mrm8488 commited on
Commit
e44ddea
1 Parent(s): dce4610

Initial commit from mrm8488

Browse files
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "nyu-mll/roberta-med-small-1M-1",
7
+ "_num_labels": 2,
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "decoder_start_token_id": null,
17
+ "do_sample": false,
18
+ "early_stopping": false,
19
+ "eos_token_id": 2,
20
+ "finetuning_task": null,
21
+ "gradient_checkpointing": false,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.1,
24
+ "hidden_size": 512,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 2048,
31
+ "is_decoder": true,
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "max_position_embeddings": 514,
41
+ "min_length": 0,
42
+ "model_type": "roberta",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_attention_heads": 8,
45
+ "num_beams": 1,
46
+ "num_hidden_layers": 6,
47
+ "num_return_sequences": 1,
48
+ "output_attentions": false,
49
+ "output_hidden_states": false,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "position_embedding_type": "absolute",
53
+ "prefix": null,
54
+ "pruned_heads": {},
55
+ "repetition_penalty": 1.0,
56
+ "return_dict": true,
57
+ "sep_token_id": null,
58
+ "task_specific_params": null,
59
+ "temperature": 1.0,
60
+ "tie_encoder_decoder": false,
61
+ "tie_word_embeddings": true,
62
+ "tokenizer_class": null,
63
+ "top_k": 50,
64
+ "top_p": 1.0,
65
+ "torchscript": false,
66
+ "type_vocab_size": 1,
67
+ "use_bfloat16": false,
68
+ "vocab_size": 50265,
69
+ "xla_device": null
70
+ },
71
+ "decoder_start_token_id": 0,
72
+ "early_stopping": true,
73
+ "encoder": {
74
+ "_name_or_path": "nyu-mll/roberta-med-small-1M-1",
75
+ "_num_labels": 2,
76
+ "add_cross_attention": false,
77
+ "architectures": [
78
+ "RobertaForMaskedLM"
79
+ ],
80
+ "attention_probs_dropout_prob": 0.1,
81
+ "bad_words_ids": null,
82
+ "bos_token_id": 0,
83
+ "chunk_size_feed_forward": 0,
84
+ "decoder_start_token_id": null,
85
+ "do_sample": false,
86
+ "early_stopping": false,
87
+ "eos_token_id": 2,
88
+ "finetuning_task": null,
89
+ "gradient_checkpointing": false,
90
+ "hidden_act": "gelu",
91
+ "hidden_dropout_prob": 0.1,
92
+ "hidden_size": 512,
93
+ "id2label": {
94
+ "0": "LABEL_0",
95
+ "1": "LABEL_1"
96
+ },
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 2048,
99
+ "is_decoder": false,
100
+ "is_encoder_decoder": false,
101
+ "label2id": {
102
+ "LABEL_0": 0,
103
+ "LABEL_1": 1
104
+ },
105
+ "layer_norm_eps": 1e-05,
106
+ "length_penalty": 1.0,
107
+ "max_length": 20,
108
+ "max_position_embeddings": 514,
109
+ "min_length": 0,
110
+ "model_type": "roberta",
111
+ "no_repeat_ngram_size": 0,
112
+ "num_attention_heads": 8,
113
+ "num_beams": 1,
114
+ "num_hidden_layers": 6,
115
+ "num_return_sequences": 1,
116
+ "output_attentions": false,
117
+ "output_hidden_states": false,
118
+ "output_past": true,
119
+ "pad_token_id": 1,
120
+ "position_embedding_type": "absolute",
121
+ "prefix": null,
122
+ "pruned_heads": {},
123
+ "repetition_penalty": 1.0,
124
+ "return_dict": true,
125
+ "sep_token_id": null,
126
+ "task_specific_params": null,
127
+ "temperature": 1.0,
128
+ "tie_encoder_decoder": false,
129
+ "tie_word_embeddings": true,
130
+ "tokenizer_class": null,
131
+ "top_k": 50,
132
+ "top_p": 1.0,
133
+ "torchscript": false,
134
+ "type_vocab_size": 1,
135
+ "use_bfloat16": false,
136
+ "vocab_size": 50265,
137
+ "xla_device": null
138
+ },
139
+ "eos_token_id": 2,
140
+ "is_encoder_decoder": true,
141
+ "length_penalty": 2.0,
142
+ "max_length": 142,
143
+ "min_length": 56,
144
+ "model_type": "encoder-decoder",
145
+ "no_repeat_ngram_size": 3,
146
+ "num_beams": 4,
147
+ "vocab_size": 50265
148
+ }
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 sha256:19abe2f35082e64ff35af0926cb5377a8c6b9ebed3773e2bcca8d13895e69168
3
+ size 386988523
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_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"}, "special_tokens_map_file": null, "name_or_path": "nyu-mll/roberta-med-small-1M-1"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fedf2bf4929564406a0243b429fecd4e6a52704b15d8abdc5257fa77beef107
3
+ size 2031
vocab.json ADDED
The diff for this file is too large to render. See raw diff