Jo Kristian Bergum commited on
Commit
df12733
1 Parent(s): e7e3092

Import model weights and tokenizer configuration

Browse files
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-medium-uncased",
3
+ "architectures": [
4
+ "ColBERT"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 512,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2048,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 8,
17
+ "num_hidden_layers": 8,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "type_vocab_size": 2,
21
+ "vocab_size": 30522
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f33bb114e0f9ae177e2eedddd880170300957ddecd2352fd17bda3e6719bd6
3
+ size 165618505
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff