stas commited on
Commit
88d122b
1 Parent(s): 971ef39

Upload GPTNeoXForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-6.9b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.35.2",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 50279
29
+ }
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": "4.35.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c2e5a03548436a78923097297762b1a87ffaf8341af4783f6fcb0cd3d2785c
3
+ size 4976542080
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e660cd22c0f11e7ba4b4bac6079be7b21b394b4a73577ef551aa8e46d22d387
3
+ size 4967384136
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909a9867bc865253b0c96482b4807e134d8265840c772397b336a867cf4e4247
3
+ size 3768217360
model.safetensors.index.json ADDED
@@ -0,0 +1,395 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13712097280
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00003-of-00003.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00003.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00003-of-00003.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00003-of-00003.safetensors",
10
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00003.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
12
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
13
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
14
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
15
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
17
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
18
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
20
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
21
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00003.safetensors",
23
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
24
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
25
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
26
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
27
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
28
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
29
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
30
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
31
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
32
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
33
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
34
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00003.safetensors",
35
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
36
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
37
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
38
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
39
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
41
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
42
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
43
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
44
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
45
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
46
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00003.safetensors",
47
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00003.safetensors",
48
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
49
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
50
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
51
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
52
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
53
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
54
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
55
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
56
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
57
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00003.safetensors",
59
+ "gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00003.safetensors",
60
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
61
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
62
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
63
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
64
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
65
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
66
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
67
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
68
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
69
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
70
+ "gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00003.safetensors",
71
+ "gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00003.safetensors",
72
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
73
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
74
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
75
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
77
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
78
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
79
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
80
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
81
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
82
+ "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00003.safetensors",
83
+ "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
84
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
85
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
86
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
87
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
88
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
89
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
90
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
91
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
92
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
93
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00003.safetensors",
95
+ "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
96
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
97
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
98
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
99
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
100
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
101
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
102
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
103
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
104
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
105
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
106
+ "gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00003.safetensors",
107
+ "gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
108
+ "gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
109
+ "gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
110
+ "gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
111
+ "gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
113
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
114
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
115
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
116
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
117
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
118
+ "gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00003.safetensors",
119
+ "gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
120
+ "gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
121
+ "gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
122
+ "gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
123
+ "gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
124
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
125
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
126
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
127
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
128
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
129
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00003.safetensors",
131
+ "gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
132
+ "gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
133
+ "gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
134
+ "gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
135
+ "gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
136
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
137
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
138
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
139
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
140
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
141
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
142
+ "gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00003.safetensors",
143
+ "gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
144
+ "gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
145
+ "gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
146
+ "gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
147
+ "gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
149
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
150
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
151
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
152
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
153
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
154
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00003.safetensors",
155
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
156
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
157
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
158
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
159
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
160
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
161
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
162
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
163
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
164
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
165
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
166
+ "gpt_neox.layers.20.attention.dense.bias": "model-00002-of-00003.safetensors",
167
+ "gpt_neox.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
168
+ "gpt_neox.layers.20.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
169
+ "gpt_neox.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
170
+ "gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
171
+ "gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
172
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
173
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
174
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
175
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
176
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
177
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
178
+ "gpt_neox.layers.21.attention.dense.bias": "model-00002-of-00003.safetensors",
179
+ "gpt_neox.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
180
+ "gpt_neox.layers.21.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
181
+ "gpt_neox.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
182
+ "gpt_neox.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
183
+ "gpt_neox.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
185
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
186
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
187
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
188
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
189
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
190
+ "gpt_neox.layers.22.attention.dense.bias": "model-00002-of-00003.safetensors",
191
+ "gpt_neox.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
192
+ "gpt_neox.layers.22.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
193
+ "gpt_neox.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
194
+ "gpt_neox.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
195
+ "gpt_neox.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
196
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
197
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
198
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
199
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
200
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
201
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
202
+ "gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00003.safetensors",
203
+ "gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
204
+ "gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
205
+ "gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
206
+ "gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
207
+ "gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
208
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
209
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
210
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
211
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
212
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
213
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
214
+ "gpt_neox.layers.24.attention.dense.bias": "model-00003-of-00003.safetensors",
215
+ "gpt_neox.layers.24.attention.dense.weight": "model-00003-of-00003.safetensors",
216
+ "gpt_neox.layers.24.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
217
+ "gpt_neox.layers.24.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
218
+ "gpt_neox.layers.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
219
+ "gpt_neox.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
220
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
221
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
222
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
223
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
224
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
225
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
226
+ "gpt_neox.layers.25.attention.dense.bias": "model-00003-of-00003.safetensors",
227
+ "gpt_neox.layers.25.attention.dense.weight": "model-00003-of-00003.safetensors",
228
+ "gpt_neox.layers.25.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
229
+ "gpt_neox.layers.25.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
230
+ "gpt_neox.layers.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
231
+ "gpt_neox.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
232
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
233
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
234
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
235
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
236
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
237
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "gpt_neox.layers.26.attention.dense.bias": "model-00003-of-00003.safetensors",
239
+ "gpt_neox.layers.26.attention.dense.weight": "model-00003-of-00003.safetensors",
240
+ "gpt_neox.layers.26.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
241
+ "gpt_neox.layers.26.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
242
+ "gpt_neox.layers.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
243
+ "gpt_neox.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
244
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
245
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
246
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
247
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
248
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
249
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
250
+ "gpt_neox.layers.27.attention.dense.bias": "model-00003-of-00003.safetensors",
251
+ "gpt_neox.layers.27.attention.dense.weight": "model-00003-of-00003.safetensors",
252
+ "gpt_neox.layers.27.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
253
+ "gpt_neox.layers.27.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
254
+ "gpt_neox.layers.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
255
+ "gpt_neox.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
256
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
257
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
258
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
259
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
260
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
261
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
262
+ "gpt_neox.layers.28.attention.dense.bias": "model-00003-of-00003.safetensors",
263
+ "gpt_neox.layers.28.attention.dense.weight": "model-00003-of-00003.safetensors",
264
+ "gpt_neox.layers.28.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
265
+ "gpt_neox.layers.28.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
266
+ "gpt_neox.layers.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
267
+ "gpt_neox.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
268
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
269
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
270
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
271
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
272
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
273
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
274
+ "gpt_neox.layers.29.attention.dense.bias": "model-00003-of-00003.safetensors",
275
+ "gpt_neox.layers.29.attention.dense.weight": "model-00003-of-00003.safetensors",
276
+ "gpt_neox.layers.29.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
277
+ "gpt_neox.layers.29.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
278
+ "gpt_neox.layers.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
279
+ "gpt_neox.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
280
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
281
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
282
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
283
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
284
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
285
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
286
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00003.safetensors",
287
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
288
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
289
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
290
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
291
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
293
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
294
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
295
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
296
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
297
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
298
+ "gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00003.safetensors",
299
+ "gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
300
+ "gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
301
+ "gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
302
+ "gpt_neox.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
303
+ "gpt_neox.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
304
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
305
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
306
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
307
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
308
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
309
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
310
+ "gpt_neox.layers.31.attention.dense.bias": "model-00003-of-00003.safetensors",
311
+ "gpt_neox.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
312
+ "gpt_neox.layers.31.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
313
+ "gpt_neox.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
314
+ "gpt_neox.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
315
+ "gpt_neox.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
316
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
317
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
318
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
319
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
320
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
321
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
322
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00003.safetensors",
323
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
324
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
325
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
326
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
327
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
329
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
330
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
331
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
332
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
333
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
334
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00003.safetensors",
335
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
336
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
337
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
338
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
339
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
340
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
341
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
342
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
343
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
344
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
345
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
346
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00003.safetensors",
347
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
348
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
349
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
350
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
351
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
352
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
353
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
354
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
355
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
356
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
357
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
358
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00003.safetensors",
359
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
360
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
361
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
362
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
363
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
364
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
365
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
366
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
367
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
368
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
369
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
370
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00003.safetensors",
371
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
372
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
373
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
374
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
375
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
376
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
377
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
378
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
379
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
380
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
381
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
382
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00003.safetensors",
383
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
384
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
385
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
386
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
387
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
388
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
389
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
390
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
391
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
392
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
393
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors"
394
+ }
395
+ }