Hugging Face's logo

a-mannion
/
bioroberta-es-umls-kgi

Fill-Mask
Transformers
PyTorch
Spanish
roberta
medical
Model card Files Community
a-mannion commited on
Commit
d84d835
·
verified ·
1 Parent(s): df95067

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +83 -1
  2. kgi_specific_config.json +29 -0
  3. pytorch_model.bin +2 -2
  4. special_tokens_map.json +61 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +65 -1
config.json CHANGED
@@ -1 +1,83 @@
1
- {"_name_or_path": "ap-mannion/kgi-bert-es", "activation": "gelu", "architectures": ["DistilBertModel"], "attention_dropout": 0.15, "dim": 768, "dropout": 0.05, "hidden_dim": 3072, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 12, "pad_token_id": 0, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "torch_dtype": "float32", "transformers_version": "4.27.4", "vocab_size": 50464}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "return_dict": true,
3
+ "output_hidden_states": false,
4
+ "output_attentions": false,
5
+ "torchscript": false,
6
+ "torch_dtype": null,
7
+ "use_bfloat16": false,
8
+ "tf_legacy_loss": false,
9
+ "pruned_heads": {},
10
+ "tie_word_embeddings": true,
11
+ "is_encoder_decoder": false,
12
+ "is_decoder": false,
13
+ "cross_attention_hidden_size": null,
14
+ "add_cross_attention": false,
15
+ "tie_encoder_decoder": false,
16
+ "max_length": 20,
17
+ "min_length": 0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "num_beams": 1,
21
+ "num_beam_groups": 1,
22
+ "diversity_penalty": 0.0,
23
+ "temperature": 1.0,
24
+ "top_k": 50,
25
+ "top_p": 1.0,
26
+ "typical_p": 1.0,
27
+ "repetition_penalty": 1.0,
28
+ "length_penalty": 1.0,
29
+ "no_repeat_ngram_size": 0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "bad_words_ids": null,
32
+ "num_return_sequences": 1,
33
+ "chunk_size_feed_forward": 0,
34
+ "output_scores": false,
35
+ "return_dict_in_generate": false,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "remove_invalid_values": false,
39
+ "exponential_decay_length_penalty": null,
40
+ "suppress_tokens": null,
41
+ "begin_suppress_tokens": null,
42
+ "architectures": [
43
+ "RobertaForMaskedLM"
44
+ ],
45
+ "finetuning_task": null,
46
+ "id2label": {
47
+ "0": "LABEL_0",
48
+ "1": "LABEL_1"
49
+ },
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "tokenizer_class": null,
55
+ "prefix": null,
56
+ "bos_token_id": 0,
57
+ "pad_token_id": 1,
58
+ "eos_token_id": 2,
59
+ "sep_token_id": null,
60
+ "decoder_start_token_id": null,
61
+ "task_specific_params": null,
62
+ "problem_type": null,
63
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-biomedical-clinical-es",
64
+ "transformers_version": "4.27.4",
65
+ "gradient_checkpointing": false,
66
+ "model_type": "roberta",
67
+ "vocab_size": 52008,
68
+ "hidden_size": 768,
69
+ "num_hidden_layers": 12,
70
+ "num_attention_heads": 12,
71
+ "hidden_act": "gelu",
72
+ "intermediate_size": 3072,
73
+ "hidden_dropout_prob": 0.1,
74
+ "attention_probs_dropout_prob": 0.1,
75
+ "max_position_embeddings": 514,
76
+ "type_vocab_size": 1,
77
+ "initializer_range": 0.02,
78
+ "layer_norm_eps": 1e-05,
79
+ "position_embedding_type": "absolute",
80
+ "use_cache": true,
81
+ "classifier_dropout": null,
82
+ "dim": 768
83
+ }
kgi_specific_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_labels_link_pred": 6,
3
+ "link_pred_dropout": 0.1,
4
+ "num_labels_triple_clf": 2,
5
+ "triple_clf_dropout": 0.1,
6
+ "task_weight_coefficients": [
7
+ 0.375,
8
+ 0.375,
9
+ 0.25
10
+ ],
11
+ "n_tasks": 4,
12
+ "_clf_classes": [
13
+ 52008,
14
+ 6,
15
+ 2,
16
+ 52008
17
+ ],
18
+ "_module_list": [
19
+ "lm_head",
20
+ "link_classifier",
21
+ "triple_classifier",
22
+ "lm_head"
23
+ ],
24
+ "_nonzero_task_weight_coefficients": [
25
+ 0.375,
26
+ 0.375,
27
+ 0.25
28
+ ]
29
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1897f2e28a57a679875b21976d3a84af33e3549e1a2ae06ae181b8eec90dc5f
3
- size 496885021
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54bd1e7524e099072a86f044e4a64c092744f5bf353606b9c8fe0b301d10fd0
3
+ size 671104738
special_tokens_map.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[SY]",
4
+ "[RO]",
5
+ "[RN]",
6
+ "[RB]",
7
+ "[CHD]",
8
+ "[RQ]",
9
+ "[PAR]",
10
+ "[HREL]"
11
+ ],
12
+ "bos_token": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "cls_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "mask_token": {
34
+ "content": "<mask>",
35
+ "lstrip": true,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "pad_token": {
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "unk_token": {
55
+ "content": "<unk>",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false
60
+ }
61
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,65 @@
1
- {"name_or_path": "", "model_max_length": 1000000000000000019884624838656, "model_input_names": ["input_ids", "token_type_ids", "attention_mask"]}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "max_len": 512,
37
+ "model_max_length": 256,
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
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }