Upload 7 files
Browse files- config.json +67 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "l",
|
14 |
+
"1": "u",
|
15 |
+
"2": "¿u",
|
16 |
+
"3": "¿l",
|
17 |
+
"4": "?u",
|
18 |
+
"5": "?l",
|
19 |
+
"6": "¡l",
|
20 |
+
"7": "¡u",
|
21 |
+
"8": "!u",
|
22 |
+
"9": "!l",
|
23 |
+
"10": ",u",
|
24 |
+
"11": ",l",
|
25 |
+
"12": ".u",
|
26 |
+
"13": ".l",
|
27 |
+
"14": ":u",
|
28 |
+
"15": ":l",
|
29 |
+
"16": "¿?u",
|
30 |
+
"17": "¡!u"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"l": 0,
|
36 |
+
"u": 1,
|
37 |
+
",u": 10,
|
38 |
+
",l": 11,
|
39 |
+
".u": 12,
|
40 |
+
".l": 13,
|
41 |
+
":u": 14,
|
42 |
+
":l": 15,
|
43 |
+
"¿?u": 16,
|
44 |
+
"¡!u": 17,
|
45 |
+
"¿u": 2,
|
46 |
+
"¿l": 3,
|
47 |
+
"?u": 4,
|
48 |
+
"?l": 5,
|
49 |
+
"¡l": 6,
|
50 |
+
"¡u": 7,
|
51 |
+
"!u": 8,
|
52 |
+
"!l": 9
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-12,
|
55 |
+
"max_position_embeddings": 512,
|
56 |
+
"model_type": "bert",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"output_past": true,
|
60 |
+
"pad_token_id": 1,
|
61 |
+
"position_embedding_type": "absolute",
|
62 |
+
"torch_dtype": "float32",
|
63 |
+
"transformers_version": "4.25.1",
|
64 |
+
"type_vocab_size": 2,
|
65 |
+
"use_cache": true,
|
66 |
+
"vocab_size": 31002
|
67 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a4491ad93a725b4ebb3f6849aa5084ba4d4638f03dbe12a7b5fb46549fd2480
|
3 |
+
size 437168685
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/home/ronghao/.cache/huggingface/hub/models--dccuchile--bert-base-spanish-wwm-cased/snapshots/56a7647b957a4230fc3f80dafbe80f2ba9b0de73/special_tokens_map.json",
|
12 |
+
"strip_accents": false,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afefb788f5b5ec2cc8327fad747b3fbb8116575103534aeaa5f67938e1b880ee
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|