",
108
+ "layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
109
+ "layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
110
+ "layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
111
+ "layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
112
+ "layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
113
+ "layers.1.attention.k_norm.weight": "model-00001-of-00002.safetensors",
114
+ "layers.1.attention.q_norm.weight": "model-00001-of-00002.safetensors",
115
+ "layers.1.attention.wk.weight": "model-00001-of-00002.safetensors",
116
+ "layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
117
+ "layers.1.attention.wq.weight": "model-00001-of-00002.safetensors",
118
+ "layers.1.attention.wv.weight": "model-00001-of-00002.safetensors",
119
+ "layers.1.attention_norms.0.weight": "model-00001-of-00002.safetensors",
120
+ "layers.1.attention_norms.1.weight": "model-00001-of-00002.safetensors",
121
+ "layers.1.attention_norms.2.weight": "model-00001-of-00002.safetensors",
122
+ "layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
123
+ "layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
124
+ "layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
125
+ "layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
126
+ "layers.10.attention.k_norm.weight": "model-00001-of-00002.safetensors",
127
+ "layers.10.attention.q_norm.weight": "model-00001-of-00002.safetensors",
128
+ "layers.10.attention.wk.weight": "model-00001-of-00002.safetensors",
129
+ "layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
130
+ "layers.10.attention.wq.weight": "model-00001-of-00002.safetensors",
131
+ "layers.10.attention.wv.weight": "model-00001-of-00002.safetensors",
132
+ "layers.10.attention_norms.0.weight": "model-00001-of-00002.safetensors",
133
+ "layers.10.attention_norms.1.weight": "model-00001-of-00002.safetensors",
134
+ "layers.10.attention_norms.2.weight": "model-00001-of-00002.safetensors",
135
+ "layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
136
+ "layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
137
+ "layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
138
+ "layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
139
+ "layers.11.attention.k_norm.weight": "model-00001-of-00002.safetensors",
140
+ "layers.11.attention.q_norm.weight": "model-00001-of-00002.safetensors",
141
+ "layers.11.attention.wk.weight": "model-00001-of-00002.safetensors",
142
+ "layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
143
+ "layers.11.attention.wq.weight": "model-00001-of-00002.safetensors",
144
+ "layers.11.attention.wv.weight": "model-00001-of-00002.safetensors",
145
+ "layers.11.attention_norms.0.weight": "model-00001-of-00002.safetensors",
146
+ "layers.11.attention_norms.1.weight": "model-00001-of-00002.safetensors",
147
+ "layers.11.attention_norms.2.weight": "model-00001-of-00002.safetensors",
148
+ "layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
149
+ "layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
150
+ "layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
151
+ "layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
152
+ "layers.12.attention.k_norm.weight": "model-00001-of-00002.safetensors",
153
+ "layers.12.attention.q_norm.weight": "model-00001-of-00002.safetensors",
154
+ "layers.12.attention.wk.weight": "model-00001-of-00002.safetensors",
155
+ "layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
156
+ "layers.12.attention.wq.weight": "model-00001-of-00002.safetensors",
157
+ "layers.12.attention.wv.weight": "model-00001-of-00002.safetensors",
158
+ "layers.12.attention_norms.0.weight": "model-00001-of-00002.safetensors",
159
+ "layers.12.attention_norms.1.weight": "model-00001-of-00002.safetensors",
160
+ "layers.12.attention_norms.2.weight": "model-00001-of-00002.safetensors",
161
+ "layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
162
+ "layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
163
+ "layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
164
+ "layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
165
+ "layers.13.attention.k_norm.weight": "model-00001-of-00002.safetensors",
166
+ "layers.13.attention.q_norm.weight": "model-00001-of-00002.safetensors",
167
+ "layers.13.attention.wk.weight": "model-00001-of-00002.safetensors",
168
+ "layers.13.attention.wo.weight": "model-00001-of-00002.safetensors",
169
+ "layers.13.attention.wq.weight": "model-00001-of-00002.safetensors",
170
+ "layers.13.attention.wv.weight": "model-00001-of-00002.safetensors",
171
+ "layers.13.attention_norms.0.weight": "model-00001-of-00002.safetensors",
172
+ "layers.13.attention_norms.1.weight": "model-00001-of-00002.safetensors",
173
+ "layers.13.attention_norms.2.weight": "model-00001-of-00002.safetensors",
174
+ "layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
175
+ "layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
176
+ "layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
177
+ "layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
178
+ "layers.14.attention.k_norm.weight": "model-00001-of-00002.safetensors",
179
+ "layers.14.attention.q_norm.weight": "model-00001-of-00002.safetensors",
180
+ "layers.14.attention.wk.weight": "model-00001-of-00002.safetensors",
181
+ "layers.14.attention.wo.weight": "model-00001-of-00002.safetensors",
182
+ "layers.14.attention.wq.weight": "model-00001-of-00002.safetensors",
183
+ "layers.14.attention.wv.weight": "model-00001-of-00002.safetensors",
184
+ "layers.14.attention_norms.0.weight": "model-00001-of-00002.safetensors",
185
+ "layers.14.attention_norms.1.weight": "model-00001-of-00002.safetensors",
186
+ "layers.14.attention_norms.2.weight": "model-00001-of-00002.safetensors",
187
+ "layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
188
+ "layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
189
+ "layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
190
+ "layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
191
+ "layers.15.attention.k_norm.weight": "model-00001-of-00002.safetensors",
192
+ "layers.15.attention.q_norm.weight": "model-00001-of-00002.safetensors",
193
+ "layers.15.attention.wk.weight": "model-00001-of-00002.safetensors",
194
+ "layers.15.attention.wo.weight": "model-00001-of-00002.safetensors",
195
+ "layers.15.attention.wq.weight": "model-00001-of-00002.safetensors",
196
+ "layers.15.attention.wv.weight": "model-00001-of-00002.safetensors",
197
+ "layers.15.attention_norms.0.weight": "model-00001-of-00002.safetensors",
198
+ "layers.15.attention_norms.1.weight": "model-00001-of-00002.safetensors",
199
+ "layers.15.attention_norms.2.weight": "model-00001-of-00002.safetensors",
200
+ "layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
201
+ "layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
202
+ "layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
203
+ "layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
204
+ "layers.16.attention.k_norm.weight": "model-00001-of-00002.safetensors",
205
+ "layers.16.attention.q_norm.weight": "model-00001-of-00002.safetensors",
206
+ "layers.16.attention.wk.weight": "model-00001-of-00002.safetensors",
207
+ "layers.16.attention.wo.weight": "model-00001-of-00002.safetensors",
208
+ "layers.16.attention.wq.weight": "model-00001-of-00002.safetensors",
209
+ "layers.16.attention.wv.weight": "model-00001-of-00002.safetensors",
210
+ "layers.16.attention_norms.0.weight": "model-00001-of-00002.safetensors",
211
+ "layers.16.attention_norms.1.weight": "model-00001-of-00002.safetensors",
212
+ "layers.16.attention_norms.2.weight": "model-00001-of-00002.safetensors",
213
+ "layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
214
+ "layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
215
+ "layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
216
+ "layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
217
+ "layers.17.attention.k_norm.weight": "model-00001-of-00002.safetensors",
218
+ "layers.17.attention.q_norm.weight": "model-00001-of-00002.safetensors",
219
+ "layers.17.attention.wk.weight": "model-00001-of-00002.safetensors",
220
+ "layers.17.attention.wo.weight": "model-00001-of-00002.safetensors",
221
+ "layers.17.attention.wq.weight": "model-00001-of-00002.safetensors",
222
+ "layers.17.attention.wv.weight": "model-00001-of-00002.safetensors",
223
+ "layers.17.attention_norms.0.weight": "model-00001-of-00002.safetensors",
224
+ "layers.17.attention_norms.1.weight": "model-00001-of-00002.safetensors",
225
+ "layers.17.attention_norms.2.weight": "model-00001-of-00002.safetensors",
226
+ "layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
227
+ "layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
228
+ "layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
229
+ "layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
230
+ "layers.18.attention.k_norm.weight": "model-00001-of-00002.safetensors",
231
+ "layers.18.attention.q_norm.weight": "model-00001-of-00002.safetensors",
232
+ "layers.18.attention.wk.weight": "model-00001-of-00002.safetensors",
233
+ "layers.18.attention.wo.weight": "model-00001-of-00002.safetensors",
234
+ "layers.18.attention.wq.weight": "model-00001-of-00002.safetensors",
235
+ "layers.18.attention.wv.weight": "model-00001-of-00002.safetensors",
236
+ "layers.18.attention_norms.0.weight": "model-00001-of-00002.safetensors",
237
+ "layers.18.attention_norms.1.weight": "model-00001-of-00002.safetensors",
238
+ "layers.18.attention_norms.2.weight": "model-00001-of-00002.safetensors",
239
+ "layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
240
+ "layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
241
+ "layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
242
+ "layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
243
+ "layers.19.attention.k_norm.weight": "model-00001-of-00002.safetensors",
244
+ "layers.19.attention.q_norm.weight": "model-00001-of-00002.safetensors",
245
+ "layers.19.attention.wk.weight": "model-00001-of-00002.safetensors",
246
+ "layers.19.attention.wo.weight": "model-00001-of-00002.safetensors",
247
+ "layers.19.attention.wq.weight": "model-00001-of-00002.safetensors",
248
+ "layers.19.attention.wv.weight": "model-00001-of-00002.safetensors",
249
+ "layers.19.attention_norms.0.weight": "model-00001-of-00002.safetensors",
250
+ "layers.19.attention_norms.1.weight": "model-00001-of-00002.safetensors",
251
+ "layers.19.attention_norms.2.weight": "model-00001-of-00002.safetensors",
252
+ "layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
253
+ "layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
254
+ "layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
255
+ "layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
256
+ "layers.2.attention.k_norm.weight": "model-00001-of-00002.safetensors",
257
+ "layers.2.attention.q_norm.weight": "model-00001-of-00002.safetensors",
258
+ "layers.2.attention.wk.weight": "model-00001-of-00002.safetensors",
259
+ "layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
260
+ "layers.2.attention.wq.weight": "model-00001-of-00002.safetensors",
261
+ "layers.2.attention.wv.weight": "model-00001-of-00002.safetensors",
262
+ "layers.2.attention_norms.0.weight": "model-00001-of-00002.safetensors",
263
+ "layers.2.attention_norms.1.weight": "model-00001-of-00002.safetensors",
264
+ "layers.2.attention_norms.2.weight": "model-00001-of-00002.safetensors",
265
+ "layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
266
+ "layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
267
+ "layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
268
+ "layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
269
+ "layers.20.attention.k_norm.weight": "model-00001-of-00002.safetensors",
270
+ "layers.20.attention.q_norm.weight": "model-00001-of-00002.safetensors",
271
+ "layers.20.attention.wk.weight": "model-00001-of-00002.safetensors",
272
+ "layers.20.attention.wo.weight": "model-00001-of-00002.safetensors",
273
+ "layers.20.attention.wq.weight": "model-00001-of-00002.safetensors",
274
+ "layers.20.attention.wv.weight": "model-00001-of-00002.safetensors",
275
+ "layers.20.attention_norms.0.weight": "model-00001-of-00002.safetensors",
276
+ "layers.20.attention_norms.1.weight": "model-00001-of-00002.safetensors",
277
+ "layers.20.attention_norms.2.weight": "model-00001-of-00002.safetensors",
278
+ "layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
279
+ "layers.20.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
280
+ "layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
281
+ "layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
282
+ "layers.21.attention.k_norm.weight": "model-00001-of-00002.safetensors",
283
+ "layers.21.attention.q_norm.weight": "model-00001-of-00002.safetensors",
284
+ "layers.21.attention.wk.weight": "model-00001-of-00002.safetensors",
285
+ "layers.21.attention.wo.weight": "model-00001-of-00002.safetensors",
286
+ "layers.21.attention.wq.weight": "model-00001-of-00002.safetensors",
287
+ "layers.21.attention.wv.weight": "model-00001-of-00002.safetensors",
288
+ "layers.21.attention_norms.0.weight": "model-00001-of-00002.safetensors",
289
+ "layers.21.attention_norms.1.weight": "model-00001-of-00002.safetensors",
290
+ "layers.21.attention_norms.2.weight": "model-00001-of-00002.safetensors",
291
+ "layers.21.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
292
+ "layers.21.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
293
+ "layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
294
+ "layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
295
+ "layers.22.attention.k_norm.weight": "model-00001-of-00002.safetensors",
296
+ "layers.22.attention.q_norm.weight": "model-00001-of-00002.safetensors",
297
+ "layers.22.attention.wk.weight": "model-00001-of-00002.safetensors",
298
+ "layers.22.attention.wo.weight": "model-00001-of-00002.safetensors",
299
+ "layers.22.attention.wq.weight": "model-00001-of-00002.safetensors",
300
+ "layers.22.attention.wv.weight": "model-00001-of-00002.safetensors",
301
+ "layers.22.attention_norms.0.weight": "model-00001-of-00002.safetensors",
302
+ "layers.22.attention_norms.1.weight": "model-00001-of-00002.safetensors",
303
+ "layers.22.attention_norms.2.weight": "model-00001-of-00002.safetensors",
304
+ "layers.22.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
305
+ "layers.22.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
306
+ "layers.22.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
307
+ "layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
308
+ "layers.23.attention.k_norm.weight": "model-00001-of-00002.safetensors",
309
+ "layers.23.attention.q_norm.weight": "model-00001-of-00002.safetensors",
310
+ "layers.23.attention.wk.weight": "model-00001-of-00002.safetensors",
311
+ "layers.23.attention.wo.weight": "model-00001-of-00002.safetensors",
312
+ "layers.23.attention.wq.weight": "model-00001-of-00002.safetensors",
313
+ "layers.23.attention.wv.weight": "model-00001-of-00002.safetensors",
314
+ "layers.23.attention_norms.0.weight": "model-00001-of-00002.safetensors",
315
+ "layers.23.attention_norms.1.weight": "model-00001-of-00002.safetensors",
316
+ "layers.23.attention_norms.2.weight": "model-00001-of-00002.safetensors",
317
+ "layers.23.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
318
+ "layers.23.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
319
+ "layers.23.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
320
+ "layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
321
+ "layers.24.attention.k_norm.weight": "model-00001-of-00002.safetensors",
322
+ "layers.24.attention.q_norm.weight": "model-00001-of-00002.safetensors",
323
+ "layers.24.attention.wk.weight": "model-00001-of-00002.safetensors",
324
+ "layers.24.attention.wo.weight": "model-00001-of-00002.safetensors",
325
+ "layers.24.attention.wq.weight": "model-00001-of-00002.safetensors",
326
+ "layers.24.attention.wv.weight": "model-00001-of-00002.safetensors",
327
+ "layers.24.attention_norms.0.weight": "model-00001-of-00002.safetensors",
328
+ "layers.24.attention_norms.1.weight": "model-00001-of-00002.safetensors",
329
+ "layers.24.attention_norms.2.weight": "model-00001-of-00002.safetensors",
330
+ "layers.24.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
331
+ "layers.24.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
332
+ "layers.24.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
333
+ "layers.24.ffn_norm.weight": "model-00001-of-00002.safetensors",
334
+ "layers.25.attention.k_norm.weight": "model-00001-of-00002.safetensors",
335
+ "layers.25.attention.q_norm.weight": "model-00001-of-00002.safetensors",
336
+ "layers.25.attention.wk.weight": "model-00001-of-00002.safetensors",
337
+ "layers.25.attention.wo.weight": "model-00001-of-00002.safetensors",
338
+ "layers.25.attention.wq.weight": "model-00001-of-00002.safetensors",
339
+ "layers.25.attention.wv.weight": "model-00001-of-00002.safetensors",
340
+ "layers.25.attention_norms.0.weight": "model-00001-of-00002.safetensors",
341
+ "layers.25.attention_norms.1.weight": "model-00001-of-00002.safetensors",
342
+ "layers.25.attention_norms.2.weight": "model-00001-of-00002.safetensors",
343
+ "layers.25.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
344
+ "layers.25.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
345
+ "layers.25.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
346
+ "layers.25.ffn_norm.weight": "model-00001-of-00002.safetensors",
347
+ "layers.26.attention.k_norm.weight": "model-00001-of-00002.safetensors",
348
+ "layers.26.attention.q_norm.weight": "model-00001-of-00002.safetensors",
349
+ "layers.26.attention.wk.weight": "model-00001-of-00002.safetensors",
350
+ "layers.26.attention.wo.weight": "model-00001-of-00002.safetensors",
351
+ "layers.26.attention.wq.weight": "model-00001-of-00002.safetensors",
352
+ "layers.26.attention.wv.weight": "model-00001-of-00002.safetensors",
353
+ "layers.26.attention_norms.0.weight": "model-00001-of-00002.safetensors",
354
+ "layers.26.attention_norms.1.weight": "model-00001-of-00002.safetensors",
355
+ "layers.26.attention_norms.2.weight": "model-00001-of-00002.safetensors",
356
+ "layers.26.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
357
+ "layers.26.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
358
+ "layers.26.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
359
+ "layers.26.ffn_norm.weight": "model-00001-of-00002.safetensors",
360
+ "layers.27.attention.k_norm.weight": "model-00001-of-00002.safetensors",
361
+ "layers.27.attention.q_norm.weight": "model-00001-of-00002.safetensors",
362
+ "layers.27.attention.wk.weight": "model-00001-of-00002.safetensors",
363
+ "layers.27.attention.wo.weight": "model-00001-of-00002.safetensors",
364
+ "layers.27.attention.wq.weight": "model-00001-of-00002.safetensors",
365
+ "layers.27.attention.wv.weight": "model-00001-of-00002.safetensors",
366
+ "layers.27.attention_norms.0.weight": "model-00001-of-00002.safetensors",
367
+ "layers.27.attention_norms.1.weight": "model-00001-of-00002.safetensors",
368
+ "layers.27.attention_norms.2.weight": "model-00001-of-00002.safetensors",
369
+ "layers.27.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
370
+ "layers.27.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
371
+ "layers.27.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
372
+ "layers.27.ffn_norm.weight": "model-00001-of-00002.safetensors",
373
+ "layers.28.attention.k_norm.weight": "model-00001-of-00002.safetensors",
374
+ "layers.28.attention.q_norm.weight": "model-00001-of-00002.safetensors",
375
+ "layers.28.attention.wk.weight": "model-00001-of-00002.safetensors",
376
+ "layers.28.attention.wo.weight": "model-00001-of-00002.safetensors",
377
+ "layers.28.attention.wq.weight": "model-00001-of-00002.safetensors",
378
+ "layers.28.attention.wv.weight": "model-00001-of-00002.safetensors",
379
+ "layers.28.attention_norms.0.weight": "model-00001-of-00002.safetensors",
380
+ "layers.28.attention_norms.1.weight": "model-00001-of-00002.safetensors",
381
+ "layers.28.attention_norms.2.weight": "model-00001-of-00002.safetensors",
382
+ "layers.28.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
383
+ "layers.28.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
384
+ "layers.28.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
385
+ "layers.28.ffn_norm.weight": "model-00001-of-00002.safetensors",
386
+ "layers.29.attention.k_norm.weight": "model-00001-of-00002.safetensors",
387
+ "layers.29.attention.q_norm.weight": "model-00001-of-00002.safetensors",
388
+ "layers.29.attention.wk.weight": "model-00001-of-00002.safetensors",
389
+ "layers.29.attention.wo.weight": "model-00001-of-00002.safetensors",
390
+ "layers.29.attention.wq.weight": "model-00001-of-00002.safetensors",
391
+ "layers.29.attention.wv.weight": "model-00001-of-00002.safetensors",
392
+ "layers.29.attention_norms.0.weight": "model-00001-of-00002.safetensors",
393
+ "layers.29.attention_norms.1.weight": "model-00001-of-00002.safetensors",
394
+ "layers.29.attention_norms.2.weight": "model-00001-of-00002.safetensors",
395
+ "layers.29.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
396
+ "layers.29.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
397
+ "layers.29.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
398
+ "layers.29.ffn_norm.weight": "model-00001-of-00002.safetensors",
399
+ "layers.3.attention.k_norm.weight": "model-00001-of-00002.safetensors",
400
+ "layers.3.attention.q_norm.weight": "model-00001-of-00002.safetensors",
401
+ "layers.3.attention.wk.weight": "model-00001-of-00002.safetensors",
402
+ "layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
403
+ "layers.3.attention.wq.weight": "model-00001-of-00002.safetensors",
404
+ "layers.3.attention.wv.weight": "model-00001-of-00002.safetensors",
405
+ "layers.3.attention_norms.0.weight": "model-00001-of-00002.safetensors",
406
+ "layers.3.attention_norms.1.weight": "model-00001-of-00002.safetensors",
407
+ "layers.3.attention_norms.2.weight": "model-00001-of-00002.safetensors",
408
+ "layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
409
+ "layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
410
+ "layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
411
+ "layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
412
+ "layers.30.attention.k_norm.weight": "model-00001-of-00002.safetensors",
413
+ "layers.30.attention.q_norm.weight": "model-00001-of-00002.safetensors",
414
+ "layers.30.attention.wk.weight": "model-00001-of-00002.safetensors",
415
+ "layers.30.attention.wo.weight": "model-00001-of-00002.safetensors",
416
+ "layers.30.attention.wq.weight": "model-00001-of-00002.safetensors",
417
+ "layers.30.attention.wv.weight": "model-00001-of-00002.safetensors",
418
+ "layers.30.attention_norms.0.weight": "model-00002-of-00002.safetensors",
419
+ "layers.30.attention_norms.1.weight": "model-00002-of-00002.safetensors",
420
+ "layers.30.attention_norms.2.weight": "model-00002-of-00002.safetensors",
421
+ "layers.30.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
422
+ "layers.30.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
423
+ "layers.30.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
424
+ "layers.30.ffn_norm.weight": "model-00002-of-00002.safetensors",
425
+ "layers.31.attention.k_norm.weight": "model-00002-of-00002.safetensors",
426
+ "layers.31.attention.q_norm.weight": "model-00002-of-00002.safetensors",
427
+ "layers.31.attention.wk.weight": "model-00002-of-00002.safetensors",
428
+ "layers.31.attention.wo.weight": "model-00002-of-00002.safetensors",
429
+ "layers.31.attention.wq.weight": "model-00002-of-00002.safetensors",
430
+ "layers.31.attention.wv.weight": "model-00002-of-00002.safetensors",
431
+ "layers.31.attention_norms.0.weight": "model-00002-of-00002.safetensors",
432
+ "layers.31.attention_norms.1.weight": "model-00002-of-00002.safetensors",
433
+ "layers.31.attention_norms.2.weight": "model-00002-of-00002.safetensors",
434
+ "layers.31.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
435
+ "layers.31.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
436
+ "layers.31.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
437
+ "layers.31.ffn_norm.weight": "model-00002-of-00002.safetensors",
438
+ "layers.4.attention.k_norm.weight": "model-00001-of-00002.safetensors",
439
+ "layers.4.attention.q_norm.weight": "model-00001-of-00002.safetensors",
440
+ "layers.4.attention.wk.weight": "model-00001-of-00002.safetensors",
441
+ "layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
442
+ "layers.4.attention.wq.weight": "model-00001-of-00002.safetensors",
443
+ "layers.4.attention.wv.weight": "model-00001-of-00002.safetensors",
444
+ "layers.4.attention_norms.0.weight": "model-00001-of-00002.safetensors",
445
+ "layers.4.attention_norms.1.weight": "model-00001-of-00002.safetensors",
446
+ "layers.4.attention_norms.2.weight": "model-00001-of-00002.safetensors",
447
+ "layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
448
+ "layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
449
+ "layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
450
+ "layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
451
+ "layers.5.attention.k_norm.weight": "model-00001-of-00002.safetensors",
452
+ "layers.5.attention.q_norm.weight": "model-00001-of-00002.safetensors",
453
+ "layers.5.attention.wk.weight": "model-00001-of-00002.safetensors",
454
+ "layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
455
+ "layers.5.attention.wq.weight": "model-00001-of-00002.safetensors",
456
+ "layers.5.attention.wv.weight": "model-00001-of-00002.safetensors",
457
+ "layers.5.attention_norms.0.weight": "model-00001-of-00002.safetensors",
458
+ "layers.5.attention_norms.1.weight": "model-00001-of-00002.safetensors",
459
+ "layers.5.attention_norms.2.weight": "model-00001-of-00002.safetensors",
460
+ "layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
461
+ "layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
462
+ "layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
463
+ "layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
464
+ "layers.6.attention.k_norm.weight": "model-00001-of-00002.safetensors",
465
+ "layers.6.attention.q_norm.weight": "model-00001-of-00002.safetensors",
466
+ "layers.6.attention.wk.weight": "model-00001-of-00002.safetensors",
467
+ "layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
468
+ "layers.6.attention.wq.weight": "model-00001-of-00002.safetensors",
469
+ "layers.6.attention.wv.weight": "model-00001-of-00002.safetensors",
470
+ "layers.6.attention_norms.0.weight": "model-00001-of-00002.safetensors",
471
+ "layers.6.attention_norms.1.weight": "model-00001-of-00002.safetensors",
472
+ "layers.6.attention_norms.2.weight": "model-00001-of-00002.safetensors",
473
+ "layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
474
+ "layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
475
+ "layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
476
+ "layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
477
+ "layers.7.attention.k_norm.weight": "model-00001-of-00002.safetensors",
478
+ "layers.7.attention.q_norm.weight": "model-00001-of-00002.safetensors",
479
+ "layers.7.attention.wk.weight": "model-00001-of-00002.safetensors",
480
+ "layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
481
+ "layers.7.attention.wq.weight": "model-00001-of-00002.safetensors",
482
+ "layers.7.attention.wv.weight": "model-00001-of-00002.safetensors",
483
+ "layers.7.attention_norms.0.weight": "model-00001-of-00002.safetensors",
484
+ "layers.7.attention_norms.1.weight": "model-00001-of-00002.safetensors",
485
+ "layers.7.attention_norms.2.weight": "model-00001-of-00002.safetensors",
486
+ "layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
487
+ "layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
488
+ "layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
489
+ "layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
490
+ "layers.8.attention.k_norm.weight": "model-00001-of-00002.safetensors",
491
+ "layers.8.attention.q_norm.weight": "model-00001-of-00002.safetensors",
492
+ "layers.8.attention.wk.weight": "model-00001-of-00002.safetensors",
493
+ "layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
494
+ "layers.8.attention.wq.weight": "model-00001-of-00002.safetensors",
495
+ "layers.8.attention.wv.weight": "model-00001-of-00002.safetensors",
496
+ "layers.8.attention_norms.0.weight": "model-00001-of-00002.safetensors",
497
+ "layers.8.attention_norms.1.weight": "model-00001-of-00002.safetensors",
498
+ "layers.8.attention_norms.2.weight": "model-00001-of-00002.safetensors",
499
+ "layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
500
+ "layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
501
+ "layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
502
+ "layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
503
+ "layers.9.attention.k_norm.weight": "model-00001-of-00002.safetensors",
504
+ "layers.9.attention.q_norm.weight": "model-00001-of-00002.safetensors",
505
+ "layers.9.attention.wk.weight": "model-00001-of-00002.safetensors",
506
+ "layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
507
+ "layers.9.attention.wq.weight": "model-00001-of-00002.safetensors",
508
+ "layers.9.attention.wv.weight": "model-00001-of-00002.safetensors",
509
+ "layers.9.attention_norms.0.weight": "model-00001-of-00002.safetensors",
510
+ "layers.9.attention_norms.1.weight": "model-00001-of-00002.safetensors",
511
+ "layers.9.attention_norms.2.weight": "model-00001-of-00002.safetensors",
512
+ "layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
513
+ "layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
514
+ "layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
515
+ "layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
516
+ "norm.weight": "model-00002-of-00002.safetensors",
517
+ "output.weight": "model-00002-of-00002.safetensors",
518
+ "tok_embeddings.weight": "model-00001-of-00002.safetensors"
519
+ }
520
+ }