dhigurashi commited on
Commit
36ebac7
1 Parent(s): b0f6037

remove unused weights

Browse files
pytorch_model-00001-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f70a7773f17511aa6dd08f5d2175b4d03dfa6319dd169bba41fe55577666b31
3
- size 9953812631
 
 
 
 
pytorch_model-00002-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1da04d8f13b66bd506926b75ed95f2359c1b365c1147e776eb0bd0278e9938fe
3
- size 9896143321
 
 
 
 
pytorch_model-00003-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:600546291f28e1d6fd77442909ebf30f353c5ad2bbfee887b70ac0c0361aed29
3
- size 6349271849
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,370 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 26199101440
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.layers.0.norm.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.layers.1.norm.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
29
- "model.layers.layers.10.norm.weight": "pytorch_model-00001-of-00003.bin",
30
- "model.layers.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
31
- "model.layers.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
32
- "model.layers.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
33
- "model.layers.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
- "model.layers.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
37
- "model.layers.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.layers.11.norm.weight": "pytorch_model-00001-of-00003.bin",
39
- "model.layers.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
40
- "model.layers.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
41
- "model.layers.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
42
- "model.layers.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
43
- "model.layers.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
- "model.layers.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
45
- "model.layers.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
46
- "model.layers.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
47
- "model.layers.layers.12.norm.weight": "pytorch_model-00001-of-00003.bin",
48
- "model.layers.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
49
- "model.layers.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
50
- "model.layers.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
51
- "model.layers.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
52
- "model.layers.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
53
- "model.layers.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
54
- "model.layers.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
55
- "model.layers.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
56
- "model.layers.layers.13.norm.weight": "pytorch_model-00001-of-00003.bin",
57
- "model.layers.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
58
- "model.layers.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
59
- "model.layers.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
60
- "model.layers.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
61
- "model.layers.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
62
- "model.layers.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
63
- "model.layers.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
64
- "model.layers.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
65
- "model.layers.layers.14.norm.weight": "pytorch_model-00001-of-00003.bin",
66
- "model.layers.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
67
- "model.layers.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
68
- "model.layers.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
69
- "model.layers.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
70
- "model.layers.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
71
- "model.layers.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
72
- "model.layers.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
73
- "model.layers.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
74
- "model.layers.layers.15.norm.weight": "pytorch_model-00002-of-00003.bin",
75
- "model.layers.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
76
- "model.layers.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
77
- "model.layers.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
78
- "model.layers.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
79
- "model.layers.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.layers.16.norm.weight": "pytorch_model-00002-of-00003.bin",
84
- "model.layers.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
86
- "model.layers.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.layers.17.norm.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.layers.18.norm.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.layers.19.norm.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
117
- "model.layers.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
118
- "model.layers.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
119
- "model.layers.layers.2.norm.weight": "pytorch_model-00001-of-00003.bin",
120
- "model.layers.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
121
- "model.layers.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
122
- "model.layers.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
123
- "model.layers.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
124
- "model.layers.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
- "model.layers.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.layers.20.norm.weight": "pytorch_model-00002-of-00003.bin",
129
- "model.layers.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
130
- "model.layers.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
131
- "model.layers.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
132
- "model.layers.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
133
- "model.layers.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
- "model.layers.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
135
- "model.layers.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
136
- "model.layers.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
137
- "model.layers.layers.21.norm.weight": "pytorch_model-00002-of-00003.bin",
138
- "model.layers.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.layers.22.norm.weight": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.layers.23.norm.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
159
- "model.layers.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
160
- "model.layers.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
162
- "model.layers.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
163
- "model.layers.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.layers.24.norm.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
169
- "model.layers.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
- "model.layers.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
171
- "model.layers.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
172
- "model.layers.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
173
- "model.layers.layers.25.norm.weight": "pytorch_model-00002-of-00003.bin",
174
- "model.layers.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
175
- "model.layers.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
176
- "model.layers.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
177
- "model.layers.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
178
- "model.layers.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
179
- "model.layers.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
- "model.layers.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
- "model.layers.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
- "model.layers.layers.26.norm.weight": "pytorch_model-00002-of-00003.bin",
183
- "model.layers.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
- "model.layers.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
- "model.layers.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
- "model.layers.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
- "model.layers.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
- "model.layers.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
189
- "model.layers.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
190
- "model.layers.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
191
- "model.layers.layers.27.norm.weight": "pytorch_model-00002-of-00003.bin",
192
- "model.layers.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
193
- "model.layers.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
194
- "model.layers.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
195
- "model.layers.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
196
- "model.layers.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
197
- "model.layers.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
198
- "model.layers.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
199
- "model.layers.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
200
- "model.layers.layers.28.norm.weight": "pytorch_model-00002-of-00003.bin",
201
- "model.layers.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
202
- "model.layers.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
203
- "model.layers.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
204
- "model.layers.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
205
- "model.layers.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
- "model.layers.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
207
- "model.layers.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
208
- "model.layers.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
209
- "model.layers.layers.29.norm.weight": "pytorch_model-00002-of-00003.bin",
210
- "model.layers.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
211
- "model.layers.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
212
- "model.layers.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
213
- "model.layers.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
214
- "model.layers.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
215
- "model.layers.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
216
- "model.layers.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
217
- "model.layers.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
218
- "model.layers.layers.3.norm.weight": "pytorch_model-00001-of-00003.bin",
219
- "model.layers.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
220
- "model.layers.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
221
- "model.layers.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
222
- "model.layers.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
223
- "model.layers.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
- "model.layers.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
225
- "model.layers.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
226
- "model.layers.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
227
- "model.layers.layers.30.norm.weight": "pytorch_model-00003-of-00003.bin",
228
- "model.layers.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
229
- "model.layers.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
230
- "model.layers.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
231
- "model.layers.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
232
- "model.layers.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
233
- "model.layers.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
234
- "model.layers.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
235
- "model.layers.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
236
- "model.layers.layers.31.norm.weight": "pytorch_model-00003-of-00003.bin",
237
- "model.layers.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
238
- "model.layers.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
239
- "model.layers.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
240
- "model.layers.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
241
- "model.layers.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
- "model.layers.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
243
- "model.layers.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
244
- "model.layers.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
245
- "model.layers.layers.32.norm.weight": "pytorch_model-00003-of-00003.bin",
246
- "model.layers.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
247
- "model.layers.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
248
- "model.layers.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
250
- "model.layers.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
251
- "model.layers.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
252
- "model.layers.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
254
- "model.layers.layers.33.norm.weight": "pytorch_model-00003-of-00003.bin",
255
- "model.layers.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
256
- "model.layers.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
257
- "model.layers.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
258
- "model.layers.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.layers.34.norm.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
269
- "model.layers.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
- "model.layers.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
271
- "model.layers.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
272
- "model.layers.layers.35.norm.weight": "pytorch_model-00003-of-00003.bin",
273
- "model.layers.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
274
- "model.layers.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
275
- "model.layers.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
276
- "model.layers.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
277
- "model.layers.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
- "model.layers.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
279
- "model.layers.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
280
- "model.layers.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
281
- "model.layers.layers.36.norm.weight": "pytorch_model-00003-of-00003.bin",
282
- "model.layers.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
283
- "model.layers.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
284
- "model.layers.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
285
- "model.layers.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
286
- "model.layers.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
287
- "model.layers.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
288
- "model.layers.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
289
- "model.layers.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
290
- "model.layers.layers.37.norm.weight": "pytorch_model-00003-of-00003.bin",
291
- "model.layers.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
292
- "model.layers.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
293
- "model.layers.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
294
- "model.layers.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
295
- "model.layers.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
296
- "model.layers.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
297
- "model.layers.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
298
- "model.layers.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
299
- "model.layers.layers.38.norm.weight": "pytorch_model-00003-of-00003.bin",
300
- "model.layers.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
301
- "model.layers.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
302
- "model.layers.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
303
- "model.layers.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
304
- "model.layers.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
305
- "model.layers.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
306
- "model.layers.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
307
- "model.layers.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
308
- "model.layers.layers.39.norm.weight": "pytorch_model-00003-of-00003.bin",
309
- "model.layers.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
310
- "model.layers.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
311
- "model.layers.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
312
- "model.layers.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
313
- "model.layers.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
314
- "model.layers.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
315
- "model.layers.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
316
- "model.layers.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
317
- "model.layers.layers.4.norm.weight": "pytorch_model-00001-of-00003.bin",
318
- "model.layers.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
319
- "model.layers.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
320
- "model.layers.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
321
- "model.layers.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
322
- "model.layers.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
323
- "model.layers.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
324
- "model.layers.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
325
- "model.layers.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
326
- "model.layers.layers.5.norm.weight": "pytorch_model-00001-of-00003.bin",
327
- "model.layers.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
328
- "model.layers.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
329
- "model.layers.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
330
- "model.layers.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
331
- "model.layers.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
332
- "model.layers.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
333
- "model.layers.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
334
- "model.layers.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
335
- "model.layers.layers.6.norm.weight": "pytorch_model-00001-of-00003.bin",
336
- "model.layers.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
337
- "model.layers.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
338
- "model.layers.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
339
- "model.layers.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
340
- "model.layers.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
341
- "model.layers.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
342
- "model.layers.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
343
- "model.layers.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
344
- "model.layers.layers.7.norm.weight": "pytorch_model-00001-of-00003.bin",
345
- "model.layers.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
346
- "model.layers.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
347
- "model.layers.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
348
- "model.layers.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
349
- "model.layers.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
350
- "model.layers.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
351
- "model.layers.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
352
- "model.layers.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
353
- "model.layers.layers.8.norm.weight": "pytorch_model-00001-of-00003.bin",
354
- "model.layers.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
355
- "model.layers.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
356
- "model.layers.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
357
- "model.layers.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
358
- "model.layers.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
359
- "model.layers.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
360
- "model.layers.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
361
- "model.layers.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
362
- "model.layers.layers.9.norm.weight": "pytorch_model-00001-of-00003.bin",
363
- "model.layers.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
364
- "model.layers.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
365
- "model.layers.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
366
- "model.layers.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
367
- "model.layers.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
369
- }
370
- }