duwuonline
commited on
Commit
•
7c56373
1
Parent(s):
421bbe7
mymodel-classify-category-news
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +57 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +19 -0
- training_args.bin +3 -0
.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
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B\u1ea5t \u0111\u1ed9ng s\u1ea3n",
|
15 |
+
"1": "Du l\u1ecbch",
|
16 |
+
"2": "Gi\u00e1o d\u1ee5c",
|
17 |
+
"3": "Gi\u1ea3i tr\u00ed",
|
18 |
+
"4": "Kinh doanh",
|
19 |
+
"5": "Ph\u00e1p lu\u1eadt",
|
20 |
+
"6": "S\u1ee9c kh\u1ecfe",
|
21 |
+
"7": "Th\u1ebf gi\u1edbi",
|
22 |
+
"8": "Th\u1ec3 thao",
|
23 |
+
"9": "Th\u1eddi s\u1ef1",
|
24 |
+
"10": "Xe",
|
25 |
+
"11": "\u0110\u1eddi s\u1ed1ng"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"B\u1ea5t \u0111\u1ed9ng s\u1ea3n": 0,
|
31 |
+
"Du l\u1ecbch": 1,
|
32 |
+
"Gi\u00e1o d\u1ee5c": 2,
|
33 |
+
"Gi\u1ea3i tr\u00ed": 3,
|
34 |
+
"Kinh doanh": 4,
|
35 |
+
"Ph\u00e1p lu\u1eadt": 5,
|
36 |
+
"S\u1ee9c kh\u1ecfe": 6,
|
37 |
+
"Th\u1ebf gi\u1edbi": 7,
|
38 |
+
"Th\u1ec3 thao": 8,
|
39 |
+
"Th\u1eddi s\u1ef1": 9,
|
40 |
+
"Xe": 10,
|
41 |
+
"\u0110\u1eddi s\u1ed1ng": 11
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-05,
|
44 |
+
"max_position_embeddings": 514,
|
45 |
+
"model_type": "roberta",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"output_past": true,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"position_embedding_type": "absolute",
|
51 |
+
"problem_type": "multi_label_classification",
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.31.0",
|
54 |
+
"type_vocab_size": 1,
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 250002
|
57 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b3918b09efe8e32320ed525fdb677bb9e11c7f1b5fdac141696b4c9b3f9ebb2
|
3 |
+
size 1112280433
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf7d585926000ffec2c828378ac39314f973f4f580a3be19026fe40f6690c66f
|
3 |
+
size 17082925
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b74ae9a8397ccd00acd09f3a3eb446159e19b87d44edd4556f0a69105339e73e
|
3 |
+
size 3963
|