mrm8488 commited on
Commit
2118ced
1 Parent(s): ad8fa33

Initial commit from mrm8488

Browse files
config.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/bsc-r2r_shared_mlsum-es-4/checkpoint-2000",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "BSC-TeMU/roberta-base-bne",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.0,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.0,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 514,
46
+ "min_length": 0,
47
+ "model_type": "roberta",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.10.0.dev0",
77
+ "type_vocab_size": 1,
78
+ "use_bfloat16": false,
79
+ "use_cache": true,
80
+ "vocab_size": 50262
81
+ },
82
+ "encoder": {
83
+ "_name_or_path": "BSC-TeMU/roberta-base-bne",
84
+ "add_cross_attention": false,
85
+ "architectures": [
86
+ "RobertaForMaskedLM"
87
+ ],
88
+ "attention_probs_dropout_prob": 0.0,
89
+ "bad_words_ids": null,
90
+ "bos_token_id": 0,
91
+ "chunk_size_feed_forward": 0,
92
+ "classifier_dropout": null,
93
+ "decoder_start_token_id": null,
94
+ "diversity_penalty": 0.0,
95
+ "do_sample": false,
96
+ "early_stopping": false,
97
+ "encoder_no_repeat_ngram_size": 0,
98
+ "eos_token_id": 2,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "gradient_checkpointing": false,
103
+ "hidden_act": "gelu",
104
+ "hidden_dropout_prob": 0.0,
105
+ "hidden_size": 768,
106
+ "id2label": {
107
+ "0": "LABEL_0",
108
+ "1": "LABEL_1"
109
+ },
110
+ "initializer_range": 0.02,
111
+ "intermediate_size": 3072,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "layer_norm_eps": 1e-05,
119
+ "length_penalty": 1.0,
120
+ "max_length": 20,
121
+ "max_position_embeddings": 514,
122
+ "min_length": 0,
123
+ "model_type": "roberta",
124
+ "no_repeat_ngram_size": 0,
125
+ "num_attention_heads": 12,
126
+ "num_beam_groups": 1,
127
+ "num_beams": 1,
128
+ "num_hidden_layers": 12,
129
+ "num_return_sequences": 1,
130
+ "output_attentions": false,
131
+ "output_hidden_states": false,
132
+ "output_scores": false,
133
+ "pad_token_id": 1,
134
+ "position_embedding_type": "absolute",
135
+ "prefix": null,
136
+ "problem_type": null,
137
+ "pruned_heads": {},
138
+ "remove_invalid_values": false,
139
+ "repetition_penalty": 1.0,
140
+ "return_dict": true,
141
+ "return_dict_in_generate": false,
142
+ "sep_token_id": null,
143
+ "task_specific_params": null,
144
+ "temperature": 1.0,
145
+ "tie_encoder_decoder": false,
146
+ "tie_word_embeddings": true,
147
+ "tokenizer_class": null,
148
+ "top_k": 50,
149
+ "top_p": 1.0,
150
+ "torch_dtype": null,
151
+ "torchscript": false,
152
+ "transformers_version": "4.10.0.dev0",
153
+ "type_vocab_size": 1,
154
+ "use_bfloat16": false,
155
+ "use_cache": true,
156
+ "vocab_size": 50262
157
+ },
158
+ "is_encoder_decoder": true,
159
+ "model_type": "encoder-decoder",
160
+ "tie_encoder_decoder": true,
161
+ "torch_dtype": "float32",
162
+ "transformers_version": null
163
+ }
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 sha256:8f012b5741164baf73da86fa15abc82fc66329bebfe94260033929969901344d
3
+ size 614798389
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "BSC-TeMU/roberta-base-bne", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff