izhx commited on
Commit
b6d03f5
1 Parent(s): 020bd78
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-3b",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomModel"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2560,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_head": 32,
19
+ "n_inner": null,
20
+ "n_layer": 30,
21
+ "offset_alibi": 100,
22
+ "pad_token_id": 3,
23
+ "pretraining_tp": 4,
24
+ "skip_bias_add": true,
25
+ "skip_bias_add_qkv": false,
26
+ "slow_but_exact": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.1",
29
+ "unk_token_id": 0,
30
+ "use_cache": true,
31
+ "vocab_size": 250880
32
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66b132530a744f65e304d8050268d45a66dd7b7b12eae81b5c1ffb85cd72b6e
3
+ size 9912308072
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392906acbdea030a5b85d1aaca349e1ef2cabbbd249e15b0e7e6abaa2884f8e2
3
+ size 2098048779
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12010229760
4
+ },
5
+ "weight_map": {
6
+ "h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
7
+ "h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
8
+ "h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
9
+ "h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
10
+ "h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
11
+ "h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
12
+ "h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
13
+ "h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
+ "h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
15
+ "h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
16
+ "h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
17
+ "h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
18
+ "h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
19
+ "h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
20
+ "h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
21
+ "h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
22
+ "h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
23
+ "h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
24
+ "h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
25
+ "h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
27
+ "h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
28
+ "h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
29
+ "h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
30
+ "h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
31
+ "h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
32
+ "h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
33
+ "h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
34
+ "h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
35
+ "h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
36
+ "h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
37
+ "h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
38
+ "h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
39
+ "h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
40
+ "h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
41
+ "h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
42
+ "h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
43
+ "h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
44
+ "h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
45
+ "h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
46
+ "h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
47
+ "h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
48
+ "h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
49
+ "h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
50
+ "h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
51
+ "h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
52
+ "h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
53
+ "h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
54
+ "h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
55
+ "h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
56
+ "h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
57
+ "h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
58
+ "h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
59
+ "h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
60
+ "h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
61
+ "h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
63
+ "h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
64
+ "h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
65
+ "h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
66
+ "h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
67
+ "h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
68
+ "h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
69
+ "h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
70
+ "h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
71
+ "h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
72
+ "h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
73
+ "h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
74
+ "h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
75
+ "h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
76
+ "h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
77
+ "h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
78
+ "h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
79
+ "h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
81
+ "h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
82
+ "h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
83
+ "h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
84
+ "h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
85
+ "h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
86
+ "h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
87
+ "h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
88
+ "h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
89
+ "h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
90
+ "h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
91
+ "h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
92
+ "h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
93
+ "h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
94
+ "h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
95
+ "h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
96
+ "h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
97
+ "h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
99
+ "h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
100
+ "h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
101
+ "h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
102
+ "h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
103
+ "h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
104
+ "h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
105
+ "h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
106
+ "h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
107
+ "h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
108
+ "h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
109
+ "h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
110
+ "h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
111
+ "h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
112
+ "h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
113
+ "h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
114
+ "h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
115
+ "h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
116
+ "h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
117
+ "h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
118
+ "h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
119
+ "h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
120
+ "h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
121
+ "h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
122
+ "h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
123
+ "h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
124
+ "h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
125
+ "h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
126
+ "h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
127
+ "h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
128
+ "h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
129
+ "h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
130
+ "h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
131
+ "h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
132
+ "h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
133
+ "h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
134
+ "h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
135
+ "h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
136
+ "h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
137
+ "h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
138
+ "h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
139
+ "h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
140
+ "h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
141
+ "h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
142
+ "h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
143
+ "h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
144
+ "h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
145
+ "h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
146
+ "h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
147
+ "h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
148
+ "h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
149
+ "h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
150
+ "h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
151
+ "h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
152
+ "h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
153
+ "h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
154
+ "h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
155
+ "h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
156
+ "h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
157
+ "h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
158
+ "h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
159
+ "h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
160
+ "h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
161
+ "h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
162
+ "h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
163
+ "h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
164
+ "h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
165
+ "h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
166
+ "h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
167
+ "h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
168
+ "h.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
169
+ "h.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
170
+ "h.20.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
171
+ "h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
172
+ "h.20.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
173
+ "h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
174
+ "h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
175
+ "h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
176
+ "h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
177
+ "h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
178
+ "h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
179
+ "h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
180
+ "h.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
181
+ "h.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
182
+ "h.21.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
183
+ "h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
184
+ "h.21.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
185
+ "h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
186
+ "h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
187
+ "h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
188
+ "h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
189
+ "h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
190
+ "h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
191
+ "h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
192
+ "h.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
193
+ "h.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
194
+ "h.22.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
195
+ "h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
196
+ "h.22.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
197
+ "h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
198
+ "h.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
199
+ "h.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
200
+ "h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
201
+ "h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
202
+ "h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
203
+ "h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
204
+ "h.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
205
+ "h.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
206
+ "h.23.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
207
+ "h.23.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
208
+ "h.23.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
209
+ "h.23.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
210
+ "h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
211
+ "h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
212
+ "h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
213
+ "h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
214
+ "h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
215
+ "h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
216
+ "h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
217
+ "h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
218
+ "h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
219
+ "h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
220
+ "h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
221
+ "h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
222
+ "h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
223
+ "h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
224
+ "h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
225
+ "h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
226
+ "h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
227
+ "h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
228
+ "h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
229
+ "h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
230
+ "h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
231
+ "h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
232
+ "h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
233
+ "h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
234
+ "h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
235
+ "h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
236
+ "h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
237
+ "h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
238
+ "h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
239
+ "h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
240
+ "h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
241
+ "h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
242
+ "h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
243
+ "h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
244
+ "h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
245
+ "h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
246
+ "h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
247
+ "h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
248
+ "h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
249
+ "h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
250
+ "h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
251
+ "h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
252
+ "h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
253
+ "h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
254
+ "h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
255
+ "h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
256
+ "h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
257
+ "h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
258
+ "h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
259
+ "h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
260
+ "h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
261
+ "h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
262
+ "h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
263
+ "h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
264
+ "h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
265
+ "h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
266
+ "h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
267
+ "h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
268
+ "h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
269
+ "h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
270
+ "h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
271
+ "h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
272
+ "h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
273
+ "h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
274
+ "h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
275
+ "h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
276
+ "h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
277
+ "h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
278
+ "h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
279
+ "h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
280
+ "h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
281
+ "h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
282
+ "h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
283
+ "h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
284
+ "h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
285
+ "h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
286
+ "h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
287
+ "h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
288
+ "h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
289
+ "h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
290
+ "h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
291
+ "h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
292
+ "h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
293
+ "h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
294
+ "h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
295
+ "h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
296
+ "h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
297
+ "h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
298
+ "h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
299
+ "h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
300
+ "h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
301
+ "h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
302
+ "h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
303
+ "h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
304
+ "h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
305
+ "h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
306
+ "h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
307
+ "h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
308
+ "h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
309
+ "h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
310
+ "h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
311
+ "h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
312
+ "h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
313
+ "h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
314
+ "h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
315
+ "h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
316
+ "h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
317
+ "h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
318
+ "h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
319
+ "h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
320
+ "h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
321
+ "h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
322
+ "h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
323
+ "h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
324
+ "h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
325
+ "h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
326
+ "h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
327
+ "h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
328
+ "h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
329
+ "h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
330
+ "h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
331
+ "h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
332
+ "h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
333
+ "h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
334
+ "h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
335
+ "h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
336
+ "h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
337
+ "h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
338
+ "h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
339
+ "h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
340
+ "h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
341
+ "h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
342
+ "h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
343
+ "h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
344
+ "h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
345
+ "h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
346
+ "h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
347
+ "h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
348
+ "h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
349
+ "h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
350
+ "h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
351
+ "h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
352
+ "h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
353
+ "h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
354
+ "h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
355
+ "h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
356
+ "h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
357
+ "h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
358
+ "h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
359
+ "h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
360
+ "h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
361
+ "h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
362
+ "h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
363
+ "h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
364
+ "h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
365
+ "h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
366
+ "ln_f.bias": "pytorch_model-00002-of-00002.bin",
367
+ "ln_f.weight": "pytorch_model-00002-of-00002.bin",
368
+ "word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
369
+ "word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
370
+ "word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
371
+ }
372
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e9ea51af5f91cb3744f1940e912bd1509f295ef955f73f556988a1ec3de24c
3
+ size 14501297
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }