Hugging Face's logo

stabilityai
/
japanese-stablelm-base-alpha-7b

Text Generation
Transformers
PyTorch
Japanese
japanese-stablelm
causal-lm
custom_code
Model card Files Community
9

Add fp16/int8 weights

#2
by mkshing - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+276
-0
Files changed (4) hide show
  1. pytorch_model.bin.index.fp16.json +267 -0
  2. pytorch_model.fp16-00001-of-00002.bin +3 -0
  3. pytorch_model.fp16-00002-of-00002.bin +3 -0
  4. pytorch_model.int8.bin +3 -0
pytorch_model.bin.index.fp16.json ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14026295296
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "pytorch_model.fp16-00002-of-00002.bin",
7
+ "transformer.embed_in.weight": "pytorch_model.fp16-00001-of-00002.bin",
8
+ "transformer.final_layer_norm.bias": "pytorch_model.fp16-00002-of-00002.bin",
9
+ "transformer.final_layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
10
+ "transformer.layers.0.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
11
+ "transformer.layers.0.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
12
+ "transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
13
+ "transformer.layers.0.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
14
+ "transformer.layers.0.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
15
+ "transformer.layers.0.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
16
+ "transformer.layers.0.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
17
+ "transformer.layers.0.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
18
+ "transformer.layers.1.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
19
+ "transformer.layers.1.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
20
+ "transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
21
+ "transformer.layers.1.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
22
+ "transformer.layers.1.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
23
+ "transformer.layers.1.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
24
+ "transformer.layers.1.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
25
+ "transformer.layers.1.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
26
+ "transformer.layers.10.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
27
+ "transformer.layers.10.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
28
+ "transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
29
+ "transformer.layers.10.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
30
+ "transformer.layers.10.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
31
+ "transformer.layers.10.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
32
+ "transformer.layers.10.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
33
+ "transformer.layers.10.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
34
+ "transformer.layers.11.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
35
+ "transformer.layers.11.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
36
+ "transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
37
+ "transformer.layers.11.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
38
+ "transformer.layers.11.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
39
+ "transformer.layers.11.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
40
+ "transformer.layers.11.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
41
+ "transformer.layers.11.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
42
+ "transformer.layers.12.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
43
+ "transformer.layers.12.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
44
+ "transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
45
+ "transformer.layers.12.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
46
+ "transformer.layers.12.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
47
+ "transformer.layers.12.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
48
+ "transformer.layers.12.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
49
+ "transformer.layers.12.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
50
+ "transformer.layers.13.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
51
+ "transformer.layers.13.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
52
+ "transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
53
+ "transformer.layers.13.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
54
+ "transformer.layers.13.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
55
+ "transformer.layers.13.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
56
+ "transformer.layers.13.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
57
+ "transformer.layers.13.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
58
+ "transformer.layers.14.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
59
+ "transformer.layers.14.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
60
+ "transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
61
+ "transformer.layers.14.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
62
+ "transformer.layers.14.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
63
+ "transformer.layers.14.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
64
+ "transformer.layers.14.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
65
+ "transformer.layers.14.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
66
+ "transformer.layers.15.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
67
+ "transformer.layers.15.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
68
+ "transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
69
+ "transformer.layers.15.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
70
+ "transformer.layers.15.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
71
+ "transformer.layers.15.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
72
+ "transformer.layers.15.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
73
+ "transformer.layers.15.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
74
+ "transformer.layers.16.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
75
+ "transformer.layers.16.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
76
+ "transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
77
+ "transformer.layers.16.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
78
+ "transformer.layers.16.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
79
+ "transformer.layers.16.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
80
+ "transformer.layers.16.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
81
+ "transformer.layers.16.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
82
+ "transformer.layers.17.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
83
+ "transformer.layers.17.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
84
+ "transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
85
+ "transformer.layers.17.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
86
+ "transformer.layers.17.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
87
+ "transformer.layers.17.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
88
+ "transformer.layers.17.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
89
+ "transformer.layers.17.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
90
+ "transformer.layers.18.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
91
+ "transformer.layers.18.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
92
+ "transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
93
+ "transformer.layers.18.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
94
+ "transformer.layers.18.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
95
+ "transformer.layers.18.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
96
+ "transformer.layers.18.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
97
+ "transformer.layers.18.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
98
+ "transformer.layers.19.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
99
+ "transformer.layers.19.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
100
+ "transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
101
+ "transformer.layers.19.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
102
+ "transformer.layers.19.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
103
+ "transformer.layers.19.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
104
+ "transformer.layers.19.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
105
+ "transformer.layers.19.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
106
+ "transformer.layers.2.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
107
+ "transformer.layers.2.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
108
+ "transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
109
+ "transformer.layers.2.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
110
+ "transformer.layers.2.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
111
+ "transformer.layers.2.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
112
+ "transformer.layers.2.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
113
+ "transformer.layers.2.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
114
+ "transformer.layers.20.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
115
+ "transformer.layers.20.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
116
+ "transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
117
+ "transformer.layers.20.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
118
+ "transformer.layers.20.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
119
+ "transformer.layers.20.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
120
+ "transformer.layers.20.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
121
+ "transformer.layers.20.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
122
+ "transformer.layers.21.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
123
+ "transformer.layers.21.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
124
+ "transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
125
+ "transformer.layers.21.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
126
+ "transformer.layers.21.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
127
+ "transformer.layers.21.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
128
+ "transformer.layers.21.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
129
+ "transformer.layers.21.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
130
+ "transformer.layers.22.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
131
+ "transformer.layers.22.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
132
+ "transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
133
+ "transformer.layers.22.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
134
+ "transformer.layers.22.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
135
+ "transformer.layers.22.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
136
+ "transformer.layers.22.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
137
+ "transformer.layers.22.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
138
+ "transformer.layers.23.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
139
+ "transformer.layers.23.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
140
+ "transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
141
+ "transformer.layers.23.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
142
+ "transformer.layers.23.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
143
+ "transformer.layers.23.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
144
+ "transformer.layers.23.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
145
+ "transformer.layers.23.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
146
+ "transformer.layers.24.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
147
+ "transformer.layers.24.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
148
+ "transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
149
+ "transformer.layers.24.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
150
+ "transformer.layers.24.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
151
+ "transformer.layers.24.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
152
+ "transformer.layers.24.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
153
+ "transformer.layers.24.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
154
+ "transformer.layers.25.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
155
+ "transformer.layers.25.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
156
+ "transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
157
+ "transformer.layers.25.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
158
+ "transformer.layers.25.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
159
+ "transformer.layers.25.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
160
+ "transformer.layers.25.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
161
+ "transformer.layers.25.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
162
+ "transformer.layers.26.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
163
+ "transformer.layers.26.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
164
+ "transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
165
+ "transformer.layers.26.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
166
+ "transformer.layers.26.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
167
+ "transformer.layers.26.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
168
+ "transformer.layers.26.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
169
+ "transformer.layers.26.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
170
+ "transformer.layers.27.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
171
+ "transformer.layers.27.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
172
+ "transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
173
+ "transformer.layers.27.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
174
+ "transformer.layers.27.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
175
+ "transformer.layers.27.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
176
+ "transformer.layers.27.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
177
+ "transformer.layers.27.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
178
+ "transformer.layers.28.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
179
+ "transformer.layers.28.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
180
+ "transformer.layers.28.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
181
+ "transformer.layers.28.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
182
+ "transformer.layers.28.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
183
+ "transformer.layers.28.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
184
+ "transformer.layers.28.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
185
+ "transformer.layers.28.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
186
+ "transformer.layers.29.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
187
+ "transformer.layers.29.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
188
+ "transformer.layers.29.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
189
+ "transformer.layers.29.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
190
+ "transformer.layers.29.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
191
+ "transformer.layers.29.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
192
+ "transformer.layers.29.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
193
+ "transformer.layers.29.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
194
+ "transformer.layers.3.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
195
+ "transformer.layers.3.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
196
+ "transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
197
+ "transformer.layers.3.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
198
+ "transformer.layers.3.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
199
+ "transformer.layers.3.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
200
+ "transformer.layers.3.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
201
+ "transformer.layers.3.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
202
+ "transformer.layers.30.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
203
+ "transformer.layers.30.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
204
+ "transformer.layers.30.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
205
+ "transformer.layers.30.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
206
+ "transformer.layers.30.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
207
+ "transformer.layers.30.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
208
+ "transformer.layers.30.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
209
+ "transformer.layers.30.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
210
+ "transformer.layers.31.attention.dense.weight": "pytorch_model.fp16-00002-of-00002.bin",
211
+ "transformer.layers.31.attention.query_key_value.weight": "pytorch_model.fp16-00002-of-00002.bin",
212
+ "transformer.layers.31.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00002-of-00002.bin",
213
+ "transformer.layers.31.attention.rotary_emb.scale": "pytorch_model.fp16-00002-of-00002.bin",
214
+ "transformer.layers.31.mlp.out_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
215
+ "transformer.layers.31.mlp.packed_input_proj.weight": "pytorch_model.fp16-00002-of-00002.bin",
216
+ "transformer.layers.31.post_attention_layernorm.bias": "pytorch_model.fp16-00002-of-00002.bin",
217
+ "transformer.layers.31.post_attention_layernorm.weight": "pytorch_model.fp16-00002-of-00002.bin",
218
+ "transformer.layers.4.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
219
+ "transformer.layers.4.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
220
+ "transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
221
+ "transformer.layers.4.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
222
+ "transformer.layers.4.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
223
+ "transformer.layers.4.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
224
+ "transformer.layers.4.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
225
+ "transformer.layers.4.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
226
+ "transformer.layers.5.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
227
+ "transformer.layers.5.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
228
+ "transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
229
+ "transformer.layers.5.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
230
+ "transformer.layers.5.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
231
+ "transformer.layers.5.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
232
+ "transformer.layers.5.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
233
+ "transformer.layers.5.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
234
+ "transformer.layers.6.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
235
+ "transformer.layers.6.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
236
+ "transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
237
+ "transformer.layers.6.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
238
+ "transformer.layers.6.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
239
+ "transformer.layers.6.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
240
+ "transformer.layers.6.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
241
+ "transformer.layers.6.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
242
+ "transformer.layers.7.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
243
+ "transformer.layers.7.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
244
+ "transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
245
+ "transformer.layers.7.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
246
+ "transformer.layers.7.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
247
+ "transformer.layers.7.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
248
+ "transformer.layers.7.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
249
+ "transformer.layers.7.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
250
+ "transformer.layers.8.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
251
+ "transformer.layers.8.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
252
+ "transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
253
+ "transformer.layers.8.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
254
+ "transformer.layers.8.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
255
+ "transformer.layers.8.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
256
+ "transformer.layers.8.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
257
+ "transformer.layers.8.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin",
258
+ "transformer.layers.9.attention.dense.weight": "pytorch_model.fp16-00001-of-00002.bin",
259
+ "transformer.layers.9.attention.query_key_value.weight": "pytorch_model.fp16-00001-of-00002.bin",
260
+ "transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model.fp16-00001-of-00002.bin",
261
+ "transformer.layers.9.attention.rotary_emb.scale": "pytorch_model.fp16-00001-of-00002.bin",
262
+ "transformer.layers.9.mlp.out_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
263
+ "transformer.layers.9.mlp.packed_input_proj.weight": "pytorch_model.fp16-00001-of-00002.bin",
264
+ "transformer.layers.9.post_attention_layernorm.bias": "pytorch_model.fp16-00001-of-00002.bin",
265
+ "transformer.layers.9.post_attention_layernorm.weight": "pytorch_model.fp16-00001-of-00002.bin"
266
+ }
267
+ }
pytorch_model.fp16-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69cad361b39d014e8ee53a8444b770ee743aa9345f02c4d0a1c8de352cde52ba
3
+ size 9980812437
pytorch_model.fp16-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbd63bd09564d36a89a595088bb08718d4f8073b459e619ac30e3e1fc1f8394
3
+ size 4045578636
pytorch_model.int8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591534362ca69523995b2f6f0bdda4cb5b9be79670259d303de95241281906c2
3
+ size 7555864683