bishaldpande
commited on
Commit
•
5180c15
1
Parent(s):
d0f13a5
initial commit
Browse files- .gitattributes +3 -0
- README.md +3 -0
- config.json +54 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ 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 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
37 |
+
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
# Info
|
2 |
+
|
3 |
+
NER model trained on everest ner dataset for Nepali NER.
|
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
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": "O",
|
15 |
+
"1": "B-Person",
|
16 |
+
"2": "I-Person",
|
17 |
+
"3": "B-Organization",
|
18 |
+
"4": "I-Organization",
|
19 |
+
"5": "B-Location",
|
20 |
+
"6": "I-Location",
|
21 |
+
"7": "B-Event",
|
22 |
+
"8": "I-Event",
|
23 |
+
"9": "B-Date",
|
24 |
+
"10": "I-Date"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"B-Date": 9,
|
30 |
+
"B-Event": 7,
|
31 |
+
"B-Location": 5,
|
32 |
+
"B-Organization": 3,
|
33 |
+
"B-Person": 1,
|
34 |
+
"I-Date": 10,
|
35 |
+
"I-Event": 8,
|
36 |
+
"I-Location": 6,
|
37 |
+
"I-Organization": 4,
|
38 |
+
"I-Person": 2,
|
39 |
+
"O": 0
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-05,
|
42 |
+
"max_position_embeddings": 514,
|
43 |
+
"model_type": "xlm-roberta",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"output_past": true,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"position_embedding_type": "absolute",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.18.0",
|
51 |
+
"type_vocab_size": 1,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 250002
|
54 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54029b8e59f16c81e0433c5c4a036fea3082209ad2dda00ab6119a5866387fdb
|
3 |
+
size 1109917105
|
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 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
3 |
+
size 17082660
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c018695dd08c2c43003f9c4df31e22808fa02c93bf63579d73022334d1195f38
|
3 |
+
size 3119
|