Commit
•
8047dea
1
Parent(s):
21094d0
init
Browse files- README.md +3 -0
- config.json +32 -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
README.md
CHANGED
@@ -1,3 +1,6 @@
|
|
1 |
---
|
2 |
license: bsd
|
3 |
---
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: bsd
|
3 |
---
|
4 |
+
# contriever-base-chinese
|
5 |
+
|
6 |
+
* https://github.com/facebookresearch/contriever
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-chinese",
|
3 |
+
"architectures": [
|
4 |
+
"BertRetriver"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"pooling": "avg",
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.27.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 21128
|
32 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a3942d5153c7a3dbf026200a0b79c27e0a061d2b6a9be89961cb52a954be3a1
|
3 |
+
size 406778789
|
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": false,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": null,
|
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
|
|