Added tokenizer config files
Browse files- config.json +2 -2
- pytorch_model.bin +2 -2
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
@@ -27,7 +27,7 @@
|
|
27 |
"position_embedding_type": "absolute",
|
28 |
"problem_type": "single_label_classification",
|
29 |
"torch_dtype": "float32",
|
30 |
-
"transformers_version": "4.
|
31 |
"type_vocab_size": 2,
|
32 |
"use_cache": true,
|
33 |
"vocab_size": 31090
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "biodatlab/score-claim-identification",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
27 |
"position_embedding_type": "absolute",
|
28 |
"problem_type": "single_label_classification",
|
29 |
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.29.2",
|
31 |
"type_vocab_size": 2,
|
32 |
"use_cache": true,
|
33 |
"vocab_size": 31090
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98338e029183fa8f7915a099da287f0e9facea9720165de1b73f092bbc7d874
|
3 |
+
size 439750005
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
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 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|