Upload 7 files
Browse files- added_tokens.json +1 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data/djh/plm/chinese-roberta-wwm-ext-large",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model_type": "bert",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pooler_fc_size": 768,
|
24 |
+
"pooler_num_attention_heads": 12,
|
25 |
+
"pooler_num_fc_layers": 3,
|
26 |
+
"pooler_size_per_head": 128,
|
27 |
+
"pooler_type": "first_token_transform",
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.20.0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 21128
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc902a1992b80b43f62e8114c8c41f7ba0e798c5d15fb39a169bb699e1b85d9b
|
3 |
+
size 1302328466
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"name_or_path": "/data/djh/plm/chinese-roberta-wwm-ext-large",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": "/data/djh/plm/chinese-roberta-wwm-ext-large/special_tokens_map.json",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|