Upload 11 files
Browse files- config.json +58 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../02_dependencies/hubert-base-cc",
|
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": "O",
|
14 |
+
"1": "B-COMMA",
|
15 |
+
"2": "B-DOT",
|
16 |
+
"3": "B-EXCLAM",
|
17 |
+
"4": "B-QUES",
|
18 |
+
"5": "B-HYPHEN",
|
19 |
+
"6": "B-COLON",
|
20 |
+
"7": "B-UPPER",
|
21 |
+
"8": "B-UPCOMMA",
|
22 |
+
"9": "B-UPDOT",
|
23 |
+
"10": "B-UPEXCLAM",
|
24 |
+
"11": "B-UPQUES",
|
25 |
+
"12": "B-UPHYPHEN",
|
26 |
+
"13": "B-UPCOLON"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"B-COLON": 6,
|
32 |
+
"B-COMMA": 1,
|
33 |
+
"B-DOT": 2,
|
34 |
+
"B-EXCLAM": 3,
|
35 |
+
"B-HYPHEN": 5,
|
36 |
+
"B-QUES": 4,
|
37 |
+
"B-UPCOLON": 13,
|
38 |
+
"B-UPCOMMA": 8,
|
39 |
+
"B-UPDOT": 9,
|
40 |
+
"B-UPEXCLAM": 10,
|
41 |
+
"B-UPHYPHEN": 12,
|
42 |
+
"B-UPPER": 7,
|
43 |
+
"B-UPQUES": 11,
|
44 |
+
"O": 0
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-12,
|
47 |
+
"max_position_embeddings": 512,
|
48 |
+
"model_type": "bert",
|
49 |
+
"num_attention_heads": 12,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"pad_token_id": 0,
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.28.0",
|
55 |
+
"type_vocab_size": 2,
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 32001
|
58 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2db5a551d3511a1f1fa2d3836f3f8170aab0657401cfefc5d33be7e2669c566
|
3 |
+
size 880423301
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7cc21ab4321fa96c3839c0400567c8c9b3518607ab630b2795a24bde9229079
|
3 |
+
size 440225261
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb31b249f260e8942cc5282e281d1ae946e99c1ea745157be2e3eacb3303bc3
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5178efbc3cd92ff5d1a06beec371dbeedd5b33597655eaeb9623642fcc786b00
|
3 |
+
size 627
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"full_tokenizer_file": null,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_len": 512,
|
9 |
+
"model_max_length": 1000000000000000019884624838656,
|
10 |
+
"never_split": null,
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b2b2a18f45dfc6fb37faa55b622c816a695cad2c7d18de94a73dafaf2430922
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|