tahercoolguy commited on
Commit
badab20
1 Parent(s): 9fa3c36
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neox-20b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu_fast",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 6144,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 24576,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "gpt_neox",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 44,
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.25,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.21.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 50432
26
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c91261a976ccb0ca73efe02dd231743c0607ec95de40219748e2055db675ee
3
+ size 9931428677
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1847225abd1013b5fe5cb64bca4a40dd3dcfe7da4643ee516f8255df753890a
3
+ size 9919337667
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91af2dbedfd95f182a85d6a61feab99315423d3efccccaa05007bc0ee9ce2eb6
3
+ size 919298391
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,1027 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 20769950960
4
+ },
5
+ "weight_map": {
6
+ "embed_out.absmax": "pytorch_model-00003-of-00003.bin",
7
+ "embed_out.code": "pytorch_model-00003-of-00003.bin",
8
+ "embed_out.weight": "pytorch_model-00003-of-00003.bin",
9
+ "gpt_neox.embed_in.absmax": "pytorch_model-00001-of-00003.bin",
10
+ "gpt_neox.embed_in.code": "pytorch_model-00001-of-00003.bin",
11
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
12
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
13
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
14
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
15
+ "gpt_neox.layers.0.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
16
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
17
+ "gpt_neox.layers.0.attention.dense.code": "pytorch_model-00001-of-00003.bin",
18
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
19
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
20
+ "gpt_neox.layers.0.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
21
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
22
+ "gpt_neox.layers.0.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
23
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
24
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
25
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
26
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
28
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
29
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
30
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
31
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
32
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
33
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
34
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
35
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
36
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
37
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
38
+ "gpt_neox.layers.1.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
39
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
40
+ "gpt_neox.layers.1.attention.dense.code": "pytorch_model-00001-of-00003.bin",
41
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
42
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
43
+ "gpt_neox.layers.1.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
44
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
45
+ "gpt_neox.layers.1.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
46
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
47
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
48
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
49
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
50
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
51
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
52
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
53
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
54
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
55
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
56
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
57
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
58
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
59
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
60
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
61
+ "gpt_neox.layers.10.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
62
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
63
+ "gpt_neox.layers.10.attention.dense.code": "pytorch_model-00001-of-00003.bin",
64
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
65
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
66
+ "gpt_neox.layers.10.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
67
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
68
+ "gpt_neox.layers.10.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
69
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
70
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
71
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
72
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
74
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
75
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
76
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
77
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
78
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
79
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
80
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
81
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
82
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
83
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
84
+ "gpt_neox.layers.11.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
85
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
86
+ "gpt_neox.layers.11.attention.dense.code": "pytorch_model-00001-of-00003.bin",
87
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
88
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
89
+ "gpt_neox.layers.11.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
90
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
91
+ "gpt_neox.layers.11.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
92
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
93
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
94
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
95
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
96
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
97
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
98
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
99
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
100
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
101
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
102
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
103
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
104
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
105
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
106
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00003.bin",
107
+ "gpt_neox.layers.12.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
108
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
109
+ "gpt_neox.layers.12.attention.dense.code": "pytorch_model-00001-of-00003.bin",
110
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
111
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
112
+ "gpt_neox.layers.12.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
113
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
114
+ "gpt_neox.layers.12.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
115
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
116
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
117
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
118
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
119
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
120
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
121
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
122
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
123
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
124
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
125
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
126
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
127
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
128
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00003.bin",
130
+ "gpt_neox.layers.13.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
131
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
132
+ "gpt_neox.layers.13.attention.dense.code": "pytorch_model-00001-of-00003.bin",
133
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
134
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
135
+ "gpt_neox.layers.13.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
136
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
137
+ "gpt_neox.layers.13.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
138
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
139
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
140
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
141
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
142
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
143
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
144
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
145
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
146
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
147
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
148
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
149
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
150
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
151
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
152
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00003.bin",
153
+ "gpt_neox.layers.14.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
154
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
155
+ "gpt_neox.layers.14.attention.dense.code": "pytorch_model-00001-of-00003.bin",
156
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
157
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
158
+ "gpt_neox.layers.14.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
159
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
160
+ "gpt_neox.layers.14.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
161
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
162
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
163
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
164
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
165
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
166
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
167
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
168
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
169
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
170
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
171
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
172
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
173
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
174
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
175
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00003.bin",
176
+ "gpt_neox.layers.15.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
177
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
178
+ "gpt_neox.layers.15.attention.dense.code": "pytorch_model-00001-of-00003.bin",
179
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
180
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
181
+ "gpt_neox.layers.15.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
182
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
183
+ "gpt_neox.layers.15.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
184
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
185
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
186
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
187
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
188
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
189
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
190
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
191
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
192
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
193
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
194
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
195
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
196
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
197
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
198
+ "gpt_neox.layers.16.attention.bias": "pytorch_model-00001-of-00003.bin",
199
+ "gpt_neox.layers.16.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
200
+ "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
201
+ "gpt_neox.layers.16.attention.dense.code": "pytorch_model-00001-of-00003.bin",
202
+ "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
203
+ "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
204
+ "gpt_neox.layers.16.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
205
+ "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
206
+ "gpt_neox.layers.16.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
207
+ "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
208
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
209
+ "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
210
+ "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
211
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
212
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
213
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
214
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
215
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
216
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
217
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
218
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
219
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
220
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
221
+ "gpt_neox.layers.17.attention.bias": "pytorch_model-00001-of-00003.bin",
222
+ "gpt_neox.layers.17.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
223
+ "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
224
+ "gpt_neox.layers.17.attention.dense.code": "pytorch_model-00001-of-00003.bin",
225
+ "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
226
+ "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
227
+ "gpt_neox.layers.17.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
228
+ "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
229
+ "gpt_neox.layers.17.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
230
+ "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
231
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
232
+ "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
233
+ "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
234
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
235
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
236
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
237
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
238
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
239
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
240
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
241
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
242
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
243
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
244
+ "gpt_neox.layers.18.attention.bias": "pytorch_model-00001-of-00003.bin",
245
+ "gpt_neox.layers.18.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
246
+ "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
247
+ "gpt_neox.layers.18.attention.dense.code": "pytorch_model-00001-of-00003.bin",
248
+ "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
249
+ "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
250
+ "gpt_neox.layers.18.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
251
+ "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
252
+ "gpt_neox.layers.18.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
253
+ "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
254
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
255
+ "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
256
+ "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
257
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
258
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
259
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
260
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
261
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
262
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
263
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
264
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
265
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
266
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
267
+ "gpt_neox.layers.19.attention.bias": "pytorch_model-00001-of-00003.bin",
268
+ "gpt_neox.layers.19.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
269
+ "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
270
+ "gpt_neox.layers.19.attention.dense.code": "pytorch_model-00001-of-00003.bin",
271
+ "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
272
+ "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
273
+ "gpt_neox.layers.19.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
274
+ "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
275
+ "gpt_neox.layers.19.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
276
+ "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
277
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
278
+ "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
279
+ "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
280
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
281
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
282
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
283
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
284
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
285
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
286
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
287
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
288
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
289
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
290
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
291
+ "gpt_neox.layers.2.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
292
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
293
+ "gpt_neox.layers.2.attention.dense.code": "pytorch_model-00001-of-00003.bin",
294
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
295
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
296
+ "gpt_neox.layers.2.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
297
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
298
+ "gpt_neox.layers.2.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
299
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
300
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
301
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
302
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
304
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
305
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
306
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
307
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
308
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
309
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
310
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
311
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
312
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
+ "gpt_neox.layers.20.attention.bias": "pytorch_model-00001-of-00003.bin",
314
+ "gpt_neox.layers.20.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
315
+ "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
316
+ "gpt_neox.layers.20.attention.dense.code": "pytorch_model-00001-of-00003.bin",
317
+ "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
318
+ "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
319
+ "gpt_neox.layers.20.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
320
+ "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
321
+ "gpt_neox.layers.20.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
322
+ "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
323
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
324
+ "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
325
+ "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
326
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
327
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
328
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
329
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
330
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
331
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
332
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
333
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
334
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
335
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
336
+ "gpt_neox.layers.21.attention.bias": "pytorch_model-00001-of-00003.bin",
337
+ "gpt_neox.layers.21.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
338
+ "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
339
+ "gpt_neox.layers.21.attention.dense.code": "pytorch_model-00002-of-00003.bin",
340
+ "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
341
+ "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
342
+ "gpt_neox.layers.21.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
343
+ "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
344
+ "gpt_neox.layers.21.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
345
+ "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
346
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
347
+ "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
348
+ "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
350
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
351
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
352
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
353
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
354
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
355
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
356
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
357
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
358
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
359
+ "gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
360
+ "gpt_neox.layers.22.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
361
+ "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
362
+ "gpt_neox.layers.22.attention.dense.code": "pytorch_model-00002-of-00003.bin",
363
+ "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
364
+ "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
365
+ "gpt_neox.layers.22.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
366
+ "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
367
+ "gpt_neox.layers.22.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
368
+ "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
369
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
370
+ "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
371
+ "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
372
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
373
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
374
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
375
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
376
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
377
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
378
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
379
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
380
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
381
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
382
+ "gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
383
+ "gpt_neox.layers.23.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
384
+ "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
385
+ "gpt_neox.layers.23.attention.dense.code": "pytorch_model-00002-of-00003.bin",
386
+ "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
387
+ "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
388
+ "gpt_neox.layers.23.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
389
+ "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
390
+ "gpt_neox.layers.23.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
391
+ "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
392
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
393
+ "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
394
+ "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
395
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
396
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
397
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
398
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
399
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
400
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
401
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
402
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
403
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
404
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
405
+ "gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00003.bin",
406
+ "gpt_neox.layers.24.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
407
+ "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
408
+ "gpt_neox.layers.24.attention.dense.code": "pytorch_model-00002-of-00003.bin",
409
+ "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
410
+ "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
411
+ "gpt_neox.layers.24.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
412
+ "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
413
+ "gpt_neox.layers.24.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
414
+ "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
415
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
416
+ "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
417
+ "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
418
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
419
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
420
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
421
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
422
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
423
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
424
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
425
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
426
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
427
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
428
+ "gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00003.bin",
429
+ "gpt_neox.layers.25.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
430
+ "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
431
+ "gpt_neox.layers.25.attention.dense.code": "pytorch_model-00002-of-00003.bin",
432
+ "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
433
+ "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
434
+ "gpt_neox.layers.25.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
435
+ "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
436
+ "gpt_neox.layers.25.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
437
+ "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
438
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
439
+ "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
440
+ "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
441
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
442
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
443
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
444
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
445
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
446
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
447
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
448
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
449
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
450
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
451
+ "gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00003.bin",
452
+ "gpt_neox.layers.26.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
453
+ "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
454
+ "gpt_neox.layers.26.attention.dense.code": "pytorch_model-00002-of-00003.bin",
455
+ "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
456
+ "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
457
+ "gpt_neox.layers.26.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
458
+ "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
459
+ "gpt_neox.layers.26.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
460
+ "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
461
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
462
+ "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
463
+ "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
464
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
465
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
466
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
467
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
468
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
469
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
470
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
471
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
472
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
473
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
474
+ "gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00003.bin",
475
+ "gpt_neox.layers.27.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
476
+ "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
477
+ "gpt_neox.layers.27.attention.dense.code": "pytorch_model-00002-of-00003.bin",
478
+ "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
479
+ "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
480
+ "gpt_neox.layers.27.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
481
+ "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
482
+ "gpt_neox.layers.27.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
483
+ "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
484
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
485
+ "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
486
+ "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
487
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
488
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
489
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
490
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
491
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
492
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
493
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
494
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
495
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
496
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
497
+ "gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00003.bin",
498
+ "gpt_neox.layers.28.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
499
+ "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
500
+ "gpt_neox.layers.28.attention.dense.code": "pytorch_model-00002-of-00003.bin",
501
+ "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
502
+ "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
503
+ "gpt_neox.layers.28.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
504
+ "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
505
+ "gpt_neox.layers.28.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
506
+ "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
507
+ "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
508
+ "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
509
+ "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
510
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
511
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
512
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
513
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
514
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
515
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
516
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
517
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
518
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
519
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
520
+ "gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00003.bin",
521
+ "gpt_neox.layers.29.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
522
+ "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
523
+ "gpt_neox.layers.29.attention.dense.code": "pytorch_model-00002-of-00003.bin",
524
+ "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
525
+ "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
526
+ "gpt_neox.layers.29.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
527
+ "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
528
+ "gpt_neox.layers.29.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
529
+ "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
530
+ "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
531
+ "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
532
+ "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
533
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
534
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
535
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
536
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
537
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
538
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
539
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
540
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
541
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
542
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
543
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
544
+ "gpt_neox.layers.3.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
545
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
546
+ "gpt_neox.layers.3.attention.dense.code": "pytorch_model-00001-of-00003.bin",
547
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
548
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
549
+ "gpt_neox.layers.3.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
550
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
551
+ "gpt_neox.layers.3.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
552
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
553
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
554
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
555
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
556
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
557
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
558
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
559
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
560
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
561
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
562
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
563
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
564
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
565
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
566
+ "gpt_neox.layers.30.attention.bias": "pytorch_model-00002-of-00003.bin",
567
+ "gpt_neox.layers.30.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
568
+ "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
569
+ "gpt_neox.layers.30.attention.dense.code": "pytorch_model-00002-of-00003.bin",
570
+ "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
571
+ "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
572
+ "gpt_neox.layers.30.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
573
+ "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
574
+ "gpt_neox.layers.30.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
575
+ "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
576
+ "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
577
+ "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
578
+ "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
579
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
580
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
581
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
582
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
583
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
584
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
585
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
586
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
587
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
588
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
589
+ "gpt_neox.layers.31.attention.bias": "pytorch_model-00002-of-00003.bin",
590
+ "gpt_neox.layers.31.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
591
+ "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
592
+ "gpt_neox.layers.31.attention.dense.code": "pytorch_model-00002-of-00003.bin",
593
+ "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
594
+ "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
595
+ "gpt_neox.layers.31.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
596
+ "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
597
+ "gpt_neox.layers.31.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
598
+ "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
599
+ "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
600
+ "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
601
+ "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
602
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
603
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
604
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
605
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
606
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
607
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
608
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
609
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
610
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
611
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
612
+ "gpt_neox.layers.32.attention.bias": "pytorch_model-00002-of-00003.bin",
613
+ "gpt_neox.layers.32.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
614
+ "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
615
+ "gpt_neox.layers.32.attention.dense.code": "pytorch_model-00002-of-00003.bin",
616
+ "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
617
+ "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
618
+ "gpt_neox.layers.32.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
619
+ "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
620
+ "gpt_neox.layers.32.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
621
+ "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
622
+ "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
623
+ "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
624
+ "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
625
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
626
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
627
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
628
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
629
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
630
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
631
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
632
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
633
+ "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
634
+ "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
635
+ "gpt_neox.layers.33.attention.bias": "pytorch_model-00002-of-00003.bin",
636
+ "gpt_neox.layers.33.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
637
+ "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
638
+ "gpt_neox.layers.33.attention.dense.code": "pytorch_model-00002-of-00003.bin",
639
+ "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
640
+ "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
641
+ "gpt_neox.layers.33.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
642
+ "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
643
+ "gpt_neox.layers.33.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
644
+ "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
645
+ "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
646
+ "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
647
+ "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
648
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
649
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
650
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
651
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
652
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
653
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
654
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
655
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
656
+ "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
657
+ "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
658
+ "gpt_neox.layers.34.attention.bias": "pytorch_model-00002-of-00003.bin",
659
+ "gpt_neox.layers.34.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
660
+ "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
661
+ "gpt_neox.layers.34.attention.dense.code": "pytorch_model-00002-of-00003.bin",
662
+ "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
663
+ "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
664
+ "gpt_neox.layers.34.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
665
+ "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
666
+ "gpt_neox.layers.34.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
667
+ "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
668
+ "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
669
+ "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
670
+ "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
671
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
672
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
673
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
674
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
675
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
676
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
677
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
678
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
679
+ "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
680
+ "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
681
+ "gpt_neox.layers.35.attention.bias": "pytorch_model-00002-of-00003.bin",
682
+ "gpt_neox.layers.35.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
683
+ "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
684
+ "gpt_neox.layers.35.attention.dense.code": "pytorch_model-00002-of-00003.bin",
685
+ "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
686
+ "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
687
+ "gpt_neox.layers.35.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
688
+ "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
689
+ "gpt_neox.layers.35.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
690
+ "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
691
+ "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
692
+ "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
693
+ "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
694
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
695
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
696
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
697
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
698
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
699
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
700
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
701
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
702
+ "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
703
+ "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
704
+ "gpt_neox.layers.36.attention.bias": "pytorch_model-00002-of-00003.bin",
705
+ "gpt_neox.layers.36.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
706
+ "gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
707
+ "gpt_neox.layers.36.attention.dense.code": "pytorch_model-00002-of-00003.bin",
708
+ "gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
709
+ "gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
710
+ "gpt_neox.layers.36.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
711
+ "gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
712
+ "gpt_neox.layers.36.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
713
+ "gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
714
+ "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
715
+ "gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
716
+ "gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
717
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
718
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
719
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
720
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
721
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
722
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
723
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
724
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
725
+ "gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
726
+ "gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
727
+ "gpt_neox.layers.37.attention.bias": "pytorch_model-00002-of-00003.bin",
728
+ "gpt_neox.layers.37.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
729
+ "gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
730
+ "gpt_neox.layers.37.attention.dense.code": "pytorch_model-00002-of-00003.bin",
731
+ "gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
732
+ "gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
733
+ "gpt_neox.layers.37.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
734
+ "gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
735
+ "gpt_neox.layers.37.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
736
+ "gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
737
+ "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
738
+ "gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
739
+ "gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
740
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
741
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
742
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
743
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
744
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
745
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
746
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
747
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
748
+ "gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
749
+ "gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
750
+ "gpt_neox.layers.38.attention.bias": "pytorch_model-00002-of-00003.bin",
751
+ "gpt_neox.layers.38.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
752
+ "gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
753
+ "gpt_neox.layers.38.attention.dense.code": "pytorch_model-00002-of-00003.bin",
754
+ "gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
755
+ "gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
756
+ "gpt_neox.layers.38.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
757
+ "gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
758
+ "gpt_neox.layers.38.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
759
+ "gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
760
+ "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
761
+ "gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
762
+ "gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
763
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
764
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
765
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
766
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
767
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
768
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
769
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
770
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
771
+ "gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
772
+ "gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
773
+ "gpt_neox.layers.39.attention.bias": "pytorch_model-00002-of-00003.bin",
774
+ "gpt_neox.layers.39.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
775
+ "gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
776
+ "gpt_neox.layers.39.attention.dense.code": "pytorch_model-00002-of-00003.bin",
777
+ "gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
778
+ "gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
779
+ "gpt_neox.layers.39.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
780
+ "gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
781
+ "gpt_neox.layers.39.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
782
+ "gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
783
+ "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
784
+ "gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
785
+ "gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
786
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
787
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
788
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
789
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
790
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
791
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
792
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
793
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
794
+ "gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
795
+ "gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
796
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
797
+ "gpt_neox.layers.4.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
798
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
799
+ "gpt_neox.layers.4.attention.dense.code": "pytorch_model-00001-of-00003.bin",
800
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
801
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
802
+ "gpt_neox.layers.4.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
803
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
804
+ "gpt_neox.layers.4.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
805
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
806
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
807
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
808
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
809
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
810
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
811
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
812
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
813
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
814
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
815
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
816
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
817
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
818
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
819
+ "gpt_neox.layers.40.attention.bias": "pytorch_model-00002-of-00003.bin",
820
+ "gpt_neox.layers.40.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
821
+ "gpt_neox.layers.40.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
822
+ "gpt_neox.layers.40.attention.dense.code": "pytorch_model-00002-of-00003.bin",
823
+ "gpt_neox.layers.40.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
824
+ "gpt_neox.layers.40.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
825
+ "gpt_neox.layers.40.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
826
+ "gpt_neox.layers.40.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
827
+ "gpt_neox.layers.40.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
828
+ "gpt_neox.layers.40.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
829
+ "gpt_neox.layers.40.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
830
+ "gpt_neox.layers.40.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
831
+ "gpt_neox.layers.40.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
832
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
833
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
834
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
835
+ "gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
836
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
837
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
838
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
839
+ "gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
840
+ "gpt_neox.layers.40.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
841
+ "gpt_neox.layers.40.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
842
+ "gpt_neox.layers.41.attention.bias": "pytorch_model-00002-of-00003.bin",
843
+ "gpt_neox.layers.41.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
844
+ "gpt_neox.layers.41.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
845
+ "gpt_neox.layers.41.attention.dense.code": "pytorch_model-00002-of-00003.bin",
846
+ "gpt_neox.layers.41.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
847
+ "gpt_neox.layers.41.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
848
+ "gpt_neox.layers.41.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
849
+ "gpt_neox.layers.41.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
850
+ "gpt_neox.layers.41.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
851
+ "gpt_neox.layers.41.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
852
+ "gpt_neox.layers.41.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
853
+ "gpt_neox.layers.41.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
854
+ "gpt_neox.layers.41.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
855
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.absmax": "pytorch_model-00002-of-00003.bin",
856
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
857
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.code": "pytorch_model-00002-of-00003.bin",
858
+ "gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
859
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
860
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
861
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
862
+ "gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
863
+ "gpt_neox.layers.41.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
864
+ "gpt_neox.layers.41.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
865
+ "gpt_neox.layers.42.attention.bias": "pytorch_model-00002-of-00003.bin",
866
+ "gpt_neox.layers.42.attention.dense.absmax": "pytorch_model-00002-of-00003.bin",
867
+ "gpt_neox.layers.42.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
868
+ "gpt_neox.layers.42.attention.dense.code": "pytorch_model-00002-of-00003.bin",
869
+ "gpt_neox.layers.42.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
870
+ "gpt_neox.layers.42.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
871
+ "gpt_neox.layers.42.attention.query_key_value.absmax": "pytorch_model-00002-of-00003.bin",
872
+ "gpt_neox.layers.42.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
873
+ "gpt_neox.layers.42.attention.query_key_value.code": "pytorch_model-00002-of-00003.bin",
874
+ "gpt_neox.layers.42.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
875
+ "gpt_neox.layers.42.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
876
+ "gpt_neox.layers.42.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
877
+ "gpt_neox.layers.42.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
878
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.absmax": "pytorch_model-00003-of-00003.bin",
879
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
880
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.code": "pytorch_model-00003-of-00003.bin",
881
+ "gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
882
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.absmax": "pytorch_model-00002-of-00003.bin",
883
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
884
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.code": "pytorch_model-00002-of-00003.bin",
885
+ "gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
886
+ "gpt_neox.layers.42.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
887
+ "gpt_neox.layers.42.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
888
+ "gpt_neox.layers.43.attention.bias": "pytorch_model-00003-of-00003.bin",
889
+ "gpt_neox.layers.43.attention.dense.absmax": "pytorch_model-00003-of-00003.bin",
890
+ "gpt_neox.layers.43.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
891
+ "gpt_neox.layers.43.attention.dense.code": "pytorch_model-00003-of-00003.bin",
892
+ "gpt_neox.layers.43.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
893
+ "gpt_neox.layers.43.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
894
+ "gpt_neox.layers.43.attention.query_key_value.absmax": "pytorch_model-00003-of-00003.bin",
895
+ "gpt_neox.layers.43.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
896
+ "gpt_neox.layers.43.attention.query_key_value.code": "pytorch_model-00003-of-00003.bin",
897
+ "gpt_neox.layers.43.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
898
+ "gpt_neox.layers.43.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
899
+ "gpt_neox.layers.43.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
900
+ "gpt_neox.layers.43.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
901
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.absmax": "pytorch_model-00003-of-00003.bin",
902
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
903
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.code": "pytorch_model-00003-of-00003.bin",
904
+ "gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
905
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.absmax": "pytorch_model-00003-of-00003.bin",
906
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
907
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.code": "pytorch_model-00003-of-00003.bin",
908
+ "gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
909
+ "gpt_neox.layers.43.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
910
+ "gpt_neox.layers.43.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
911
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
912
+ "gpt_neox.layers.5.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
913
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
914
+ "gpt_neox.layers.5.attention.dense.code": "pytorch_model-00001-of-00003.bin",
915
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
916
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
917
+ "gpt_neox.layers.5.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
918
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
919
+ "gpt_neox.layers.5.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
920
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
921
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
922
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
923
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
924
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
925
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
926
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
927
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
928
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
929
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
930
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
931
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
932
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
933
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
934
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
935
+ "gpt_neox.layers.6.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
936
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
937
+ "gpt_neox.layers.6.attention.dense.code": "pytorch_model-00001-of-00003.bin",
938
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
939
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
940
+ "gpt_neox.layers.6.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
941
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
942
+ "gpt_neox.layers.6.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
943
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
944
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
945
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
946
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
947
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
948
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
949
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
950
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
951
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
952
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
953
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
954
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
955
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
956
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
957
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
958
+ "gpt_neox.layers.7.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
959
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
960
+ "gpt_neox.layers.7.attention.dense.code": "pytorch_model-00001-of-00003.bin",
961
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
962
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
963
+ "gpt_neox.layers.7.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
964
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
965
+ "gpt_neox.layers.7.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
966
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
967
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
968
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
969
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
970
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
971
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
972
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
973
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
974
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
975
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
976
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
977
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
978
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
979
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
980
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
981
+ "gpt_neox.layers.8.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
982
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
983
+ "gpt_neox.layers.8.attention.dense.code": "pytorch_model-00001-of-00003.bin",
984
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
985
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
986
+ "gpt_neox.layers.8.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
987
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
988
+ "gpt_neox.layers.8.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
989
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
990
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
991
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
992
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
993
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
994
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
995
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
996
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
997
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
998
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
999
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
1000
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
1001
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
1002
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
1003
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
1004
+ "gpt_neox.layers.9.attention.dense.absmax": "pytorch_model-00001-of-00003.bin",
1005
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
1006
+ "gpt_neox.layers.9.attention.dense.code": "pytorch_model-00001-of-00003.bin",
1007
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
1008
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
1009
+ "gpt_neox.layers.9.attention.query_key_value.absmax": "pytorch_model-00001-of-00003.bin",
1010
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
1011
+ "gpt_neox.layers.9.attention.query_key_value.code": "pytorch_model-00001-of-00003.bin",
1012
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
1013
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
1014
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
1015
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
1016
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.absmax": "pytorch_model-00001-of-00003.bin",
1017
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
1018
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.code": "pytorch_model-00001-of-00003.bin",
1019
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
1020
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.absmax": "pytorch_model-00001-of-00003.bin",
1021
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
1022
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.code": "pytorch_model-00001-of-00003.bin",
1023
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
1024
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
1025
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
1026
+ }
1027
+ }