Hugging Face's logo

stabilityai
/
stablelm-base-alpha-3b

Text Generation
Transformers
PyTorch
English
gpt_neox
causal-lm
text-generation-inference
Inference Endpoints
Model card Files Community
9

Adding `safetensors` variant of this model

#9
by SFconvertbot - opened
base: refs/heads/main
←
from: refs/pr/9
Discussion Files changed
+257
-0
Files changed (3) hide show
  1. model-00001-of-00002.safetensors +3 -0
  2. model-00002-of-00002.safetensors +3 -0
  3. model.safetensors.index.json +251 -0
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d02bbfc80ad21c6c043e05d8fea315fbb3e5a4c0a4098a837166e9f10e491a6
3
+ size 10161099864
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3e3c6109572ef9bd5156940e3fcedc6ebbc8b8a4baf633e38ea40e802de881
3
+ size 4656652256
model.safetensors.index.json ADDED
@@ -0,0 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14582842432.0
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00002-of-00002.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
10
+ "gpt_neox.layers.0.attention.bias": "model-00001-of-00002.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
12
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
13
+ "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00002.safetensors",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "gpt_neox.layers.1.attention.bias": "model-00001-of-00002.safetensors",
26
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
27
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
28
+ "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00002.safetensors",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "gpt_neox.layers.10.attention.bias": "model-00001-of-00002.safetensors",
41
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
42
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
43
+ "gpt_neox.layers.10.attention.masked_bias": "model-00001-of-00002.safetensors",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "gpt_neox.layers.11.attention.bias": "model-00001-of-00002.safetensors",
56
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
57
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
58
+ "gpt_neox.layers.11.attention.masked_bias": "model-00001-of-00002.safetensors",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "gpt_neox.layers.12.attention.bias": "model-00002-of-00002.safetensors",
71
+ "gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00002.safetensors",
72
+ "gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00002.safetensors",
73
+ "gpt_neox.layers.12.attention.masked_bias": "model-00002-of-00002.safetensors",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00002.safetensors",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
85
+ "gpt_neox.layers.13.attention.bias": "model-00002-of-00002.safetensors",
86
+ "gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00002.safetensors",
87
+ "gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00002.safetensors",
88
+ "gpt_neox.layers.13.attention.masked_bias": "model-00002-of-00002.safetensors",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00002.safetensors",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
100
+ "gpt_neox.layers.14.attention.bias": "model-00002-of-00002.safetensors",
101
+ "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00002.safetensors",
102
+ "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00002.safetensors",
103
+ "gpt_neox.layers.14.attention.masked_bias": "model-00002-of-00002.safetensors",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00002.safetensors",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
115
+ "gpt_neox.layers.15.attention.bias": "model-00002-of-00002.safetensors",
116
+ "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00002.safetensors",
117
+ "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00002.safetensors",
118
+ "gpt_neox.layers.15.attention.masked_bias": "model-00002-of-00002.safetensors",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00002.safetensors",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "gpt_neox.layers.2.attention.bias": "model-00001-of-00002.safetensors",
131
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
132
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
133
+ "gpt_neox.layers.2.attention.masked_bias": "model-00001-of-00002.safetensors",
134
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
135
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
136
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
137
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
138
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
140
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
141
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
142
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
143
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
144
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "gpt_neox.layers.3.attention.bias": "model-00001-of-00002.safetensors",
146
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
147
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
148
+ "gpt_neox.layers.3.attention.masked_bias": "model-00001-of-00002.safetensors",
149
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
150
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
151
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
152
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
153
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
155
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
156
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
157
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
158
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
159
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
160
+ "gpt_neox.layers.4.attention.bias": "model-00001-of-00002.safetensors",
161
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
162
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
163
+ "gpt_neox.layers.4.attention.masked_bias": "model-00001-of-00002.safetensors",
164
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
165
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
166
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
167
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
168
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
170
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
171
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
172
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
173
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
174
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "gpt_neox.layers.5.attention.bias": "model-00001-of-00002.safetensors",
176
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
177
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
178
+ "gpt_neox.layers.5.attention.masked_bias": "model-00001-of-00002.safetensors",
179
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
180
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
181
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
182
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
183
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
185
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
186
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
187
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
188
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
189
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "gpt_neox.layers.6.attention.bias": "model-00001-of-00002.safetensors",
191
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
192
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
193
+ "gpt_neox.layers.6.attention.masked_bias": "model-00001-of-00002.safetensors",
194
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
195
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
196
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
197
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
198
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
200
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
201
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
202
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
203
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
204
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "gpt_neox.layers.7.attention.bias": "model-00001-of-00002.safetensors",
206
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
207
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
208
+ "gpt_neox.layers.7.attention.masked_bias": "model-00001-of-00002.safetensors",
209
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
210
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
211
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
212
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
213
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
215
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
216
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
217
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
218
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
219
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "gpt_neox.layers.8.attention.bias": "model-00001-of-00002.safetensors",
221
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
222
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
223
+ "gpt_neox.layers.8.attention.masked_bias": "model-00001-of-00002.safetensors",
224
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
225
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
226
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
227
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
228
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
230
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
231
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
232
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
233
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
234
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
235
+ "gpt_neox.layers.9.attention.bias": "model-00001-of-00002.safetensors",
236
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
237
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
238
+ "gpt_neox.layers.9.attention.masked_bias": "model-00001-of-00002.safetensors",
239
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
240
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
241
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
242
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
243
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
245
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
246
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
247
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
248
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
249
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
250
+ }
251
+ }