Upload 8 files
Browse files- config.json +110 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SCAI-BIO/bio-gottbert-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "B-Mutation",
|
16 |
+
"1": "B-ExpressionSignal",
|
17 |
+
"2": "B-PolaritySignal",
|
18 |
+
"3": "I-HematoDiagnosis",
|
19 |
+
"4": "I-MorphologicAbnormality",
|
20 |
+
"5": "B-Infection",
|
21 |
+
"6": "I-Infection",
|
22 |
+
"7": "I-Proliferation",
|
23 |
+
"8": "B-Hematopoiesis",
|
24 |
+
"9": "I-DiagnosisType",
|
25 |
+
"10": "I-CellAssociation",
|
26 |
+
"11": "B-SizeSignal",
|
27 |
+
"12": "I-ShiftSignal",
|
28 |
+
"13": "I-PolaritySignal",
|
29 |
+
"14": "O",
|
30 |
+
"15": "B-AmountSignal",
|
31 |
+
"16": "B-MalignancySignal",
|
32 |
+
"17": "I-SizeSignal",
|
33 |
+
"18": "I-OtherDiagnosis",
|
34 |
+
"19": "I-MalignancySignal",
|
35 |
+
"20": "B-Expression",
|
36 |
+
"21": "B-DiagnosisType",
|
37 |
+
"22": "B-Proliferation",
|
38 |
+
"23": "I-Expression",
|
39 |
+
"24": "B-QuantitySignal",
|
40 |
+
"25": "B-MorphologicAbnormality",
|
41 |
+
"26": "B-ShiftSignal",
|
42 |
+
"27": "B-HematoDiagnosis",
|
43 |
+
"28": "B-CellType",
|
44 |
+
"29": "B-OtherDiagnosis",
|
45 |
+
"30": "B-ClonalitySignal",
|
46 |
+
"31": "B-CellAssociation",
|
47 |
+
"32": "I-QuantitySignal",
|
48 |
+
"33": "I-Mutation",
|
49 |
+
"34": "I-Hematopoiesis",
|
50 |
+
"35": "I-CellType",
|
51 |
+
"36": "I-AmountSignal",
|
52 |
+
"37": "I-ClonalitySignal",
|
53 |
+
"38": "I-ExpressionSignal"
|
54 |
+
},
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 3072,
|
57 |
+
"label2id": {
|
58 |
+
"B-AmountSignal": 15,
|
59 |
+
"B-CellAssociation": 31,
|
60 |
+
"B-CellType": 28,
|
61 |
+
"B-ClonalitySignal": 30,
|
62 |
+
"B-DiagnosisType": 21,
|
63 |
+
"B-Expression": 20,
|
64 |
+
"B-ExpressionSignal": 1,
|
65 |
+
"B-HematoDiagnosis": 27,
|
66 |
+
"B-Hematopoiesis": 8,
|
67 |
+
"B-Infection": 5,
|
68 |
+
"B-MalignancySignal": 16,
|
69 |
+
"B-MorphologicAbnormality": 25,
|
70 |
+
"B-Mutation": 0,
|
71 |
+
"B-OtherDiagnosis": 29,
|
72 |
+
"B-PolaritySignal": 2,
|
73 |
+
"B-Proliferation": 22,
|
74 |
+
"B-QuantitySignal": 24,
|
75 |
+
"B-ShiftSignal": 26,
|
76 |
+
"B-SizeSignal": 11,
|
77 |
+
"I-AmountSignal": 36,
|
78 |
+
"I-CellAssociation": 10,
|
79 |
+
"I-CellType": 35,
|
80 |
+
"I-ClonalitySignal": 37,
|
81 |
+
"I-DiagnosisType": 9,
|
82 |
+
"I-Expression": 23,
|
83 |
+
"I-ExpressionSignal": 38,
|
84 |
+
"I-HematoDiagnosis": 3,
|
85 |
+
"I-Hematopoiesis": 34,
|
86 |
+
"I-Infection": 6,
|
87 |
+
"I-MalignancySignal": 19,
|
88 |
+
"I-MorphologicAbnormality": 4,
|
89 |
+
"I-Mutation": 33,
|
90 |
+
"I-OtherDiagnosis": 18,
|
91 |
+
"I-PolaritySignal": 13,
|
92 |
+
"I-Proliferation": 7,
|
93 |
+
"I-QuantitySignal": 32,
|
94 |
+
"I-ShiftSignal": 12,
|
95 |
+
"I-SizeSignal": 17,
|
96 |
+
"O": 14
|
97 |
+
},
|
98 |
+
"layer_norm_eps": 1e-05,
|
99 |
+
"max_position_embeddings": 514,
|
100 |
+
"model_type": "roberta",
|
101 |
+
"num_attention_heads": 12,
|
102 |
+
"num_hidden_layers": 12,
|
103 |
+
"pad_token_id": 1,
|
104 |
+
"position_embedding_type": "absolute",
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.36.2",
|
107 |
+
"type_vocab_size": 1,
|
108 |
+
"use_cache": true,
|
109 |
+
"vocab_size": 52009
|
110 |
+
}
|
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 sha256:15104c354ea0e72a89d2f440b29986c6526d7fb69f2a26e6190bc7699464b564
|
3 |
+
size 501721628
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
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 |
+
"52008": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88f62f38ff7a68f342bf5f126db93d90e0c57d9432c66949d98d0dc4cd25f4a
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|