DataPilot commited on
Commit
39f3454
1 Parent(s): 80b41ef
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "fine_model/finetuned",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "end_token_id": 2,
11
+ "eos_token_id": 2,
12
+ "gradient_checkpointing": false,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "gpt2",
16
+ "n_ctx": 2048,
17
+ "n_embd": 2304,
18
+ "n_head": 24,
19
+ "n_inner": 9216,
20
+ "n_layer": 24,
21
+ "n_positions": 2048,
22
+ "pad_token_id": 2,
23
+ "reorder_and_upcast_attn": false,
24
+ "resid_pdrop": 0.1,
25
+ "scale_attn_by_inverse_layer_idx": false,
26
+ "scale_attn_weights": true,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.38.2",
34
+ "use_cache": true,
35
+ "vocab_size": 51200
36
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662209d6381e95c2330b65dd5e6ced28a4d602f1a2dcd4e4a35c68ab5c548fcb
3
+ size 4994440272
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbd0f20e935fc3657104a7d8c599a3eda5e5b834dbc4f96ddf270f685b9cf9d
3
+ size 1614512904
model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6608922624
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
42
+ "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
43
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
44
+ "transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
66
+ "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
67
+ "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
68
+ "transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
69
+ "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
70
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
71
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
75
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
81
+ "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
83
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
90
+ "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
91
+ "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
92
+ "transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
93
+ "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
94
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
95
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
97
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
99
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
101
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
103
+ "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
105
+ "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
107
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
109
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
115
+ "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
116
+ "transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
117
+ "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
118
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
119
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
120
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
121
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
122
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
123
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
125
+ "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
126
+ "transformer.h.18.attn.c_attn.bias": "model-00002-of-00002.safetensors",
127
+ "transformer.h.18.attn.c_attn.weight": "model-00002-of-00002.safetensors",
128
+ "transformer.h.18.attn.c_proj.bias": "model-00002-of-00002.safetensors",
129
+ "transformer.h.18.attn.c_proj.weight": "model-00002-of-00002.safetensors",
130
+ "transformer.h.18.ln_1.bias": "model-00002-of-00002.safetensors",
131
+ "transformer.h.18.ln_1.weight": "model-00002-of-00002.safetensors",
132
+ "transformer.h.18.ln_2.bias": "model-00002-of-00002.safetensors",
133
+ "transformer.h.18.ln_2.weight": "model-00002-of-00002.safetensors",
134
+ "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
135
+ "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
136
+ "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
137
+ "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
138
+ "transformer.h.19.attn.c_attn.bias": "model-00002-of-00002.safetensors",
139
+ "transformer.h.19.attn.c_attn.weight": "model-00002-of-00002.safetensors",
140
+ "transformer.h.19.attn.c_proj.bias": "model-00002-of-00002.safetensors",
141
+ "transformer.h.19.attn.c_proj.weight": "model-00002-of-00002.safetensors",
142
+ "transformer.h.19.ln_1.bias": "model-00002-of-00002.safetensors",
143
+ "transformer.h.19.ln_1.weight": "model-00002-of-00002.safetensors",
144
+ "transformer.h.19.ln_2.bias": "model-00002-of-00002.safetensors",
145
+ "transformer.h.19.ln_2.weight": "model-00002-of-00002.safetensors",
146
+ "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
147
+ "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
148
+ "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
149
+ "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
150
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
151
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
153
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
159
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
161
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.20.attn.c_attn.bias": "model-00002-of-00002.safetensors",
163
+ "transformer.h.20.attn.c_attn.weight": "model-00002-of-00002.safetensors",
164
+ "transformer.h.20.attn.c_proj.bias": "model-00002-of-00002.safetensors",
165
+ "transformer.h.20.attn.c_proj.weight": "model-00002-of-00002.safetensors",
166
+ "transformer.h.20.ln_1.bias": "model-00002-of-00002.safetensors",
167
+ "transformer.h.20.ln_1.weight": "model-00002-of-00002.safetensors",
168
+ "transformer.h.20.ln_2.bias": "model-00002-of-00002.safetensors",
169
+ "transformer.h.20.ln_2.weight": "model-00002-of-00002.safetensors",
170
+ "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
171
+ "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
172
+ "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
173
+ "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
174
+ "transformer.h.21.attn.c_attn.bias": "model-00002-of-00002.safetensors",
175
+ "transformer.h.21.attn.c_attn.weight": "model-00002-of-00002.safetensors",
176
+ "transformer.h.21.attn.c_proj.bias": "model-00002-of-00002.safetensors",
177
+ "transformer.h.21.attn.c_proj.weight": "model-00002-of-00002.safetensors",
178
+ "transformer.h.21.ln_1.bias": "model-00002-of-00002.safetensors",
179
+ "transformer.h.21.ln_1.weight": "model-00002-of-00002.safetensors",
180
+ "transformer.h.21.ln_2.bias": "model-00002-of-00002.safetensors",
181
+ "transformer.h.21.ln_2.weight": "model-00002-of-00002.safetensors",
182
+ "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
183
+ "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
184
+ "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
185
+ "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
186
+ "transformer.h.22.attn.c_attn.bias": "model-00002-of-00002.safetensors",
187
+ "transformer.h.22.attn.c_attn.weight": "model-00002-of-00002.safetensors",
188
+ "transformer.h.22.attn.c_proj.bias": "model-00002-of-00002.safetensors",
189
+ "transformer.h.22.attn.c_proj.weight": "model-00002-of-00002.safetensors",
190
+ "transformer.h.22.ln_1.bias": "model-00002-of-00002.safetensors",
191
+ "transformer.h.22.ln_1.weight": "model-00002-of-00002.safetensors",
192
+ "transformer.h.22.ln_2.bias": "model-00002-of-00002.safetensors",
193
+ "transformer.h.22.ln_2.weight": "model-00002-of-00002.safetensors",
194
+ "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
195
+ "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
196
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
197
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
198
+ "transformer.h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors",
199
+ "transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
200
+ "transformer.h.23.attn.c_proj.bias": "model-00002-of-00002.safetensors",
201
+ "transformer.h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors",
202
+ "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
203
+ "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
204
+ "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
205
+ "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
206
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
207
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
208
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
209
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
210
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
211
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
212
+ "transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
213
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
214
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
215
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
216
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
217
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
218
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
219
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
220
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
221
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
222
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
223
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
224
+ "transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
225
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
226
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
227
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
228
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
229
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
230
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
231
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
232
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
233
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
234
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
239
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
241
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
242
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
243
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
245
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
246
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
247
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
248
+ "transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
249
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
250
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
251
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
252
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
253
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
255
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
257
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
259
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
260
+ "transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
261
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
262
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
263
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
264
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
265
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
266
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
267
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
268
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
269
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
270
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
271
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
272
+ "transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
273
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
274
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
275
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
276
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
277
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
278
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
279
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
280
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
281
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
282
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
283
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
285
+ "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
286
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
287
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
289
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
291
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
293
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
294
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
295
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
296
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
297
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
298
+ }
299
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
3
+ size 1208648
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "4": {
29
+ "content": "<sep>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "5": {
37
+ "content": "<mask>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "6": {
45
+ "content": "<cls>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ }
52
+ },
53
+ "additional_special_tokens": [],
54
+ "bos_token": "<s>",
55
+ "clean_up_tokenization_spaces": true,
56
+ "cls_token": "<cls>",
57
+ "do_lower_case": false,
58
+ "eos_token": "</s>",
59
+ "extra_ids": 0,
60
+ "keep_accents": true,
61
+ "legacy": true,
62
+ "mask_token": "<mask>",
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "</s>",
65
+ "sep_token": "<sep>",
66
+ "sp_model_kwargs": {},
67
+ "tokenizer_class": "T5Tokenizer",
68
+ "unk_token": "<unk>"
69
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc4e4af65131edfcb91e03fd144309cc7283d8095774e759bce4b73d8e51a26
3
+ size 4856