aplycaebous commited on
Commit
a7a03ab
1 Parent(s): ed065e9

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "csebuetnlp/banglabert",
3
+ "architectures": [
4
+ "ElectraForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 768,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "electra",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "summary_activation": "gelu",
21
+ "summary_last_dropout": 0.1,
22
+ "summary_type": "first",
23
+ "summary_use_proj": true,
24
+ "transformers_version": "4.5.1",
25
+ "type_vocab_size": 2,
26
+ "vocab_size": 32000
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9865ebfadc6f38ca385913d64bfa35eadfa03805aeefe42d8465ca075b353a78
3
+ size 442694675
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": false, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "csebuetnlp/banglabert", "do_basic_tokenize": true, "never_split": null}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f24963b485280a9eb872b7e98a46a2c87994cc90d2856c867e9831dc8b97f7
3
+ size 2351
vocab.txt ADDED
The diff for this file is too large to render. See raw diff