Snow-White-995
commited on
Commit
•
0bf0aa4
1
Parent(s):
e9fbc55
Upload 11 files
Browse files- bert/chinese-roberta-wwm-ext-large/added_tokens.json +1 -0
- bert/chinese-roberta-wwm-ext-large/config.json +28 -0
- bert/chinese-roberta-wwm-ext-large/pytorch_model.bin +3 -0
- bert/chinese-roberta-wwm-ext-large/special_tokens_map.json +1 -0
- bert/chinese-roberta-wwm-ext-large/tokenizer.json +0 -0
- bert/chinese-roberta-wwm-ext-large/tokenizer_config.json +1 -0
- bert/chinese-roberta-wwm-ext-large/vocab.txt +0 -0
- bert/deberta-v3-large/config.json +22 -0
- bert/deberta-v3-large/pytorch_model.bin +3 -0
- bert/deberta-v3-large/spm.model +3 -0
- bert/deberta-v3-large/tokenizer_config.json +4 -0
bert/chinese-roberta-wwm-ext-large/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
bert/chinese-roberta-wwm-ext-large/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pooler_fc_size": 768,
|
22 |
+
"pooler_num_attention_heads": 12,
|
23 |
+
"pooler_num_fc_layers": 3,
|
24 |
+
"pooler_size_per_head": 128,
|
25 |
+
"pooler_type": "first_token_transform",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"vocab_size": 21128
|
28 |
+
}
|
bert/chinese-roberta-wwm-ext-large/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ac62d49144d770c5ca9a5d1d3039c4995665a080febe63198189857c6bd11cd
|
3 |
+
size 1306484351
|
bert/chinese-roberta-wwm-ext-large/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
bert/chinese-roberta-wwm-ext-large/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
bert/chinese-roberta-wwm-ext-large/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"init_inputs": []}
|
bert/chinese-roberta-wwm-ext-large/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
bert/deberta-v3-large/config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "deberta-v2",
|
3 |
+
"attention_probs_dropout_prob": 0.1,
|
4 |
+
"hidden_act": "gelu",
|
5 |
+
"hidden_dropout_prob": 0.1,
|
6 |
+
"hidden_size": 1024,
|
7 |
+
"initializer_range": 0.02,
|
8 |
+
"intermediate_size": 4096,
|
9 |
+
"max_position_embeddings": 512,
|
10 |
+
"relative_attention": true,
|
11 |
+
"position_buckets": 256,
|
12 |
+
"norm_rel_ebd": "layer_norm",
|
13 |
+
"share_att_key": true,
|
14 |
+
"pos_att_type": "p2c|c2p",
|
15 |
+
"layer_norm_eps": 1e-7,
|
16 |
+
"max_relative_positions": -1,
|
17 |
+
"position_biased_input": false,
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"type_vocab_size": 0,
|
21 |
+
"vocab_size": 128100
|
22 |
+
}
|
bert/deberta-v3-large/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5b5d93e2db101aaf281df0ea1216c07ad73620ff59c5b42dccac4bf2eef5b5
|
3 |
+
size 873673253
|
bert/deberta-v3-large/spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
bert/deberta-v3-large/tokenizer_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": false,
|
3 |
+
"vocab_type": "spm"
|
4 |
+
}
|