KoichiYasuoka commited on
Commit
c3e10cc
1 Parent(s): 0ffd133

initial release

Browse files
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "th"
4
+ tags:
5
+ - "thai"
6
+ - "masked-lm"
7
+ - "wikipedia"
8
+ license: "apache-2.0"
9
+ pipeline_tag: "fill-mask"
10
+ mask_token: "<mask>"
11
+ widget:
12
+ - text: "แผนกนี้กำลังเผชิญกับความ<mask>ใหม่"
13
+ ---
14
+
15
+ # roberta-base-thai-syllable
16
+
17
+ ## Model Description
18
+
19
+ This is a RoBERTa model pre-trained on Thai Wikipedia texts, derived from [wangchanberta-base-wiki-syllable](https://huggingface.co/airesearch/wangchanberta-base-wiki-syllable). Character-embeddings are modified to use BertTokenizerFast. You can fine-tune `roberta-base-thai-syllable` for downstream tasks, such as POS-tagging, dependency-parsing, and so on.
20
+
21
+ ## How to Use
22
+
23
+ ```py
24
+ from transformers import AutoTokenizer,AutoModelForMaskedLM
25
+ tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-thai-syllable")
26
+ model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-base-thai-syllable")
27
+ ```
28
+
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "mask_token_id": 4,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "tokenizer_class": "BertTokenizerFast",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.10.0",
26
+ "type_vocab_size": 1,
27
+ "unk_token_id": 3,
28
+ "use_cache": true,
29
+ "vocab_size": 33144
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a586df08fb40079c21f555426486f93c9a7ff6e82d75cf095b0c83894a5a7e9
3
+ size 446197851
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 416, "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff