Commit
•
75108ab
1
Parent(s):
664a4a5
Upload GPTNeoXForCausalLM
Browse files- config.json +2 -2
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +389 -389
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -22,7 +22,7 @@
|
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
-
"torch_dtype": "
|
26 |
"transformers_version": "4.37.2",
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./sft-models/pythia-2.8b-multiplication-first-ft/checkpoint-32768",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.37.2",
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c05d9abefc16dc18dd4874abc55c1d1750e98842ab56a2c75c5b88c3e9823ed
|
3 |
+
size 4999731368
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:536705d49c049be5a4308ae9a0324ff0bb38b8c5d7a8437dc0275521c4ebdff3
|
3 |
+
size 4956643296
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2c832995027447ef6704dad1e83d3868725fa2f6c895ea081fe8f0839e4fbeb
|
3 |
+
size 1144507000
|
model.safetensors.index.json
CHANGED
@@ -1,395 +1,395 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
-
"embed_out.weight": "model-
|
7 |
-
"gpt_neox.embed_in.weight": "model-00001-of-
|
8 |
-
"gpt_neox.final_layer_norm.bias": "model-
|
9 |
-
"gpt_neox.final_layer_norm.weight": "model-
|
10 |
-
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-
|
11 |
-
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-
|
12 |
-
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-
|
13 |
-
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-
|
14 |
-
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-
|
15 |
-
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-
|
16 |
-
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-
|
17 |
-
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-
|
18 |
-
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-
|
19 |
-
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-
|
20 |
-
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-
|
21 |
-
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
22 |
-
"gpt_neox.layers.1.attention.dense.bias": "model-00001-of-
|
23 |
-
"gpt_neox.layers.1.attention.dense.weight": "model-00001-of-
|
24 |
-
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-
|
25 |
-
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-
|
26 |
-
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-
|
27 |
-
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-
|
28 |
-
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-
|
29 |
-
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-
|
30 |
-
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-
|
31 |
-
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-
|
32 |
-
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-
|
33 |
-
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
34 |
-
"gpt_neox.layers.10.attention.dense.bias": "model-00001-of-
|
35 |
-
"gpt_neox.layers.10.attention.dense.weight": "model-00001-of-
|
36 |
-
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-
|
37 |
-
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-
|
38 |
-
"gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-
|
39 |
-
"gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-
|
40 |
-
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-
|
41 |
-
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-
|
42 |
-
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-
|
43 |
-
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-
|
44 |
-
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-
|
45 |
-
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-
|
46 |
-
"gpt_neox.layers.11.attention.dense.bias": "model-00001-of-
|
47 |
-
"gpt_neox.layers.11.attention.dense.weight": "model-00001-of-
|
48 |
-
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-
|
49 |
-
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-
|
50 |
-
"gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-
|
51 |
-
"gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-
|
52 |
-
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-
|
53 |
-
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-
|
54 |
-
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-
|
55 |
-
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-
|
56 |
-
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-
|
57 |
-
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-
|
58 |
-
"gpt_neox.layers.12.attention.dense.bias": "model-00001-of-
|
59 |
-
"gpt_neox.layers.12.attention.dense.weight": "model-00001-of-
|
60 |
-
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-
|
61 |
-
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-
|
62 |
-
"gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-
|
63 |
-
"gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-
|
64 |
-
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-
|
65 |
-
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-
|
66 |
-
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-
|
67 |
-
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-
|
68 |
-
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-
|
69 |
-
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-
|
70 |
-
"gpt_neox.layers.13.attention.dense.bias": "model-00001-of-
|
71 |
-
"gpt_neox.layers.13.attention.dense.weight": "model-00001-of-
|
72 |
-
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-
|
73 |
-
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-
|
74 |
-
"gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-
|
75 |
-
"gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-
|
76 |
-
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-
|
77 |
-
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-
|
78 |
-
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-
|
79 |
-
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-
|
80 |
-
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-
|
81 |
-
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-
|
82 |
-
"gpt_neox.layers.14.attention.dense.bias": "model-
|
83 |
-
"gpt_neox.layers.14.attention.dense.weight": "model-
|
84 |
-
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-
|
85 |
-
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-
|
86 |
-
"gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-
|
87 |
-
"gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-
|
88 |
-
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-
|
89 |
-
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-
|
90 |
-
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-
|
91 |
-
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-
|
92 |
-
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-
|
93 |
-
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-
|
94 |
-
"gpt_neox.layers.15.attention.dense.bias": "model-
|
95 |
-
"gpt_neox.layers.15.attention.dense.weight": "model-
|
96 |
-
"gpt_neox.layers.15.attention.query_key_value.bias": "model-
|
97 |
-
"gpt_neox.layers.15.attention.query_key_value.weight": "model-
|
98 |
-
"gpt_neox.layers.15.input_layernorm.bias": "model-
|
99 |
-
"gpt_neox.layers.15.input_layernorm.weight": "model-
|
100 |
-
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-
|
101 |
-
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-
|
102 |
-
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-
|
103 |
-
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-
|
104 |
-
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-
|
105 |
-
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-
|
106 |
-
"gpt_neox.layers.16.attention.dense.bias": "model-
|
107 |
-
"gpt_neox.layers.16.attention.dense.weight": "model-
|
108 |
-
"gpt_neox.layers.16.attention.query_key_value.bias": "model-
|
109 |
-
"gpt_neox.layers.16.attention.query_key_value.weight": "model-
|
110 |
-
"gpt_neox.layers.16.input_layernorm.bias": "model-
|
111 |
-
"gpt_neox.layers.16.input_layernorm.weight": "model-
|
112 |
-
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-
|
113 |
-
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-
|
114 |
-
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-
|
115 |
-
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-
|
116 |
-
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-
|
117 |
-
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-
|
118 |
-
"gpt_neox.layers.17.attention.dense.bias": "model-
|
119 |
-
"gpt_neox.layers.17.attention.dense.weight": "model-
|
120 |
-
"gpt_neox.layers.17.attention.query_key_value.bias": "model-
|
121 |
-
"gpt_neox.layers.17.attention.query_key_value.weight": "model-
|
122 |
-
"gpt_neox.layers.17.input_layernorm.bias": "model-
|
123 |
-
"gpt_neox.layers.17.input_layernorm.weight": "model-
|
124 |
-
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-
|
125 |
-
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-
|
126 |
-
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-
|
127 |
-
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-
|
128 |
-
"gpt_neox.layers.17.post_attention_layernorm.bias": "model-
|
129 |
-
"gpt_neox.layers.17.post_attention_layernorm.weight": "model-
|
130 |
-
"gpt_neox.layers.18.attention.dense.bias": "model-
|
131 |
-
"gpt_neox.layers.18.attention.dense.weight": "model-
|
132 |
-
"gpt_neox.layers.18.attention.query_key_value.bias": "model-
|
133 |
-
"gpt_neox.layers.18.attention.query_key_value.weight": "model-
|
134 |
-
"gpt_neox.layers.18.input_layernorm.bias": "model-
|
135 |
-
"gpt_neox.layers.18.input_layernorm.weight": "model-
|
136 |
-
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-
|
137 |
-
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-
|
138 |
-
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-
|
139 |
-
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-
|
140 |
-
"gpt_neox.layers.18.post_attention_layernorm.bias": "model-
|
141 |
-
"gpt_neox.layers.18.post_attention_layernorm.weight": "model-
|
142 |
-
"gpt_neox.layers.19.attention.dense.bias": "model-
|
143 |
-
"gpt_neox.layers.19.attention.dense.weight": "model-
|
144 |
-
"gpt_neox.layers.19.attention.query_key_value.bias": "model-
|
145 |
-
"gpt_neox.layers.19.attention.query_key_value.weight": "model-
|
146 |
-
"gpt_neox.layers.19.input_layernorm.bias": "model-
|
147 |
-
"gpt_neox.layers.19.input_layernorm.weight": "model-
|
148 |
-
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-
|
149 |
-
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-
|
150 |
-
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-
|
151 |
-
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-
|
152 |
-
"gpt_neox.layers.19.post_attention_layernorm.bias": "model-
|
153 |
-
"gpt_neox.layers.19.post_attention_layernorm.weight": "model-
|
154 |
-
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-
|
155 |
-
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-
|
156 |
-
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-
|
157 |
-
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-
|
158 |
-
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-
|
159 |
-
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-
|
160 |
-
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-
|
161 |
-
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-
|
162 |
-
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-
|
163 |
-
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-
|
164 |
-
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-
|
165 |
-
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
166 |
-
"gpt_neox.layers.20.attention.dense.bias": "model-
|
167 |
-
"gpt_neox.layers.20.attention.dense.weight": "model-
|
168 |
-
"gpt_neox.layers.20.attention.query_key_value.bias": "model-
|
169 |
-
"gpt_neox.layers.20.attention.query_key_value.weight": "model-
|
170 |
-
"gpt_neox.layers.20.input_layernorm.bias": "model-
|
171 |
-
"gpt_neox.layers.20.input_layernorm.weight": "model-
|
172 |
-
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-
|
173 |
-
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-
|
174 |
-
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-
|
175 |
-
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-
|
176 |
-
"gpt_neox.layers.20.post_attention_layernorm.bias": "model-
|
177 |
-
"gpt_neox.layers.20.post_attention_layernorm.weight": "model-
|
178 |
-
"gpt_neox.layers.21.attention.dense.bias": "model-
|
179 |
-
"gpt_neox.layers.21.attention.dense.weight": "model-
|
180 |
-
"gpt_neox.layers.21.attention.query_key_value.bias": "model-
|
181 |
-
"gpt_neox.layers.21.attention.query_key_value.weight": "model-
|
182 |
-
"gpt_neox.layers.21.input_layernorm.bias": "model-
|
183 |
-
"gpt_neox.layers.21.input_layernorm.weight": "model-
|
184 |
-
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-
|
185 |
-
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-
|
186 |
-
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-
|
187 |
-
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-
|
188 |
-
"gpt_neox.layers.21.post_attention_layernorm.bias": "model-
|
189 |
-
"gpt_neox.layers.21.post_attention_layernorm.weight": "model-
|
190 |
-
"gpt_neox.layers.22.attention.dense.bias": "model-
|
191 |
-
"gpt_neox.layers.22.attention.dense.weight": "model-
|
192 |
-
"gpt_neox.layers.22.attention.query_key_value.bias": "model-
|
193 |
-
"gpt_neox.layers.22.attention.query_key_value.weight": "model-
|
194 |
-
"gpt_neox.layers.22.input_layernorm.bias": "model-
|
195 |
-
"gpt_neox.layers.22.input_layernorm.weight": "model-
|
196 |
-
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-
|
197 |
-
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-
|
198 |
-
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-
|
199 |
-
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-
|
200 |
-
"gpt_neox.layers.22.post_attention_layernorm.bias": "model-
|
201 |
-
"gpt_neox.layers.22.post_attention_layernorm.weight": "model-
|
202 |
-
"gpt_neox.layers.23.attention.dense.bias": "model-
|
203 |
-
"gpt_neox.layers.23.attention.dense.weight": "model-
|
204 |
-
"gpt_neox.layers.23.attention.query_key_value.bias": "model-
|
205 |
-
"gpt_neox.layers.23.attention.query_key_value.weight": "model-
|
206 |
-
"gpt_neox.layers.23.input_layernorm.bias": "model-
|
207 |
-
"gpt_neox.layers.23.input_layernorm.weight": "model-
|
208 |
-
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-
|
209 |
-
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-
|
210 |
-
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-
|
211 |
-
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-
|
212 |
-
"gpt_neox.layers.23.post_attention_layernorm.bias": "model-
|
213 |
-
"gpt_neox.layers.23.post_attention_layernorm.weight": "model-
|
214 |
-
"gpt_neox.layers.24.attention.dense.bias": "model-
|
215 |
-
"gpt_neox.layers.24.attention.dense.weight": "model-
|
216 |
-
"gpt_neox.layers.24.attention.query_key_value.bias": "model-
|
217 |
-
"gpt_neox.layers.24.attention.query_key_value.weight": "model-
|
218 |
-
"gpt_neox.layers.24.input_layernorm.bias": "model-
|
219 |
-
"gpt_neox.layers.24.input_layernorm.weight": "model-
|
220 |
-
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-
|
221 |
-
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-
|
222 |
-
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-
|
223 |
-
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-
|
224 |
-
"gpt_neox.layers.24.post_attention_layernorm.bias": "model-
|
225 |
-
"gpt_neox.layers.24.post_attention_layernorm.weight": "model-
|
226 |
-
"gpt_neox.layers.25.attention.dense.bias": "model-
|
227 |
-
"gpt_neox.layers.25.attention.dense.weight": "model-
|
228 |
-
"gpt_neox.layers.25.attention.query_key_value.bias": "model-
|
229 |
-
"gpt_neox.layers.25.attention.query_key_value.weight": "model-
|
230 |
-
"gpt_neox.layers.25.input_layernorm.bias": "model-
|
231 |
-
"gpt_neox.layers.25.input_layernorm.weight": "model-
|
232 |
-
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-
|
233 |
-
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-
|
234 |
-
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-
|
235 |
-
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-
|
236 |
-
"gpt_neox.layers.25.post_attention_layernorm.bias": "model-
|
237 |
-
"gpt_neox.layers.25.post_attention_layernorm.weight": "model-
|
238 |
-
"gpt_neox.layers.26.attention.dense.bias": "model-
|
239 |
-
"gpt_neox.layers.26.attention.dense.weight": "model-
|
240 |
-
"gpt_neox.layers.26.attention.query_key_value.bias": "model-
|
241 |
-
"gpt_neox.layers.26.attention.query_key_value.weight": "model-
|
242 |
-
"gpt_neox.layers.26.input_layernorm.bias": "model-
|
243 |
-
"gpt_neox.layers.26.input_layernorm.weight": "model-
|
244 |
-
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-
|
245 |
-
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-
|
246 |
-
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-
|
247 |
-
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-
|
248 |
-
"gpt_neox.layers.26.post_attention_layernorm.bias": "model-
|
249 |
-
"gpt_neox.layers.26.post_attention_layernorm.weight": "model-
|
250 |
-
"gpt_neox.layers.27.attention.dense.bias": "model-
|
251 |
-
"gpt_neox.layers.27.attention.dense.weight": "model-
|
252 |
-
"gpt_neox.layers.27.attention.query_key_value.bias": "model-
|
253 |
-
"gpt_neox.layers.27.attention.query_key_value.weight": "model-
|
254 |
-
"gpt_neox.layers.27.input_layernorm.bias": "model-
|
255 |
-
"gpt_neox.layers.27.input_layernorm.weight": "model-
|
256 |
-
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-
|
257 |
-
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-
|
258 |
-
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-
|
259 |
-
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-
|
260 |
-
"gpt_neox.layers.27.post_attention_layernorm.bias": "model-
|
261 |
-
"gpt_neox.layers.27.post_attention_layernorm.weight": "model-
|
262 |
-
"gpt_neox.layers.28.attention.dense.bias": "model-
|
263 |
-
"gpt_neox.layers.28.attention.dense.weight": "model-
|
264 |
-
"gpt_neox.layers.28.attention.query_key_value.bias": "model-
|
265 |
-
"gpt_neox.layers.28.attention.query_key_value.weight": "model-
|
266 |
-
"gpt_neox.layers.28.input_layernorm.bias": "model-
|
267 |
-
"gpt_neox.layers.28.input_layernorm.weight": "model-
|
268 |
-
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-
|
269 |
-
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-
|
270 |
-
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-
|
271 |
-
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-
|
272 |
-
"gpt_neox.layers.28.post_attention_layernorm.bias": "model-
|
273 |
-
"gpt_neox.layers.28.post_attention_layernorm.weight": "model-
|
274 |
-
"gpt_neox.layers.29.attention.dense.bias": "model-
|
275 |
-
"gpt_neox.layers.29.attention.dense.weight": "model-
|
276 |
-
"gpt_neox.layers.29.attention.query_key_value.bias": "model-
|
277 |
-
"gpt_neox.layers.29.attention.query_key_value.weight": "model-
|
278 |
-
"gpt_neox.layers.29.input_layernorm.bias": "model-
|
279 |
-
"gpt_neox.layers.29.input_layernorm.weight": "model-
|
280 |
-
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-
|
281 |
-
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-
|
282 |
-
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-
|
283 |
-
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-
|
284 |
-
"gpt_neox.layers.29.post_attention_layernorm.bias": "model-
|
285 |
-
"gpt_neox.layers.29.post_attention_layernorm.weight": "model-
|
286 |
-
"gpt_neox.layers.3.attention.dense.bias": "model-00001-of-
|
287 |
-
"gpt_neox.layers.3.attention.dense.weight": "model-00001-of-
|
288 |
-
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-
|
289 |
-
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-
|
290 |
-
"gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-
|
291 |
-
"gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-
|
292 |
-
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-
|
293 |
-
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-
|
294 |
-
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-
|
295 |
-
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-
|
296 |
-
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-
|
297 |
-
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
298 |
-
"gpt_neox.layers.30.attention.dense.bias": "model-
|
299 |
-
"gpt_neox.layers.30.attention.dense.weight": "model-
|
300 |
-
"gpt_neox.layers.30.attention.query_key_value.bias": "model-
|
301 |
-
"gpt_neox.layers.30.attention.query_key_value.weight": "model-
|
302 |
-
"gpt_neox.layers.30.input_layernorm.bias": "model-
|
303 |
-
"gpt_neox.layers.30.input_layernorm.weight": "model-
|
304 |
-
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-
|
305 |
-
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-
|
306 |
-
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-
|
307 |
-
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-
|
308 |
-
"gpt_neox.layers.30.post_attention_layernorm.bias": "model-
|
309 |
-
"gpt_neox.layers.30.post_attention_layernorm.weight": "model-
|
310 |
-
"gpt_neox.layers.31.attention.dense.bias": "model-
|
311 |
-
"gpt_neox.layers.31.attention.dense.weight": "model-
|
312 |
-
"gpt_neox.layers.31.attention.query_key_value.bias": "model-
|
313 |
-
"gpt_neox.layers.31.attention.query_key_value.weight": "model-
|
314 |
-
"gpt_neox.layers.31.input_layernorm.bias": "model-
|
315 |
-
"gpt_neox.layers.31.input_layernorm.weight": "model-
|
316 |
-
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-
|
317 |
-
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-
|
318 |
-
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-
|
319 |
-
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-
|
320 |
-
"gpt_neox.layers.31.post_attention_layernorm.bias": "model-
|
321 |
-
"gpt_neox.layers.31.post_attention_layernorm.weight": "model-
|
322 |
-
"gpt_neox.layers.4.attention.dense.bias": "model-00001-of-
|
323 |
-
"gpt_neox.layers.4.attention.dense.weight": "model-00001-of-
|
324 |
-
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-
|
325 |
-
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-
|
326 |
-
"gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-
|
327 |
-
"gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-
|
328 |
-
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-
|
329 |
-
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-
|
330 |
-
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-
|
331 |
-
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-
|
332 |
-
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-
|
333 |
-
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-
|
334 |
-
"gpt_neox.layers.5.attention.dense.bias": "model-00001-of-
|
335 |
-
"gpt_neox.layers.5.attention.dense.weight": "model-00001-of-
|
336 |
-
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-
|
337 |
-
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-
|
338 |
-
"gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-
|
339 |
-
"gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-
|
340 |
-
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-
|
341 |
-
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-
|
342 |
-
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-
|
343 |
-
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-
|
344 |
-
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-
|
345 |
-
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-
|
346 |
-
"gpt_neox.layers.6.attention.dense.bias": "model-00001-of-
|
347 |
-
"gpt_neox.layers.6.attention.dense.weight": "model-00001-of-
|
348 |
-
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-
|
349 |
-
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-
|
350 |
-
"gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-
|
351 |
-
"gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-
|
352 |
-
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-
|
353 |
-
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-
|
354 |
-
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-
|
355 |
-
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-
|
356 |
-
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-
|
357 |
-
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-
|
358 |
-
"gpt_neox.layers.7.attention.dense.bias": "model-00001-of-
|
359 |
-
"gpt_neox.layers.7.attention.dense.weight": "model-00001-of-
|
360 |
-
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-
|
361 |
-
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-
|
362 |
-
"gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-
|
363 |
-
"gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-
|
364 |
-
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-
|
365 |
-
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-
|
366 |
-
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-
|
367 |
-
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-
|
368 |
-
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-
|
369 |
-
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-
|
370 |
-
"gpt_neox.layers.8.attention.dense.bias": "model-00001-of-
|
371 |
-
"gpt_neox.layers.8.attention.dense.weight": "model-00001-of-
|
372 |
-
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-
|
373 |
-
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-
|
374 |
-
"gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-
|
375 |
-
"gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-
|
376 |
-
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-
|
377 |
-
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-
|
378 |
-
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-
|
379 |
-
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-
|
380 |
-
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-
|
381 |
-
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-
|
382 |
-
"gpt_neox.layers.9.attention.dense.bias": "model-00001-of-
|
383 |
-
"gpt_neox.layers.9.attention.dense.weight": "model-00001-of-
|
384 |
-
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-
|
385 |
-
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-
|
386 |
-
"gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-
|
387 |
-
"gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-
|
388 |
-
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-
|
389 |
-
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-
|
390 |
-
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-
|
391 |
-
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-
|
392 |
-
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-
|
393 |
-
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-
|
394 |
}
|
395 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 11100835840
|
4 |
},
|
5 |
"weight_map": {
|
6 |
+
"embed_out.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"gpt_neox.embed_in.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"gpt_neox.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
9 |
+
"gpt_neox.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
10 |
+
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00003.safetensors",
|
11 |
+
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
13 |
+
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
15 |
+
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
17 |
+
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
19 |
+
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
21 |
+
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00003.safetensors",
|
23 |
+
"gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
25 |
+
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
27 |
+
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
28 |
+
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
29 |
+
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
31 |
+
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
33 |
+
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00003.safetensors",
|
35 |
+
"gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
|
36 |
+
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
37 |
+
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
38 |
+
"gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
39 |
+
"gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
40 |
+
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
41 |
+
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
42 |
+
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
43 |
+
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
44 |
+
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
45 |
+
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
46 |
+
"gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00003.safetensors",
|
47 |
+
"gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00003.safetensors",
|
48 |
+
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
49 |
+
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
50 |
+
"gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
51 |
+
"gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
52 |
+
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
53 |
+
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
54 |
+
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
55 |
+
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
56 |
+
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
57 |
+
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
58 |
+
"gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00003.safetensors",
|
59 |
+
"gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00003.safetensors",
|
60 |
+
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
61 |
+
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
62 |
+
"gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
63 |
+
"gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
64 |
+
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
65 |
+
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
66 |
+
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
67 |
+
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
68 |
+
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
69 |
+
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
70 |
+
"gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00003.safetensors",
|
71 |
+
"gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00003.safetensors",
|
72 |
+
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
73 |
+
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
74 |
+
"gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
75 |
+
"gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
76 |
+
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
77 |
+
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
78 |
+
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
79 |
+
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
80 |
+
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
81 |
+
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
82 |
+
"gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00003.safetensors",
|
83 |
+
"gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
85 |
+
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
86 |
+
"gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
87 |
+
"gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
88 |
+
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
89 |
+
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
91 |
+
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
93 |
+
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
94 |
+
"gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00003.safetensors",
|
95 |
+
"gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
97 |
+
"gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
99 |
+
"gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
101 |
+
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
103 |
+
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
105 |
+
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00003.safetensors",
|
107 |
+
"gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
109 |
+
"gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
111 |
+
"gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
113 |
+
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
115 |
+
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
117 |
+
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
118 |
+
"gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00003.safetensors",
|
119 |
+
"gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
|
120 |
+
"gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
121 |
+
"gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
122 |
+
"gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
123 |
+
"gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
124 |
+
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
125 |
+
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
127 |
+
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
129 |
+
"gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00003.safetensors",
|
131 |
+
"gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
133 |
+
"gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
135 |
+
"gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
137 |
+
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
139 |
+
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
141 |
+
"gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00003.safetensors",
|
143 |
+
"gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
|
144 |
+
"gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
145 |
+
"gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
146 |
+
"gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
147 |
+
"gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
148 |
+
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
149 |
+
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
151 |
+
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
153 |
+
"gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
154 |
+
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00003.safetensors",
|
155 |
+
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
|
156 |
+
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
157 |
+
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
158 |
+
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
159 |
+
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
160 |
+
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
161 |
+
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
162 |
+
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
163 |
+
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
164 |
+
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
165 |
+
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
166 |
+
"gpt_neox.layers.20.attention.dense.bias": "model-00002-of-00003.safetensors",
|
167 |
+
"gpt_neox.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
|
168 |
+
"gpt_neox.layers.20.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
169 |
+
"gpt_neox.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
170 |
+
"gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
171 |
+
"gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
172 |
+
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
173 |
+
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
174 |
+
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
175 |
+
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
176 |
+
"gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
177 |
+
"gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
178 |
+
"gpt_neox.layers.21.attention.dense.bias": "model-00002-of-00003.safetensors",
|
179 |
+
"gpt_neox.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
|
180 |
+
"gpt_neox.layers.21.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
181 |
+
"gpt_neox.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
182 |
+
"gpt_neox.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
183 |
+
"gpt_neox.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
184 |
+
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
185 |
+
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
186 |
+
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
187 |
+
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
188 |
+
"gpt_neox.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
189 |
+
"gpt_neox.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
190 |
+
"gpt_neox.layers.22.attention.dense.bias": "model-00002-of-00003.safetensors",
|
191 |
+
"gpt_neox.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
|
192 |
+
"gpt_neox.layers.22.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
193 |
+
"gpt_neox.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
194 |
+
"gpt_neox.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
195 |
+
"gpt_neox.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
196 |
+
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
197 |
+
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
198 |
+
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
199 |
+
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
200 |
+
"gpt_neox.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
201 |
+
"gpt_neox.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
202 |
+
"gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00003.safetensors",
|
203 |
+
"gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
|
204 |
+
"gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
205 |
+
"gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
206 |
+
"gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
207 |
+
"gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
208 |
+
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
209 |
+
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
210 |
+
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
211 |
+
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
212 |
+
"gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
213 |
+
"gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
214 |
+
"gpt_neox.layers.24.attention.dense.bias": "model-00002-of-00003.safetensors",
|
215 |
+
"gpt_neox.layers.24.attention.dense.weight": "model-00002-of-00003.safetensors",
|
216 |
+
"gpt_neox.layers.24.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
217 |
+
"gpt_neox.layers.24.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
218 |
+
"gpt_neox.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
219 |
+
"gpt_neox.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
220 |
+
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
221 |
+
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
222 |
+
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
223 |
+
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
224 |
+
"gpt_neox.layers.24.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
225 |
+
"gpt_neox.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
226 |
+
"gpt_neox.layers.25.attention.dense.bias": "model-00002-of-00003.safetensors",
|
227 |
+
"gpt_neox.layers.25.attention.dense.weight": "model-00002-of-00003.safetensors",
|
228 |
+
"gpt_neox.layers.25.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
229 |
+
"gpt_neox.layers.25.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
230 |
+
"gpt_neox.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
231 |
+
"gpt_neox.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
232 |
+
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
233 |
+
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
234 |
+
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
235 |
+
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
236 |
+
"gpt_neox.layers.25.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
237 |
+
"gpt_neox.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
238 |
+
"gpt_neox.layers.26.attention.dense.bias": "model-00002-of-00003.safetensors",
|
239 |
+
"gpt_neox.layers.26.attention.dense.weight": "model-00002-of-00003.safetensors",
|
240 |
+
"gpt_neox.layers.26.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
241 |
+
"gpt_neox.layers.26.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
242 |
+
"gpt_neox.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
243 |
+
"gpt_neox.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
244 |
+
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
245 |
+
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
246 |
+
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
247 |
+
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
248 |
+
"gpt_neox.layers.26.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
249 |
+
"gpt_neox.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
250 |
+
"gpt_neox.layers.27.attention.dense.bias": "model-00002-of-00003.safetensors",
|
251 |
+
"gpt_neox.layers.27.attention.dense.weight": "model-00002-of-00003.safetensors",
|
252 |
+
"gpt_neox.layers.27.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
253 |
+
"gpt_neox.layers.27.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
254 |
+
"gpt_neox.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
255 |
+
"gpt_neox.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
256 |
+
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
257 |
+
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
258 |
+
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
259 |
+
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
260 |
+
"gpt_neox.layers.27.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
261 |
+
"gpt_neox.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
262 |
+
"gpt_neox.layers.28.attention.dense.bias": "model-00002-of-00003.safetensors",
|
263 |
+
"gpt_neox.layers.28.attention.dense.weight": "model-00002-of-00003.safetensors",
|
264 |
+
"gpt_neox.layers.28.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
265 |
+
"gpt_neox.layers.28.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
266 |
+
"gpt_neox.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
267 |
+
"gpt_neox.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
268 |
+
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
269 |
+
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
270 |
+
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
271 |
+
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
272 |
+
"gpt_neox.layers.28.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
273 |
+
"gpt_neox.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
274 |
+
"gpt_neox.layers.29.attention.dense.bias": "model-00002-of-00003.safetensors",
|
275 |
+
"gpt_neox.layers.29.attention.dense.weight": "model-00002-of-00003.safetensors",
|
276 |
+
"gpt_neox.layers.29.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
277 |
+
"gpt_neox.layers.29.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
278 |
+
"gpt_neox.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
279 |
+
"gpt_neox.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
280 |
+
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
281 |
+
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
282 |
+
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
283 |
+
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
284 |
+
"gpt_neox.layers.29.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
285 |
+
"gpt_neox.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
286 |
+
"gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00003.safetensors",
|
287 |
+
"gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
289 |
+
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
291 |
+
"gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
293 |
+
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
295 |
+
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
297 |
+
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
298 |
+
"gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00003.safetensors",
|
299 |
+
"gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
|
300 |
+
"gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
301 |
+
"gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
302 |
+
"gpt_neox.layers.30.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
303 |
+
"gpt_neox.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
304 |
+
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
305 |
+
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
306 |
+
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
307 |
+
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
308 |
+
"gpt_neox.layers.30.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
309 |
+
"gpt_neox.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
310 |
+
"gpt_neox.layers.31.attention.dense.bias": "model-00003-of-00003.safetensors",
|
311 |
+
"gpt_neox.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
|
312 |
+
"gpt_neox.layers.31.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
313 |
+
"gpt_neox.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
314 |
+
"gpt_neox.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
315 |
+
"gpt_neox.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
316 |
+
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
317 |
+
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
318 |
+
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
319 |
+
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
320 |
+
"gpt_neox.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
321 |
+
"gpt_neox.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
322 |
+
"gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00003.safetensors",
|
323 |
+
"gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
|
324 |
+
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
325 |
+
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
326 |
+
"gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
327 |
+
"gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
328 |
+
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
329 |
+
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
330 |
+
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
331 |
+
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
332 |
+
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
333 |
+
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
334 |
+
"gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00003.safetensors",
|
335 |
+
"gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
|
336 |
+
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
337 |
+
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
338 |
+
"gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
339 |
+
"gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
340 |
+
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
341 |
+
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
342 |
+
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
343 |
+
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
344 |
+
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
345 |
+
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
346 |
+
"gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00003.safetensors",
|
347 |
+
"gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
|
348 |
+
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
349 |
+
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
350 |
+
"gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
351 |
+
"gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
352 |
+
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
353 |
+
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
354 |
+
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
355 |
+
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
356 |
+
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
357 |
+
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
358 |
+
"gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00003.safetensors",
|
359 |
+
"gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
|
360 |
+
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
361 |
+
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
362 |
+
"gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
363 |
+
"gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
364 |
+
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
365 |
+
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
366 |
+
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
367 |
+
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
368 |
+
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
369 |
+
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
370 |
+
"gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00003.safetensors",
|
371 |
+
"gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
|
372 |
+
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
373 |
+
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
374 |
+
"gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
375 |
+
"gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
376 |
+
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
377 |
+
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
378 |
+
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
379 |
+
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
380 |
+
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
381 |
+
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
382 |
+
"gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00003.safetensors",
|
383 |
+
"gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
|
384 |
+
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
385 |
+
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
386 |
+
"gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
387 |
+
"gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
388 |
+
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
389 |
+
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
390 |
+
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
391 |
+
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
392 |
+
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
393 |
+
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors"
|
394 |
}
|
395 |
}
|