cibernicola commited on
Commit
72238e6
1 Parent(s): b97c14c

Upload 9 files

Browse files
.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
+ FLOR-6.3B-xat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
FLOR-6.3B-xat-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8bc40d0360910c8de9546f0daf0484c3462b78af539b629ac68aa496f004db
3
+ size 6863057344
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "projecte-aina/FLOR-6.3B",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "bloom",
15
+ "n_head": 32,
16
+ "n_layer": 30,
17
+ "pretraining_tp": 1,
18
+ "slow_but_exact": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.36.2",
21
+ "use_cache": true,
22
+ "vocab_size": 50257
23
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12494528512
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.bin",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.bin",
8
+ "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
9
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
10
+ "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
11
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
12
+ "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.bin",
13
+ "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.bin",
14
+ "transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.bin",
15
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.bin",
16
+ "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
17
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
18
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.bin",
19
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.bin",
20
+ "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
21
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
22
+ "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
23
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
24
+ "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.bin",
25
+ "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.bin",
26
+ "transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.bin",
27
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.bin",
28
+ "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
29
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
30
+ "transformer.h.10.input_layernorm.bias": "model-00001-of-00003.bin",
31
+ "transformer.h.10.input_layernorm.weight": "model-00001-of-00003.bin",
32
+ "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
33
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
34
+ "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
35
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
36
+ "transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00003.bin",
37
+ "transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00003.bin",
38
+ "transformer.h.10.self_attention.dense.bias": "model-00001-of-00003.bin",
39
+ "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.bin",
40
+ "transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
41
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
42
+ "transformer.h.11.input_layernorm.bias": "model-00001-of-00003.bin",
43
+ "transformer.h.11.input_layernorm.weight": "model-00001-of-00003.bin",
44
+ "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
45
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
46
+ "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
47
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
48
+ "transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00003.bin",
49
+ "transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00003.bin",
50
+ "transformer.h.11.self_attention.dense.bias": "model-00001-of-00003.bin",
51
+ "transformer.h.11.self_attention.dense.weight": "model-00001-of-00003.bin",
52
+ "transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
53
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
54
+ "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.bin",
55
+ "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.bin",
56
+ "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
57
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
58
+ "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
59
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
60
+ "transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.bin",
61
+ "transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.bin",
62
+ "transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.bin",
63
+ "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.bin",
64
+ "transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
65
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
66
+ "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.bin",
67
+ "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.bin",
68
+ "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
69
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
70
+ "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
71
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
72
+ "transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.bin",
73
+ "transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.bin",
74
+ "transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.bin",
75
+ "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.bin",
76
+ "transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
77
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
78
+ "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.bin",
79
+ "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.bin",
80
+ "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
81
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
82
+ "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
83
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
84
+ "transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.bin",
85
+ "transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.bin",
86
+ "transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.bin",
87
+ "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.bin",
88
+ "transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
89
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
90
+ "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.bin",
91
+ "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.bin",
92
+ "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
93
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
94
+ "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
95
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
96
+ "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.bin",
97
+ "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.bin",
98
+ "transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.bin",
99
+ "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.bin",
100
+ "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
101
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
102
+ "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.bin",
103
+ "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.bin",
104
+ "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
105
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
106
+ "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
107
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
108
+ "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.bin",
109
+ "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.bin",
110
+ "transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.bin",
111
+ "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.bin",
112
+ "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
113
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
114
+ "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.bin",
115
+ "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.bin",
116
+ "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
117
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
118
+ "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
119
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
120
+ "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.bin",
121
+ "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.bin",
122
+ "transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.bin",
123
+ "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.bin",
124
+ "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
125
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
126
+ "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.bin",
127
+ "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.bin",
128
+ "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
129
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
130
+ "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
131
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
132
+ "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.bin",
133
+ "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.bin",
134
+ "transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.bin",
135
+ "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.bin",
136
+ "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
137
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
138
+ "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.bin",
139
+ "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.bin",
140
+ "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
141
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
142
+ "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
143
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
144
+ "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.bin",
145
+ "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.bin",
146
+ "transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.bin",
147
+ "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.bin",
148
+ "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
149
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
150
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.bin",
151
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.bin",
152
+ "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
153
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
154
+ "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
155
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
156
+ "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.bin",
157
+ "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.bin",
158
+ "transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.bin",
159
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.bin",
160
+ "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
161
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
162
+ "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.bin",
163
+ "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.bin",
164
+ "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
165
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
166
+ "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
167
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
168
+ "transformer.h.20.post_attention_layernorm.bias": "model-00002-of-00003.bin",
169
+ "transformer.h.20.post_attention_layernorm.weight": "model-00002-of-00003.bin",
170
+ "transformer.h.20.self_attention.dense.bias": "model-00002-of-00003.bin",
171
+ "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.bin",
172
+ "transformer.h.20.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
173
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
174
+ "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.bin",
175
+ "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.bin",
176
+ "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
177
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
178
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
179
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
180
+ "transformer.h.21.post_attention_layernorm.bias": "model-00002-of-00003.bin",
181
+ "transformer.h.21.post_attention_layernorm.weight": "model-00002-of-00003.bin",
182
+ "transformer.h.21.self_attention.dense.bias": "model-00002-of-00003.bin",
183
+ "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.bin",
184
+ "transformer.h.21.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
185
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
186
+ "transformer.h.22.input_layernorm.bias": "model-00002-of-00003.bin",
187
+ "transformer.h.22.input_layernorm.weight": "model-00002-of-00003.bin",
188
+ "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
189
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
190
+ "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
191
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
192
+ "transformer.h.22.post_attention_layernorm.bias": "model-00002-of-00003.bin",
193
+ "transformer.h.22.post_attention_layernorm.weight": "model-00002-of-00003.bin",
194
+ "transformer.h.22.self_attention.dense.bias": "model-00002-of-00003.bin",
195
+ "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.bin",
196
+ "transformer.h.22.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
197
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
198
+ "transformer.h.23.input_layernorm.bias": "model-00002-of-00003.bin",
199
+ "transformer.h.23.input_layernorm.weight": "model-00002-of-00003.bin",
200
+ "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
201
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
202
+ "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
203
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
204
+ "transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00003.bin",
205
+ "transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00003.bin",
206
+ "transformer.h.23.self_attention.dense.bias": "model-00002-of-00003.bin",
207
+ "transformer.h.23.self_attention.dense.weight": "model-00002-of-00003.bin",
208
+ "transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
209
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
210
+ "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.bin",
211
+ "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.bin",
212
+ "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
213
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
214
+ "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
215
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
216
+ "transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.bin",
217
+ "transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.bin",
218
+ "transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.bin",
219
+ "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.bin",
220
+ "transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
221
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
222
+ "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.bin",
223
+ "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.bin",
224
+ "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
225
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
226
+ "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
227
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
228
+ "transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.bin",
229
+ "transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.bin",
230
+ "transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.bin",
231
+ "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.bin",
232
+ "transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
233
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
234
+ "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.bin",
235
+ "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.bin",
236
+ "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
237
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
238
+ "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
239
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
240
+ "transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.bin",
241
+ "transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.bin",
242
+ "transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.bin",
243
+ "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.bin",
244
+ "transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
245
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
246
+ "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.bin",
247
+ "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.bin",
248
+ "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
249
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
250
+ "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
251
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
252
+ "transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.bin",
253
+ "transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.bin",
254
+ "transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.bin",
255
+ "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.bin",
256
+ "transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
257
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
258
+ "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.bin",
259
+ "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.bin",
260
+ "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
261
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
262
+ "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
263
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
264
+ "transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.bin",
265
+ "transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.bin",
266
+ "transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.bin",
267
+ "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.bin",
268
+ "transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
269
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
270
+ "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.bin",
271
+ "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.bin",
272
+ "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
273
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
274
+ "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
275
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
276
+ "transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.bin",
277
+ "transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.bin",
278
+ "transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.bin",
279
+ "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.bin",
280
+ "transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
281
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
282
+ "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.bin",
283
+ "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.bin",
284
+ "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
285
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
286
+ "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
287
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
288
+ "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.bin",
289
+ "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.bin",
290
+ "transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.bin",
291
+ "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.bin",
292
+ "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
293
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
294
+ "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.bin",
295
+ "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.bin",
296
+ "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
297
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
298
+ "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
299
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
300
+ "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.bin",
301
+ "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.bin",
302
+ "transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.bin",
303
+ "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.bin",
304
+ "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
305
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
306
+ "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.bin",
307
+ "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.bin",
308
+ "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
309
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
310
+ "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
311
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
312
+ "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.bin",
313
+ "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.bin",
314
+ "transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.bin",
315
+ "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.bin",
316
+ "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
317
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
318
+ "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.bin",
319
+ "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.bin",
320
+ "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
321
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
322
+ "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
323
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
324
+ "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.bin",
325
+ "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.bin",
326
+ "transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.bin",
327
+ "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.bin",
328
+ "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
329
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
330
+ "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.bin",
331
+ "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.bin",
332
+ "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
333
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
334
+ "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
335
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
336
+ "transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00003.bin",
337
+ "transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00003.bin",
338
+ "transformer.h.7.self_attention.dense.bias": "model-00001-of-00003.bin",
339
+ "transformer.h.7.self_attention.dense.weight": "model-00001-of-00003.bin",
340
+ "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
341
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
342
+ "transformer.h.8.input_layernorm.bias": "model-00001-of-00003.bin",
343
+ "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.bin",
344
+ "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
345
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
346
+ "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
347
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
348
+ "transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00003.bin",
349
+ "transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00003.bin",
350
+ "transformer.h.8.self_attention.dense.bias": "model-00001-of-00003.bin",
351
+ "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.bin",
352
+ "transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
353
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
354
+ "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.bin",
355
+ "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.bin",
356
+ "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
357
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
358
+ "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
359
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
360
+ "transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00003.bin",
361
+ "transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00003.bin",
362
+ "transformer.h.9.self_attention.dense.bias": "model-00001-of-00003.bin",
363
+ "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.bin",
364
+ "transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
365
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
366
+ "transformer.ln_f.bias": "model-00003-of-00003.bin",
367
+ "transformer.ln_f.weight": "model-00003-of-00003.bin",
368
+ "transformer.word_embeddings.weight": "model-00001-of-00003.bin",
369
+ "transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.bin",
370
+ "transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.bin"
371
+ }
372
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1000000000000000019884624838656,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff