tt1225 commited on
Commit
1c1c644
1 Parent(s): b966c1f
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bhavikardeshna/xlm-roberta-base-vietnamese",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "SUPPORTED",
16
+ "1": "REFUTED",
17
+ "2": "NEI"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "NEI": 2,
23
+ "REFUTED": 1,
24
+ "SUPPORTED": 0
25
+ },
26
+ "language": "english",
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "xlm-roberta",
30
+ "name": "XLMRoberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "output_past": true,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "multi_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.33.0",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 250002
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e499db8e6b684e924e91ff322456d9ae6a65035ccc58f1123847ffd00779ed6
3
+ size 1112252785
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304364e2e8d0071c6a3c44ea4415d5704600003380d38fa4ed620433afe7e82e
3
+ size 17082993
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "do_lower_case": false,
6
+ "eos_token": "</s>",
7
+ "full_tokenizer_file": null,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "max_length": 256,
17
+ "model_max_length": 512,
18
+ "pad_to_multiple_of": null,
19
+ "pad_token": "<pad>",
20
+ "pad_token_type_id": 0,
21
+ "padding_side": "right",
22
+ "sep_token": "</s>",
23
+ "sp_model_kwargs": {},
24
+ "stride": 128,
25
+ "tokenizer_class": "XLMRobertaTokenizer",
26
+ "truncation_side": "right",
27
+ "truncation_strategy": "only_second",
28
+ "unk_token": "<unk>"
29
+ }