Upload 6 files
Browse files- config.json +56 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer_config.json +21 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "l",
|
15 |
+
"1": "u",
|
16 |
+
"2": "?u",
|
17 |
+
"3": "?l",
|
18 |
+
"4": "!u",
|
19 |
+
"5": "!l",
|
20 |
+
"6": ",u",
|
21 |
+
"7": ",l",
|
22 |
+
"8": ".u",
|
23 |
+
"9": ".l",
|
24 |
+
"10": ":l",
|
25 |
+
"11": ":u"
|
26 |
+
},
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"l": 0,
|
31 |
+
"u": 1,
|
32 |
+
":l": 10,
|
33 |
+
":u": 11,
|
34 |
+
"?u": 2,
|
35 |
+
"?l": 3,
|
36 |
+
"!u": 4,
|
37 |
+
"!l": 5,
|
38 |
+
",u": 6,
|
39 |
+
",l": 7,
|
40 |
+
".u": 8,
|
41 |
+
".l": 9
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-05,
|
44 |
+
"max_position_embeddings": 514,
|
45 |
+
"model_type": "xlm-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 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.25.1",
|
53 |
+
"type_vocab_size": 1,
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 250002
|
56 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5ff1f39b2d4e4fb039444b7fd8f4b3a1b6a41a0af1fa8e30e37f08bfba528af
|
3 |
+
size 1109921837
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "xlm-roberta-base",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"sp_model_kwargs": {},
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbb1e8540a1d631cf63ae3be1d650509066fb11342362e5ea191ee5d320187f2
|
3 |
+
size 3387
|