Takeshi Kojima commited on
Commit
0eace9c
1 Parent(s): f3eb622

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForCausalLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "eos_token_id": 0,
7
+ "hidden_act": "gelu",
8
+ "hidden_size": 4864,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 19456,
11
+ "layer_norm_eps": 1e-05,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "gpt_neox",
14
+ "num_attention_heads": 38,
15
+ "num_hidden_layers": 36,
16
+ "rotary_emb_base": 10000,
17
+ "rotary_pct": 0.25,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.28.1",
21
+ "use_cache": true,
22
+ "use_parallel_residual": true,
23
+ "vocab_size": 50304
24
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.28.1"
6
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,551 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 21443102920.0
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "pytorch_model-00003-of-00003.bin",
7
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
8
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
9
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
10
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
11
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
12
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
13
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
25
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
26
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
27
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
28
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
41
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
42
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
43
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
55
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
56
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
57
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
58
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
70
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00003.bin",
71
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
72
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
73
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
85
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00003.bin",
86
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
87
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
88
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
100
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00003.bin",
101
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
102
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
103
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
115
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00003.bin",
116
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
117
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
118
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
130
+ "gpt_neox.layers.16.attention.bias": "pytorch_model-00001-of-00003.bin",
131
+ "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
132
+ "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
133
+ "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
134
+ "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
135
+ "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
136
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
138
+ "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
139
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
140
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
141
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
142
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
143
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
144
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
145
+ "gpt_neox.layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
146
+ "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
147
+ "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
148
+ "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
149
+ "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
150
+ "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
151
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
152
+ "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
153
+ "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
154
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
155
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
156
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
157
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
158
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
159
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
160
+ "gpt_neox.layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
161
+ "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
162
+ "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
163
+ "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
164
+ "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
165
+ "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
166
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
168
+ "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
170
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
171
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
172
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
173
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
174
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "gpt_neox.layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
176
+ "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
177
+ "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
178
+ "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
179
+ "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
180
+ "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
181
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
182
+ "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
183
+ "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
185
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
186
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
187
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
188
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
189
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
190
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
191
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
192
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
193
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
194
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
195
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
196
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
197
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
198
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
199
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
200
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
201
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
202
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
203
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
204
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
205
+ "gpt_neox.layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
206
+ "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
207
+ "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
208
+ "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
209
+ "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
210
+ "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
211
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
212
+ "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
213
+ "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
214
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
215
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
216
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
217
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
218
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
219
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
220
+ "gpt_neox.layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
221
+ "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
222
+ "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
223
+ "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
224
+ "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
225
+ "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
226
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
228
+ "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
230
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
231
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
232
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
233
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
234
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
235
+ "gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
236
+ "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
237
+ "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
238
+ "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
239
+ "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
240
+ "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
241
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
242
+ "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
243
+ "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
244
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
245
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
246
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
247
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
248
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
249
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
250
+ "gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
251
+ "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
252
+ "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
253
+ "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
254
+ "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
255
+ "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
256
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
258
+ "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
259
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
260
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
261
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
262
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
263
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
264
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
265
+ "gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00003.bin",
266
+ "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
267
+ "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
268
+ "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
269
+ "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
270
+ "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
271
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
272
+ "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
273
+ "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
274
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
275
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
276
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
277
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
278
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
279
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
280
+ "gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00003.bin",
281
+ "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
282
+ "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
283
+ "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
284
+ "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
285
+ "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
286
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
287
+ "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
288
+ "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
289
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
290
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
291
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
292
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
293
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
294
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
295
+ "gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00003.bin",
296
+ "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
297
+ "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
298
+ "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
299
+ "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
300
+ "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
301
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
302
+ "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
303
+ "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
304
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
305
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
306
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
307
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
308
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
309
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
310
+ "gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00003.bin",
311
+ "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
312
+ "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
313
+ "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
314
+ "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
315
+ "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
316
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
317
+ "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
318
+ "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
319
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
320
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
321
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
322
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
323
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
324
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
325
+ "gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00003.bin",
326
+ "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
327
+ "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
328
+ "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
329
+ "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
330
+ "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
331
+ "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
332
+ "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
333
+ "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
334
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
335
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
336
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
337
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
338
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
339
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
340
+ "gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00003.bin",
341
+ "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
342
+ "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
343
+ "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
344
+ "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
345
+ "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
346
+ "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
347
+ "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
348
+ "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
349
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
350
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
351
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
352
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
353
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
354
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
355
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
356
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
357
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
358
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
359
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
360
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
361
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
362
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
363
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
365
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
366
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
367
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
368
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
369
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
370
+ "gpt_neox.layers.30.attention.bias": "pytorch_model-00002-of-00003.bin",
371
+ "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
372
+ "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
373
+ "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
374
+ "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
375
+ "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
376
+ "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
377
+ "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
378
+ "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
379
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
380
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
381
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
382
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
383
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
384
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
385
+ "gpt_neox.layers.31.attention.bias": "pytorch_model-00002-of-00003.bin",
386
+ "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
387
+ "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
388
+ "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
389
+ "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
390
+ "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
391
+ "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
392
+ "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
393
+ "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
394
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
395
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
396
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
397
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
398
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
399
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
400
+ "gpt_neox.layers.32.attention.bias": "pytorch_model-00002-of-00003.bin",
401
+ "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
402
+ "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
403
+ "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
404
+ "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
405
+ "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
406
+ "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
407
+ "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
408
+ "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
409
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
410
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
411
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
412
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
413
+ "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
414
+ "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
415
+ "gpt_neox.layers.33.attention.bias": "pytorch_model-00002-of-00003.bin",
416
+ "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
417
+ "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
418
+ "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
419
+ "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
420
+ "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
421
+ "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
422
+ "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
423
+ "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
424
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
425
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
426
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
427
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
428
+ "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
429
+ "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
430
+ "gpt_neox.layers.34.attention.bias": "pytorch_model-00002-of-00003.bin",
431
+ "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
432
+ "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
433
+ "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
434
+ "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
435
+ "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
436
+ "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
437
+ "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
438
+ "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
439
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
440
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
441
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
442
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
443
+ "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
444
+ "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
445
+ "gpt_neox.layers.35.attention.bias": "pytorch_model-00003-of-00003.bin",
446
+ "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
447
+ "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
448
+ "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
449
+ "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
450
+ "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
451
+ "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
452
+ "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
453
+ "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
454
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
455
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
456
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
457
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
458
+ "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
459
+ "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
460
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
461
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
462
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
463
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
464
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
465
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
466
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
467
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
468
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
469
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
470
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
471
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
472
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
473
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
474
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
475
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
476
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
477
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
478
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
479
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
480
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
481
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
482
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
483
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
484
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
485
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
486
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
487
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
488
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
489
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
490
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
491
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
492
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
493
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
494
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
495
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
496
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
497
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
498
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
499
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
500
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
501
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
502
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
503
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
504
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
505
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
506
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
507
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
508
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
509
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
510
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
511
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
512
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
513
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
514
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
515
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
516
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
517
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
518
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
519
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
520
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
521
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
522
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
523
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
524
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
525
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
526
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
527
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
528
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
529
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
530
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
531
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
532
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
533
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
534
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
535
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
536
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
537
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
538
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
539
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
540
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
541
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
542
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
543
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
544
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
545
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
546
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
547
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
548
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
549
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
550
+ }
551
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 1000000000000000019884624838656,
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }