KoichiYasuoka
commited on
Commit
β’
d9000cd
1
Parent(s):
ab046a1
model changed
Browse files- README.md +1 -1
- config.json +1 -7
- pytorch_model.bin +2 -2
- supar.model +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +9 -3
- vocab.txt +0 -0
README.md
CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: "token-classification"
|
|
16 |
|
17 |
## Model Description
|
18 |
|
19 |
-
This is a RoBERTa model pre-trained on Chinese texts (both simplified and traditional) for POS-tagging and dependency-parsing, derived from [
|
20 |
|
21 |
## How to Use
|
22 |
|
|
|
16 |
|
17 |
## Model Description
|
18 |
|
19 |
+
This is a RoBERTa model pre-trained on Chinese Wikipedia texts (both simplified and traditional) for POS-tagging and dependency-parsing, derived from [roberta-base-chinese](https://huggingface.co/KoichiYasuoka/roberta-base-chinese). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
|
20 |
|
21 |
## How to Use
|
22 |
|
config.json
CHANGED
@@ -5,7 +5,6 @@
|
|
5 |
"attention_probs_dropout_prob": 0.1,
|
6 |
"bos_token_id": 0,
|
7 |
"classifier_dropout": null,
|
8 |
-
"directionality": "bidi",
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
@@ -112,16 +111,11 @@
|
|
112 |
"num_attention_heads": 12,
|
113 |
"num_hidden_layers": 12,
|
114 |
"pad_token_id": 1,
|
115 |
-
"pooler_fc_size": 768,
|
116 |
-
"pooler_num_attention_heads": 12,
|
117 |
-
"pooler_num_fc_layers": 3,
|
118 |
-
"pooler_size_per_head": 128,
|
119 |
-
"pooler_type": "first_token_transform",
|
120 |
"position_embedding_type": "absolute",
|
121 |
"tokenizer_class": "BertTokenizerFast",
|
122 |
"torch_dtype": "float32",
|
123 |
"transformers_version": "4.22.1",
|
124 |
"type_vocab_size": 2,
|
125 |
"use_cache": true,
|
126 |
-
"vocab_size":
|
127 |
}
|
|
|
5 |
"attention_probs_dropout_prob": 0.1,
|
6 |
"bos_token_id": 0,
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
|
|
111 |
"num_attention_heads": 12,
|
112 |
"num_hidden_layers": 12,
|
113 |
"pad_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
114 |
"position_embedding_type": "absolute",
|
115 |
"tokenizer_class": "BertTokenizerFast",
|
116 |
"torch_dtype": "float32",
|
117 |
"transformers_version": "4.22.1",
|
118 |
"type_vocab_size": 2,
|
119 |
"use_cache": true,
|
120 |
+
"vocab_size": 26582
|
121 |
}
|
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:f72831ba79502d2e692459d79bc795a86ec6a3aab8c2f85dcbed55e8cb99006a
|
3 |
+
size 423672305
|
supar.model
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:b2bf95f715ff1fd628dac51042c70c1b1c3432e4d529537706edd68aa18997b6
|
3 |
+
size 478714981
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,13 +1,19 @@
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_basic_tokenize": true,
|
4 |
-
"do_lower_case":
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
-
"never_split":
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"pad_token": "[PAD]",
|
9 |
"sep_token": "[SEP]",
|
10 |
-
"strip_accents":
|
11 |
"tokenize_chinese_chars": true,
|
12 |
"tokenizer_class": "BertTokenizerFast",
|
13 |
"unk_token": "[UNK]"
|
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
+
"never_split": [
|
8 |
+
"[CLS]",
|
9 |
+
"[PAD]",
|
10 |
+
"[SEP]",
|
11 |
+
"[UNK]",
|
12 |
+
"[MASK]"
|
13 |
+
],
|
14 |
"pad_token": "[PAD]",
|
15 |
"sep_token": "[SEP]",
|
16 |
+
"strip_accents": false,
|
17 |
"tokenize_chinese_chars": true,
|
18 |
"tokenizer_class": "BertTokenizerFast",
|
19 |
"unk_token": "[UNK]"
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|