codebert commited on
Commit
08ac6c4
1 Parent(s): 20cde9b

Upload 7 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</state>": 51418,
3
+ "<0>": 51422,
4
+ "<100>": 51522,
5
+ "<101>": 51523,
6
+ "<102>": 51524,
7
+ "<103>": 51525,
8
+ "<104>": 51526,
9
+ "<105>": 51527,
10
+ "<106>": 51528,
11
+ "<107>": 51529,
12
+ "<108>": 51530,
13
+ "<109>": 51531,
14
+ "<10>": 51432,
15
+ "<110>": 51532,
16
+ "<111>": 51533,
17
+ "<112>": 51534,
18
+ "<113>": 51535,
19
+ "<114>": 51536,
20
+ "<115>": 51537,
21
+ "<116>": 51538,
22
+ "<117>": 51539,
23
+ "<118>": 51540,
24
+ "<119>": 51541,
25
+ "<11>": 51433,
26
+ "<120>": 51542,
27
+ "<121>": 51543,
28
+ "<122>": 51544,
29
+ "<123>": 51545,
30
+ "<124>": 51546,
31
+ "<125>": 51547,
32
+ "<126>": 51548,
33
+ "<127>": 51549,
34
+ "<128>": 51550,
35
+ "<129>": 51551,
36
+ "<12>": 51434,
37
+ "<130>": 51552,
38
+ "<131>": 51553,
39
+ "<132>": 51554,
40
+ "<133>": 51555,
41
+ "<134>": 51556,
42
+ "<135>": 51557,
43
+ "<136>": 51558,
44
+ "<137>": 51559,
45
+ "<138>": 51560,
46
+ "<139>": 51561,
47
+ "<13>": 51435,
48
+ "<140>": 51562,
49
+ "<141>": 51563,
50
+ "<142>": 51564,
51
+ "<143>": 51565,
52
+ "<144>": 51566,
53
+ "<145>": 51567,
54
+ "<146>": 51568,
55
+ "<147>": 51569,
56
+ "<148>": 51570,
57
+ "<149>": 51571,
58
+ "<14>": 51436,
59
+ "<150>": 51572,
60
+ "<151>": 51573,
61
+ "<152>": 51574,
62
+ "<153>": 51575,
63
+ "<154>": 51576,
64
+ "<155>": 51577,
65
+ "<156>": 51578,
66
+ "<157>": 51579,
67
+ "<158>": 51580,
68
+ "<159>": 51581,
69
+ "<15>": 51437,
70
+ "<160>": 51582,
71
+ "<161>": 51583,
72
+ "<162>": 51584,
73
+ "<163>": 51585,
74
+ "<164>": 51586,
75
+ "<165>": 51587,
76
+ "<166>": 51588,
77
+ "<167>": 51589,
78
+ "<168>": 51590,
79
+ "<169>": 51591,
80
+ "<16>": 51438,
81
+ "<170>": 51592,
82
+ "<171>": 51593,
83
+ "<172>": 51594,
84
+ "<173>": 51595,
85
+ "<174>": 51596,
86
+ "<175>": 51597,
87
+ "<176>": 51598,
88
+ "<177>": 51599,
89
+ "<178>": 51600,
90
+ "<179>": 51601,
91
+ "<17>": 51439,
92
+ "<180>": 51602,
93
+ "<181>": 51603,
94
+ "<182>": 51604,
95
+ "<183>": 51605,
96
+ "<184>": 51606,
97
+ "<185>": 51607,
98
+ "<186>": 51608,
99
+ "<187>": 51609,
100
+ "<188>": 51610,
101
+ "<189>": 51611,
102
+ "<18>": 51440,
103
+ "<190>": 51612,
104
+ "<191>": 51613,
105
+ "<192>": 51614,
106
+ "<193>": 51615,
107
+ "<194>": 51616,
108
+ "<195>": 51617,
109
+ "<196>": 51618,
110
+ "<197>": 51619,
111
+ "<198>": 51620,
112
+ "<199>": 51621,
113
+ "<19>": 51441,
114
+ "<1>": 51423,
115
+ "<20>": 51442,
116
+ "<21>": 51443,
117
+ "<22>": 51444,
118
+ "<23>": 51445,
119
+ "<24>": 51446,
120
+ "<25>": 51447,
121
+ "<26>": 51448,
122
+ "<27>": 51449,
123
+ "<28>": 51450,
124
+ "<29>": 51451,
125
+ "<2>": 51424,
126
+ "<30>": 51452,
127
+ "<31>": 51453,
128
+ "<32>": 51454,
129
+ "<33>": 51455,
130
+ "<34>": 51456,
131
+ "<35>": 51457,
132
+ "<36>": 51458,
133
+ "<37>": 51459,
134
+ "<38>": 51460,
135
+ "<39>": 51461,
136
+ "<3>": 51425,
137
+ "<40>": 51462,
138
+ "<41>": 51463,
139
+ "<42>": 51464,
140
+ "<43>": 51465,
141
+ "<44>": 51466,
142
+ "<45>": 51467,
143
+ "<46>": 51468,
144
+ "<47>": 51469,
145
+ "<48>": 51470,
146
+ "<49>": 51471,
147
+ "<4>": 51426,
148
+ "<50>": 51472,
149
+ "<51>": 51473,
150
+ "<52>": 51474,
151
+ "<53>": 51475,
152
+ "<54>": 51476,
153
+ "<55>": 51477,
154
+ "<56>": 51478,
155
+ "<57>": 51479,
156
+ "<58>": 51480,
157
+ "<59>": 51481,
158
+ "<5>": 51427,
159
+ "<60>": 51482,
160
+ "<61>": 51483,
161
+ "<62>": 51484,
162
+ "<63>": 51485,
163
+ "<64>": 51486,
164
+ "<65>": 51487,
165
+ "<66>": 51488,
166
+ "<67>": 51489,
167
+ "<68>": 51490,
168
+ "<69>": 51491,
169
+ "<6>": 51428,
170
+ "<70>": 51492,
171
+ "<71>": 51493,
172
+ "<72>": 51494,
173
+ "<73>": 51495,
174
+ "<74>": 51496,
175
+ "<75>": 51497,
176
+ "<76>": 51498,
177
+ "<77>": 51499,
178
+ "<78>": 51500,
179
+ "<79>": 51501,
180
+ "<7>": 51429,
181
+ "<80>": 51502,
182
+ "<81>": 51503,
183
+ "<82>": 51504,
184
+ "<83>": 51505,
185
+ "<84>": 51506,
186
+ "<85>": 51507,
187
+ "<86>": 51508,
188
+ "<87>": 51509,
189
+ "<88>": 51510,
190
+ "<89>": 51511,
191
+ "<8>": 51430,
192
+ "<90>": 51512,
193
+ "<91>": 51513,
194
+ "<92>": 51514,
195
+ "<93>": 51515,
196
+ "<94>": 51516,
197
+ "<95>": 51517,
198
+ "<96>": 51518,
199
+ "<97>": 51519,
200
+ "<98>": 51520,
201
+ "<99>": 51521,
202
+ "<9>": 51431,
203
+ "<codenet>": 51624,
204
+ "<dedent>": 51626,
205
+ "<dictsep>": 51419,
206
+ "<function>": 51421,
207
+ "<indent>": 51625,
208
+ "<line>": 51416,
209
+ "<output>": 51420,
210
+ "<singleline>": 51622,
211
+ "<state>": 51417,
212
+ "<tutorial>": 51623
213
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/drive/saved_models/tracelearner-codenet-mix-1024/checkpoint-305000-0.4677",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 1026,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.25.1",
26
+ "type_vocab_size": 10,
27
+ "use_cache": true,
28
+ "vocab_size": 51627
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950cd5d26eaaf8a14594bcc9ff06b71b2504334d245d4197103ebec14cede3c9
3
+ size 504445815
special_tokens_map.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<line>",
4
+ "<state>",
5
+ "</state>",
6
+ "<dictsep>",
7
+ "<output>",
8
+ "<function>",
9
+ "<singleline>",
10
+ "<tutorial>",
11
+ "<codenet>",
12
+ "<indent>",
13
+ "<dedent>",
14
+ "<0>",
15
+ "<1>",
16
+ "<2>",
17
+ "<3>",
18
+ "<4>",
19
+ "<5>",
20
+ "<6>",
21
+ "<7>",
22
+ "<8>",
23
+ "<9>",
24
+ "<10>",
25
+ "<11>",
26
+ "<12>",
27
+ "<13>",
28
+ "<14>",
29
+ "<15>",
30
+ "<16>",
31
+ "<17>",
32
+ "<18>",
33
+ "<19>",
34
+ "<20>",
35
+ "<21>",
36
+ "<22>",
37
+ "<23>",
38
+ "<24>",
39
+ "<25>",
40
+ "<26>",
41
+ "<27>",
42
+ "<28>",
43
+ "<29>",
44
+ "<30>",
45
+ "<31>",
46
+ "<32>",
47
+ "<33>",
48
+ "<34>",
49
+ "<35>",
50
+ "<36>",
51
+ "<37>",
52
+ "<38>",
53
+ "<39>",
54
+ "<40>",
55
+ "<41>",
56
+ "<42>",
57
+ "<43>",
58
+ "<44>",
59
+ "<45>",
60
+ "<46>",
61
+ "<47>",
62
+ "<48>",
63
+ "<49>",
64
+ "<50>",
65
+ "<51>",
66
+ "<52>",
67
+ "<53>",
68
+ "<54>",
69
+ "<55>",
70
+ "<56>",
71
+ "<57>",
72
+ "<58>",
73
+ "<59>",
74
+ "<60>",
75
+ "<61>",
76
+ "<62>",
77
+ "<63>",
78
+ "<64>",
79
+ "<65>",
80
+ "<66>",
81
+ "<67>",
82
+ "<68>",
83
+ "<69>",
84
+ "<70>",
85
+ "<71>",
86
+ "<72>",
87
+ "<73>",
88
+ "<74>",
89
+ "<75>",
90
+ "<76>",
91
+ "<77>",
92
+ "<78>",
93
+ "<79>",
94
+ "<80>",
95
+ "<81>",
96
+ "<82>",
97
+ "<83>",
98
+ "<84>",
99
+ "<85>",
100
+ "<86>",
101
+ "<87>",
102
+ "<88>",
103
+ "<89>",
104
+ "<90>",
105
+ "<91>",
106
+ "<92>",
107
+ "<93>",
108
+ "<94>",
109
+ "<95>",
110
+ "<96>",
111
+ "<97>",
112
+ "<98>",
113
+ "<99>",
114
+ "<100>",
115
+ "<101>",
116
+ "<102>",
117
+ "<103>",
118
+ "<104>",
119
+ "<105>",
120
+ "<106>",
121
+ "<107>",
122
+ "<108>",
123
+ "<109>",
124
+ "<110>",
125
+ "<111>",
126
+ "<112>",
127
+ "<113>",
128
+ "<114>",
129
+ "<115>",
130
+ "<116>",
131
+ "<117>",
132
+ "<118>",
133
+ "<119>",
134
+ "<120>",
135
+ "<121>",
136
+ "<122>",
137
+ "<123>",
138
+ "<124>",
139
+ "<125>",
140
+ "<126>",
141
+ "<127>",
142
+ "<128>",
143
+ "<129>",
144
+ "<130>",
145
+ "<131>",
146
+ "<132>",
147
+ "<133>",
148
+ "<134>",
149
+ "<135>",
150
+ "<136>",
151
+ "<137>",
152
+ "<138>",
153
+ "<139>",
154
+ "<140>",
155
+ "<141>",
156
+ "<142>",
157
+ "<143>",
158
+ "<144>",
159
+ "<145>",
160
+ "<146>",
161
+ "<147>",
162
+ "<148>",
163
+ "<149>",
164
+ "<150>",
165
+ "<151>",
166
+ "<152>",
167
+ "<153>",
168
+ "<154>",
169
+ "<155>",
170
+ "<156>",
171
+ "<157>",
172
+ "<158>",
173
+ "<159>",
174
+ "<160>",
175
+ "<161>",
176
+ "<162>",
177
+ "<163>",
178
+ "<164>",
179
+ "<165>",
180
+ "<166>",
181
+ "<167>",
182
+ "<168>",
183
+ "<169>",
184
+ "<170>",
185
+ "<171>",
186
+ "<172>",
187
+ "<173>",
188
+ "<174>",
189
+ "<175>",
190
+ "<176>",
191
+ "<177>",
192
+ "<178>",
193
+ "<179>",
194
+ "<180>",
195
+ "<181>",
196
+ "<182>",
197
+ "<183>",
198
+ "<184>",
199
+ "<185>",
200
+ "<186>",
201
+ "<187>",
202
+ "<188>",
203
+ "<189>",
204
+ "<190>",
205
+ "<191>",
206
+ "<192>",
207
+ "<193>",
208
+ "<194>",
209
+ "<195>",
210
+ "<196>",
211
+ "<197>",
212
+ "<198>",
213
+ "<199>"
214
+ ],
215
+ "bos_token": {
216
+ "content": "<s>",
217
+ "lstrip": false,
218
+ "normalized": true,
219
+ "rstrip": false,
220
+ "single_word": false
221
+ },
222
+ "cls_token": {
223
+ "content": "<s>",
224
+ "lstrip": false,
225
+ "normalized": true,
226
+ "rstrip": false,
227
+ "single_word": false
228
+ },
229
+ "eos_token": {
230
+ "content": "</s>",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false
235
+ },
236
+ "mask_token": {
237
+ "content": "<mask>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false
242
+ },
243
+ "pad_token": {
244
+ "content": "<pad>",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false
249
+ },
250
+ "sep_token": {
251
+ "content": "</s>",
252
+ "lstrip": false,
253
+ "normalized": true,
254
+ "rstrip": false,
255
+ "single_word": false
256
+ },
257
+ "unk_token": {
258
+ "content": "<unk>",
259
+ "lstrip": false,
260
+ "normalized": true,
261
+ "rstrip": false,
262
+ "single_word": false
263
+ }
264
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "name_or_path": "/drive/saved_models/tracelearner-codenet-mix-1024/checkpoint-305000-0.4677",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "tokenizer_file": null,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff