Hugging Face's logo

OpenAssistant
/
stablelm-7b-sft-v7-epoch-3

Text Generation
Transformers
PyTorch
English
gpt_neox
sft
Inference Endpoints
text-generation-inference
Model card Files Community
10
dvruette commited on
Commit
d3f40da
•
1 Parent(s): c8aec45

Upload GPTNeoXForCausalLM

Browse files
Files changed (10) hide show
  1. pytorch_model-00001-of-00009.bin +3 -0
  2. pytorch_model-00002-of-00009.bin +3 -0
  3. pytorch_model-00003-of-00009.bin +3 -0
  4. pytorch_model-00004-of-00009.bin +3 -0
  5. pytorch_model-00005-of-00009.bin +3 -0
  6. pytorch_model-00006-of-00009.bin +3 -0
  7. pytorch_model-00007-of-00009.bin +3 -0
  8. pytorch_model-00008-of-00009.bin +3 -0
  9. pytorch_model-00009-of-00009.bin +3 -0
  10. pytorch_model.bin.index.json +244 -244
pytorch_model-00001-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f551ef92f008bcdcbd94289368db87024cbf4d611a29725e52e4d498522fe5
3
+ size 1859720245
pytorch_model-00002-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57c91a0bdf23623a314c1231aeee71002ba013d680ed0f8a497e3eed91e9e18
3
+ size 1845823467
pytorch_model-00003-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ae570934ed7628c7884491c1fff575c300028f0e6f5a2e58d97c23cbf95e0d
3
+ size 1845823467
pytorch_model-00004-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e902a63e05d4aef4877a4771215ca7c11338bda70a91b747cb962c46546be26d
3
+ size 1845823467
pytorch_model-00005-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce421c8c043104b2db1f0abde2431eab38157cbb1e7fb5fd3e6149f22c13095d
3
+ size 1845823467
pytorch_model-00006-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6175459db55cc3b28521cb57410add83e7dec96184e37b1447c0e2c4031b442
3
+ size 1845823467
pytorch_model-00007-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66a89786816afd46f0a1d1ee394af9ff30ed60d3ac9e4eb436c261b8c020eb6
3
+ size 1845823467
pytorch_model-00008-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da6a21f316725a9b36a0bdd145ce509eabff1e97c8d8c6f724705e650ece3d7
3
+ size 1845823467
pytorch_model-00009-of-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa949b42f8d0b77ddc2b8f729a2583b3c33cc67896510082f70f2f4f82ca55d1
3
+ size 1222007504
pytorch_model.bin.index.json CHANGED
@@ -3,249 +3,249 @@
3
  "total_size": 15767528480.0
4
  },
5
  "weight_map": {
6
- "embed_out.weight": "pytorch_model-00002-of-00002.bin",
7
- "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00002.bin",
8
- "gpt_neox.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
9
- "gpt_neox.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
10
- "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00002.bin",
11
- "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
12
- "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
13
- "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
14
- "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
15
- "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
16
- "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
17
- "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
18
- "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
- "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
20
- "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
21
- "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
22
- "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
23
- "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
24
- "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
25
- "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00002.bin",
26
- "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
27
- "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
28
- "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
29
- "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
30
- "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
31
- "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
32
- "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
33
- "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
34
- "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
35
- "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
36
- "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
37
- "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
38
- "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
39
- "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
- "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00002.bin",
41
- "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
42
- "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
43
- "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
44
- "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
45
- "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
46
- "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
47
- "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
48
- "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
- "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
50
- "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
51
- "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
52
- "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
53
- "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
54
- "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
55
- "gpt_neox.layers.11.attention.bias": "pytorch_model-00002-of-00002.bin",
56
- "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
57
- "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
58
- "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
59
- "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
60
- "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
61
- "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
62
- "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
63
- "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
64
- "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
65
- "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
66
- "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
67
- "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
68
- "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
69
- "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
70
- "gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00002.bin",
71
- "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
72
- "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
73
- "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
74
- "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
75
- "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
76
- "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
77
- "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
78
- "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
79
- "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
80
- "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
81
- "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
82
- "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
83
- "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
84
- "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
85
- "gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00002.bin",
86
- "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
87
- "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
88
- "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
89
- "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
90
- "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
91
- "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
92
- "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
93
- "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
94
- "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
95
- "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
96
- "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
97
- "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
98
- "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
99
- "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
100
- "gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00002.bin",
101
- "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
102
- "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
103
- "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
104
- "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
105
- "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
106
- "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
107
- "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
108
- "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
109
- "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
110
- "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
111
- "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
112
- "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
113
- "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
114
- "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
115
- "gpt_neox.layers.15.attention.bias": "pytorch_model-00002-of-00002.bin",
116
- "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
117
- "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
118
- "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
119
- "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
120
- "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
121
- "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
122
- "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
123
- "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
124
- "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
125
- "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
126
- "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
127
- "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
128
- "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
129
- "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
130
- "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00002.bin",
131
- "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
132
- "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
133
- "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
134
- "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
135
- "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
136
- "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
137
- "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
138
- "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
- "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
140
- "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
141
- "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
142
- "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
143
- "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
144
- "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
145
- "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00002.bin",
146
- "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
147
- "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
148
- "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
149
- "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
150
- "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
151
- "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
152
- "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
153
- "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
154
- "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
155
- "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
156
- "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
157
- "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
158
- "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
159
- "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
160
- "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
161
- "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
162
- "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
163
- "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
164
- "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
165
- "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
166
- "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
167
- "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
168
- "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
- "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
170
- "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
171
- "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
172
- "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
173
- "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
174
- "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
175
- "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
176
- "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
177
- "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
178
- "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
179
- "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
180
- "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
181
- "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
182
- "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
183
- "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
184
- "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
185
- "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
186
- "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
187
- "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
188
- "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
189
- "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
190
- "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00002.bin",
191
- "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
192
- "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
193
- "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
194
- "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
195
- "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
196
- "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
197
- "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
198
- "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
199
- "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
200
- "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
201
- "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
202
- "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
203
- "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
204
- "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
205
- "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00002.bin",
206
- "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
207
- "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
208
- "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
209
- "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
210
- "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
211
- "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
212
- "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
213
- "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
214
- "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
215
- "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
216
- "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
217
- "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
218
- "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
219
- "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
220
- "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00002.bin",
221
- "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
222
- "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
223
- "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
224
- "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
225
- "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
226
- "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
227
- "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
228
- "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
229
- "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
230
- "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
231
- "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
232
- "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
233
- "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
234
- "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
235
- "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00002.bin",
236
- "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
237
- "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
238
- "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
239
- "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
240
- "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
241
- "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
242
- "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
243
- "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
244
- "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
245
- "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
246
- "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
247
- "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
248
- "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
249
- "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin"
250
  }
251
  }
 
3
  "total_size": 15767528480.0
4
  },
5
  "weight_map": {
6
+ "embed_out.weight": "pytorch_model-00009-of-00009.bin",
7
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00009.bin",
8
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00009-of-00009.bin",
9
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00009-of-00009.bin",
10
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00009.bin",
11
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
12
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
13
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
25
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00009.bin",
26
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
27
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
28
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
40
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00006-of-00009.bin",
41
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
42
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
43
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
55
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00006-of-00009.bin",
56
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
57
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
58
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
70
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00007-of-00009.bin",
71
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
72
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
73
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
85
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00007-of-00009.bin",
86
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
87
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
88
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
100
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00008-of-00009.bin",
101
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
102
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
103
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
115
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00008-of-00009.bin",
116
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
117
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
118
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
130
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00002-of-00009.bin",
131
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
132
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
133
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
134
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
135
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
136
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
137
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
138
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
139
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
140
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
141
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
142
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
143
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
144
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
145
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00002-of-00009.bin",
146
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
147
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
148
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
149
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
150
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
151
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
152
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
153
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
154
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
155
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
156
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
157
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
158
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
159
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
160
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00003-of-00009.bin",
161
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
162
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
163
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
164
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
165
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
166
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
167
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
168
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
169
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
170
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
171
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
172
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
173
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
174
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
175
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00003-of-00009.bin",
176
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
177
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
178
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
179
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
180
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
181
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
182
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
183
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
184
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
185
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
186
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
187
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
188
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
189
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
190
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00004-of-00009.bin",
191
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
192
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
193
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
194
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
195
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
196
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
197
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
198
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
199
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
200
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
201
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
202
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
203
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
204
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
205
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00004-of-00009.bin",
206
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
207
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
208
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
209
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
210
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
211
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
212
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
213
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
214
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
215
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
216
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
217
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
218
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
219
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
220
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00005-of-00009.bin",
221
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
222
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
223
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
224
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
225
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
226
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
227
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
228
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
229
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
230
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
231
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
232
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
233
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
234
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
235
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00005-of-00009.bin",
236
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
237
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
238
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
239
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
240
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
241
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
242
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
243
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
244
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
245
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
246
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
247
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
248
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
249
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin"
250
  }
251
  }