sschet commited on
Commit
0bf30ac
1 Parent(s): 5cb803b

Upload 10 files

Browse files
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ datasets:
5
+ - tner/bc5cdr
6
+ - jnlpba
7
+ - bc2gm_corpus
8
+ - drAbreu/bc4chemd_ner
9
+ - linnaeus
10
+ - ncbi_disease
11
+ ---
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<mask>": 50000}
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RoBERTaMultiNER2"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "B",
14
+ "1": "I",
15
+ "2": "O"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "B": 0,
21
+ "I": 1,
22
+ "O": 2
23
+ },
24
+ "layer_norm_eps": 1e-05,
25
+ "max_position_embeddings": 514,
26
+ "model_type": "roberta",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 1,
30
+ "type_vocab_size": 1,
31
+ "vocab_size": 50008
32
+ }
labels.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ B
2
+ I
3
+ O
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 sha256:888fb45964e5847ad4279e402d64944b9d444ac4078d6b5c028dafd0d7009711
3
+ size 1458403691
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
+ {"special_tokens_map_file": null, "full_tokenizer_file": null}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c356c07703859c7b3213e31d81fc9df739747bbf4b3d537271b36708eaee613
3
+ size 1167
vocab.json ADDED
The diff for this file is too large to render. See raw diff