Hugging Face's logo

CodeRosetta
/
CodeRosetta_cpp2cuda_ft

Safetensors
English
encoder-decoder
Model card Files Community
tehranixyz commited on
Commit
a789862
·
verified ·
1 Parent(s): 2fdc474

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +4 -0
  2. config.json +237 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +80 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<CPP>": 51416,
3
+ "<CUDA>": 51417
4
+ }
config.json ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cudaizerV2_daebt",
3
+ "add_cross_attention": true,
4
+ "architectures": [
5
+ "EncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "cudaizerV2_aer",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "RobertaForTokenClassification"
12
+ ],
13
+ "attention_probs_dropout_prob": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": null,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "gradient_checkpointing": false,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 1536,
34
+ "id2label": {
35
+ "0": "O",
36
+ "1": "B-VAR",
37
+ "2": "I-VAR",
38
+ "3": "B-FUNC",
39
+ "4": "I-FUNC",
40
+ "5": "B-TYPE",
41
+ "6": "I-TYPE",
42
+ "7": "B-PRIM",
43
+ "8": "I-PRIM",
44
+ "9": "B-NUM",
45
+ "10": "I-NUM",
46
+ "11": "B-POIN",
47
+ "12": "I-POIN",
48
+ "13": "B-PDEC",
49
+ "14": "I-PDEC",
50
+ "15": "B-CONS",
51
+ "16": "I-CONS"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 4096,
55
+ "is_decoder": true,
56
+ "is_encoder_decoder": false,
57
+ "label2id": {
58
+ "B-CONS": 15,
59
+ "B-FUNC": 3,
60
+ "B-NUM": 9,
61
+ "B-PDEC": 13,
62
+ "B-POIN": 11,
63
+ "B-PRIM": 7,
64
+ "B-TYPE": 5,
65
+ "B-VAR": 1,
66
+ "I-CONS": 16,
67
+ "I-FUNC": 4,
68
+ "I-NUM": 10,
69
+ "I-PDEC": 14,
70
+ "I-POIN": 12,
71
+ "I-PRIM": 8,
72
+ "I-TYPE": 6,
73
+ "I-VAR": 2,
74
+ "O": 0
75
+ },
76
+ "layer_norm_eps": 1e-05,
77
+ "length_penalty": 1.0,
78
+ "max_length": 20,
79
+ "max_position_embeddings": 1026,
80
+ "min_length": 0,
81
+ "model_type": "roberta",
82
+ "no_repeat_ngram_size": 0,
83
+ "num_attention_heads": 12,
84
+ "num_beam_groups": 1,
85
+ "num_beams": 1,
86
+ "num_hidden_layers": 12,
87
+ "num_return_sequences": 1,
88
+ "output_attentions": false,
89
+ "output_hidden_states": false,
90
+ "output_past": true,
91
+ "output_scores": false,
92
+ "pad_token_id": 1,
93
+ "position_embedding_type": "absolute",
94
+ "prefix": null,
95
+ "problem_type": null,
96
+ "pruned_heads": {},
97
+ "remove_invalid_values": false,
98
+ "repetition_penalty": 1.0,
99
+ "return_dict": true,
100
+ "return_dict_in_generate": false,
101
+ "sep_token_id": null,
102
+ "suppress_tokens": null,
103
+ "task_specific_params": null,
104
+ "temperature": 1.0,
105
+ "tf_legacy_loss": false,
106
+ "tie_encoder_decoder": false,
107
+ "tie_word_embeddings": true,
108
+ "tokenizer_class": null,
109
+ "top_k": 50,
110
+ "top_p": 1.0,
111
+ "torch_dtype": "float32",
112
+ "torchscript": false,
113
+ "type_vocab_size": 10,
114
+ "typical_p": 1.0,
115
+ "use_bfloat16": false,
116
+ "use_cache": true,
117
+ "vocab_size": 51418
118
+ },
119
+ "encoder": {
120
+ "_name_or_path": "cudaizerV2_aer",
121
+ "add_cross_attention": false,
122
+ "architectures": [
123
+ "RobertaForTokenClassification"
124
+ ],
125
+ "attention_probs_dropout_prob": 0.1,
126
+ "bad_words_ids": null,
127
+ "begin_suppress_tokens": null,
128
+ "bos_token_id": 0,
129
+ "chunk_size_feed_forward": 0,
130
+ "classifier_dropout": null,
131
+ "cross_attention_hidden_size": null,
132
+ "decoder_start_token_id": null,
133
+ "diversity_penalty": 0.0,
134
+ "do_sample": false,
135
+ "early_stopping": false,
136
+ "encoder_no_repeat_ngram_size": 0,
137
+ "eos_token_id": 2,
138
+ "exponential_decay_length_penalty": null,
139
+ "finetuning_task": null,
140
+ "forced_bos_token_id": null,
141
+ "forced_eos_token_id": null,
142
+ "gradient_checkpointing": false,
143
+ "hidden_act": "gelu",
144
+ "hidden_dropout_prob": 0.1,
145
+ "hidden_size": 1536,
146
+ "id2label": {
147
+ "0": "O",
148
+ "1": "B-VAR",
149
+ "2": "I-VAR",
150
+ "3": "B-FUNC",
151
+ "4": "I-FUNC",
152
+ "5": "B-TYPE",
153
+ "6": "I-TYPE",
154
+ "7": "B-PRIM",
155
+ "8": "I-PRIM",
156
+ "9": "B-NUM",
157
+ "10": "I-NUM",
158
+ "11": "B-POIN",
159
+ "12": "I-POIN",
160
+ "13": "B-PDEC",
161
+ "14": "I-PDEC",
162
+ "15": "B-CONS",
163
+ "16": "I-CONS"
164
+ },
165
+ "initializer_range": 0.02,
166
+ "intermediate_size": 4096,
167
+ "is_decoder": false,
168
+ "is_encoder_decoder": false,
169
+ "label2id": {
170
+ "B-CONS": 15,
171
+ "B-FUNC": 3,
172
+ "B-NUM": 9,
173
+ "B-PDEC": 13,
174
+ "B-POIN": 11,
175
+ "B-PRIM": 7,
176
+ "B-TYPE": 5,
177
+ "B-VAR": 1,
178
+ "I-CONS": 16,
179
+ "I-FUNC": 4,
180
+ "I-NUM": 10,
181
+ "I-PDEC": 14,
182
+ "I-POIN": 12,
183
+ "I-PRIM": 8,
184
+ "I-TYPE": 6,
185
+ "I-VAR": 2,
186
+ "O": 0
187
+ },
188
+ "layer_norm_eps": 1e-05,
189
+ "length_penalty": 1.0,
190
+ "max_length": 20,
191
+ "max_position_embeddings": 1026,
192
+ "min_length": 0,
193
+ "model_type": "roberta",
194
+ "no_repeat_ngram_size": 0,
195
+ "num_attention_heads": 12,
196
+ "num_beam_groups": 1,
197
+ "num_beams": 1,
198
+ "num_hidden_layers": 12,
199
+ "num_return_sequences": 1,
200
+ "output_attentions": false,
201
+ "output_hidden_states": false,
202
+ "output_past": true,
203
+ "output_scores": false,
204
+ "pad_token_id": 1,
205
+ "position_embedding_type": "absolute",
206
+ "prefix": null,
207
+ "problem_type": null,
208
+ "pruned_heads": {},
209
+ "remove_invalid_values": false,
210
+ "repetition_penalty": 1.0,
211
+ "return_dict": true,
212
+ "return_dict_in_generate": false,
213
+ "sep_token_id": null,
214
+ "suppress_tokens": null,
215
+ "task_specific_params": null,
216
+ "temperature": 1.0,
217
+ "tf_legacy_loss": false,
218
+ "tie_encoder_decoder": false,
219
+ "tie_word_embeddings": true,
220
+ "tokenizer_class": null,
221
+ "top_k": 50,
222
+ "top_p": 1.0,
223
+ "torch_dtype": "float32",
224
+ "torchscript": false,
225
+ "type_vocab_size": 10,
226
+ "typical_p": 1.0,
227
+ "use_bfloat16": false,
228
+ "use_cache": true,
229
+ "vocab_size": 51418
230
+ },
231
+ "eos_token_id": 2,
232
+ "is_encoder_decoder": true,
233
+ "model_type": "encoder-decoder",
234
+ "pad_token_id": 1,
235
+ "torch_dtype": "float32",
236
+ "transformers_version": "4.40.1"
237
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.40.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff4a5d29c89bb782da12d5c5ae7ee664700491d3afad6ac485d238bc0c26d94
3
+ size 3232828176
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<CPP>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<CUDA>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "bos_token": "<s>",
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "<s>",
64
+ "eos_token": "</s>",
65
+ "errors": "replace",
66
+ "mask_token": "<mask>",
67
+ "max_length": 512,
68
+ "model_max_length": 512,
69
+ "pad_to_multiple_of": null,
70
+ "pad_token": "<pad>",
71
+ "pad_token_type_id": 0,
72
+ "padding_side": "right",
73
+ "sep_token": "</s>",
74
+ "stride": 0,
75
+ "tokenizer_class": "RobertaTokenizer",
76
+ "trim_offsets": true,
77
+ "truncation_side": "right",
78
+ "truncation_strategy": "longest_first",
79
+ "unk_token": "<unk>"
80
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff