Shufan JIANG commited on
Commit
7e76b17
1 Parent(s): 2993cbf

add fine-tuned roberta-base model for definiendum extraction

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-MATH_TERM",
15
+ "1": "I-MATH_TERM",
16
+ "2": "O"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-MATH_TERM": 0,
22
+ "I-MATH_TERM": 1,
23
+ "O": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.30.2",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 50265
37
+ }
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:a648db999bbc6e1c5e7325bc6663d008aebe8f13fae8db07d79d2d0e80dd0c46
3
+ size 496302125
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "from_tf": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff