lalital commited on
Commit
8cde0de
1 Parent(s): 247d65f

Add pretrained wangchanberta-base-att-spm-uncased model

Browse files

Vocab: SentencePiece
Vocab size: 25,000
Tokenizer class: transformers.CamembertTokenizer
Checkpoint: 360,000

Version 1.0

Files changed (2) hide show
  1. config.json +23 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "roberta",
17
+ "num_attention_head": 12,
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "type_vocab_size": 1,
22
+ "vocab_size": 25005
23
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4897cb54fac5920be285e1589855866093c8d5cdfc5932cecd0900a50bdba372
3
+ size 423498558