lalital commited on
Commit
495a89a
1 Parent(s): 62c98c6

Add wangchanberta-base-thwiki-spm model

Browse files

- Vocab: SentencePiece
- Vocab size: 24,000
- Tokenizer class: thai2transformers.tokenizers.ThaiRobertaTokenizer
- Checkpoint: 7,000

README.md CHANGED
@@ -1 +1 @@
1
- wangchanberta-base-wiki-spm
1
+ ## wangchanberta-base-wiki-spm
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
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": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "mask_token_id": 4,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "type_vocab_size": 1,
22
+ "unk_token_id": 3,
23
+ "vocab_size": 24000
24
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9559c5fd6e545c17f4b7e73255c02e48cd17c0844ac5cbc7e4078cc793fbb0
3
+ size 418088102
sentencepiece.bpe.model ADDED
Binary file
sentencepiece.bpe.vocab ADDED
The diff for this file is too large to render. See raw diff