sayyedAhmed
commited on
Commit
•
493bdf0
1
Parent(s):
9aa0c1a
Upload 6 files
Browse files- config.json +102 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sakonii/distilbert-base-nepali",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-GOVERNMENT",
|
14 |
+
"2": "I-GOVERNMENT",
|
15 |
+
"3": "B-PRIVATE",
|
16 |
+
"4": "I-PRIVATE",
|
17 |
+
"5": "B-MALE",
|
18 |
+
"6": "I-MALE",
|
19 |
+
"7": "B-FEMALE",
|
20 |
+
"8": "I-FEMALE",
|
21 |
+
"9": "B-PROVINCE_2",
|
22 |
+
"10": "I-PROVINCE_2",
|
23 |
+
"11": "B-PROVINCE_5",
|
24 |
+
"12": "I-PROVINCE_5",
|
25 |
+
"13": "B-OTHER_PROVINCES",
|
26 |
+
"14": "I-OTHER_PROVINCES",
|
27 |
+
"15": "B-MADHESI_OTHER_CAST",
|
28 |
+
"16": "I-MADHESI_OTHER_CAST",
|
29 |
+
"17": "B-MADHESI_DALIT",
|
30 |
+
"18": "I-MADHESI_DALIT",
|
31 |
+
"19": "B-HILL_DALIT",
|
32 |
+
"20": "I-HILL_DALIT",
|
33 |
+
"21": "B-MOUNTAIN_HILL_JANAJATI",
|
34 |
+
"22": "I-MOUNTAIN_HILL_JANAJATI",
|
35 |
+
"23": "B-TERAI_JANAJATI",
|
36 |
+
"24": "I-TERAI_JANAJATI",
|
37 |
+
"25": "B-MUSLIM",
|
38 |
+
"26": "I-MUSLIM",
|
39 |
+
"27": "B-OTHER_MARGINALIZED",
|
40 |
+
"28": "I-OTHER_MARGINALIZED",
|
41 |
+
"29": "B-BRAHMIN",
|
42 |
+
"30": "I-BRAHMIN",
|
43 |
+
"31": "B-THAKURI",
|
44 |
+
"32": "I-THAKURI",
|
45 |
+
"33": "B-CHETTRI",
|
46 |
+
"34": "I-CHETTRI",
|
47 |
+
"35": "B-UPPER_CASTE_NEWAR",
|
48 |
+
"36": "I-UPPER_CASTE_NEWAR"
|
49 |
+
},
|
50 |
+
"initializer_range": 0.02,
|
51 |
+
"label2id": {
|
52 |
+
"B-BRAHMIN": 29,
|
53 |
+
"B-CHETTRI": 33,
|
54 |
+
"B-FEMALE": 7,
|
55 |
+
"B-GOVERNMENT": 1,
|
56 |
+
"B-HILL_DALIT": 19,
|
57 |
+
"B-MADHESI_DALIT": 17,
|
58 |
+
"B-MADHESI_OTHER_CAST": 15,
|
59 |
+
"B-MALE": 5,
|
60 |
+
"B-MOUNTAIN_HILL_JANAJATI": 21,
|
61 |
+
"B-MUSLIM": 25,
|
62 |
+
"B-OTHER_MARGINALIZED": 27,
|
63 |
+
"B-OTHER_PROVINCES": 13,
|
64 |
+
"B-PRIVATE": 3,
|
65 |
+
"B-PROVINCE_2": 9,
|
66 |
+
"B-PROVINCE_5": 11,
|
67 |
+
"B-TERAI_JANAJATI": 23,
|
68 |
+
"B-THAKURI": 31,
|
69 |
+
"B-UPPER_CASTE_NEWAR": 35,
|
70 |
+
"I-BRAHMIN": 30,
|
71 |
+
"I-CHETTRI": 34,
|
72 |
+
"I-FEMALE": 8,
|
73 |
+
"I-GOVERNMENT": 2,
|
74 |
+
"I-HILL_DALIT": 20,
|
75 |
+
"I-MADHESI_DALIT": 18,
|
76 |
+
"I-MADHESI_OTHER_CAST": 16,
|
77 |
+
"I-MALE": 6,
|
78 |
+
"I-MOUNTAIN_HILL_JANAJATI": 22,
|
79 |
+
"I-MUSLIM": 26,
|
80 |
+
"I-OTHER_MARGINALIZED": 28,
|
81 |
+
"I-OTHER_PROVINCES": 14,
|
82 |
+
"I-PRIVATE": 4,
|
83 |
+
"I-PROVINCE_2": 10,
|
84 |
+
"I-PROVINCE_5": 12,
|
85 |
+
"I-TERAI_JANAJATI": 24,
|
86 |
+
"I-THAKURI": 32,
|
87 |
+
"I-UPPER_CASTE_NEWAR": 36,
|
88 |
+
"O": 0
|
89 |
+
},
|
90 |
+
"max_position_embeddings": 512,
|
91 |
+
"model_type": "distilbert",
|
92 |
+
"n_heads": 12,
|
93 |
+
"n_layers": 6,
|
94 |
+
"pad_token_id": 0,
|
95 |
+
"qa_dropout": 0.1,
|
96 |
+
"seq_classif_dropout": 0.2,
|
97 |
+
"sinusoidal_pos_embds": false,
|
98 |
+
"tie_weights_": true,
|
99 |
+
"torch_dtype": "float32",
|
100 |
+
"transformers_version": "4.28.0",
|
101 |
+
"vocab_size": 30522
|
102 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6c0d46cfd3a15b2469133e5425acf52116baeab967810938194b120f538910c
|
3 |
+
size 265600165
|
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
The diff for this file is too large to render.
See raw diff
|
|
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": false,
|
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 sha256:3a9283f0f5f4362e9968b939faf1a37e9fdb01af22a6dd79926bd6c218f4ddfc
|
3 |
+
size 3579
|