Hugging Face's logo

xtie
/
Clinicallongformer2roberta-PET-impression

Summarization
Transformers
PyTorch
English
encoder-decoder
text2text-generation
medical
Inference Endpoints
Model card Files Community
1
xtie commited on
Commit
a1395e8
•
1 Parent(s): db894a7

Initial commit

Browse files
Files changed (8) hide show
  1. config.json +197 -0
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +15 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./template/my-Clinical-Longformer-roberta-base",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "roberta-base",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-05,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 514,
48
+ "min_length": 0,
49
+ "model_type": "roberta",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "position_embedding_type": "absolute",
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "suppress_tokens": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "type_vocab_size": 1,
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
+ "use_cache": true,
84
+ "vocab_size": 50265
85
+ },
86
+ "decoder_start_token_id": 0,
87
+ "early_stopping": true,
88
+ "encoder": {
89
+ "_name_or_path": "yikuan8/Clinical-Longformer",
90
+ "add_cross_attention": false,
91
+ "architectures": [
92
+ "LongformerForMaskedLM"
93
+ ],
94
+ "attention_mode": "longformer",
95
+ "attention_probs_dropout_prob": 0.1,
96
+ "attention_window": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 512,
108
+ 512
109
+ ],
110
+ "bad_words_ids": null,
111
+ "begin_suppress_tokens": null,
112
+ "bos_token_id": 0,
113
+ "chunk_size_feed_forward": 0,
114
+ "cross_attention_hidden_size": null,
115
+ "decoder_start_token_id": null,
116
+ "diversity_penalty": 0.0,
117
+ "do_sample": false,
118
+ "early_stopping": false,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": 2,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "gradient_checkpointing": false,
126
+ "hidden_act": "gelu",
127
+ "hidden_dropout_prob": 0.1,
128
+ "hidden_size": 768,
129
+ "id2label": {
130
+ "0": "LABEL_0",
131
+ "1": "LABEL_1"
132
+ },
133
+ "ignore_attention_mask": false,
134
+ "initializer_range": 0.02,
135
+ "intermediate_size": 3072,
136
+ "is_decoder": false,
137
+ "is_encoder_decoder": false,
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "layer_norm_eps": 1e-05,
143
+ "length_penalty": 1.0,
144
+ "max_length": 20,
145
+ "max_position_embeddings": 4098,
146
+ "min_length": 0,
147
+ "model_type": "longformer",
148
+ "no_repeat_ngram_size": 0,
149
+ "num_attention_heads": 12,
150
+ "num_beam_groups": 1,
151
+ "num_beams": 1,
152
+ "num_hidden_layers": 12,
153
+ "num_return_sequences": 1,
154
+ "onnx_export": false,
155
+ "output_attentions": false,
156
+ "output_hidden_states": false,
157
+ "output_scores": false,
158
+ "pad_token_id": 1,
159
+ "position_embedding_type": "absolute",
160
+ "prefix": null,
161
+ "problem_type": null,
162
+ "pruned_heads": {},
163
+ "remove_invalid_values": false,
164
+ "repetition_penalty": 1.0,
165
+ "return_dict": true,
166
+ "return_dict_in_generate": false,
167
+ "sep_token_id": 2,
168
+ "suppress_tokens": null,
169
+ "task_specific_params": null,
170
+ "temperature": 1.0,
171
+ "tf_legacy_loss": false,
172
+ "tie_encoder_decoder": false,
173
+ "tie_word_embeddings": true,
174
+ "tokenizer_class": null,
175
+ "top_k": 50,
176
+ "top_p": 1.0,
177
+ "torch_dtype": "float32",
178
+ "torchscript": false,
179
+ "type_vocab_size": 1,
180
+ "typical_p": 1.0,
181
+ "use_bfloat16": false,
182
+ "use_cache": true,
183
+ "vocab_size": 50265
184
+ },
185
+ "eos_token_id": 2,
186
+ "is_encoder_decoder": true,
187
+ "length_penalty": 2.0,
188
+ "max_length": 512,
189
+ "max_position_embeddings": 1024,
190
+ "model_type": "encoder-decoder",
191
+ "no_repeat_ngram_size": 3,
192
+ "num_beams": 4,
193
+ "pad_token_id": 1,
194
+ "sep_token_id": 2,
195
+ "torch_dtype": "float32",
196
+ "transformers_version": "4.32.1"
197
+ }
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": "4.32.1"
7
+ }
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 sha256:35070bb03d851677b12955fa8ef8e438368961f09cc1b30e7496fe526ffb4419
3
+ size 1207095441
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 4096,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "LongformerTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff