jon-tow commited on
Commit
73bec0e
1 Parent(s): 432f706

Upload GPTNeoXForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/fsx/ckpts/3b_tok=neox_data=pilev2-recontam=p3_lower-code_bs=8m_tp=4_pp=1_init=wang-small-init/global_step84000_hf",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 16384,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "gpt_neox",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 16,
17
+ "rotary_emb_base": 10000,
18
+ "rotary_pct": 0.25,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.27.4",
22
+ "use_cache": true,
23
+ "use_parallel_residual": true,
24
+ "vocab_size": 50688
25
+ }
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": "4.27.4"
6
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c138caae456bc522b525c93401513a5f38f429263b5775e3dec71ef5ada168
3
+ size 10161140290
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fdac4748a4c42a2029f3a6f3f0c7ce41f8eb1faf8331233e2289f96886828f4
3
+ size 4656666941
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14582842432.0
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-00001-of-00002.bin",
42
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-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-00001-of-00002.bin",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-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-00001-of-00002.bin",
56
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
57
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
58
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-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-00001-of-00002.bin",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-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
+ }