bogdankostic commited on
Commit
a34edf5
1 Parent(s): 7049dfa

Add model files

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepset/bert-small-mm_retrieval-question_encoder",
3
+ "architectures": [
4
+ "DPRQuestionEncoder"
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
+ "language": "english",
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "dpr",
17
+ "name": "DPRQuestionEncoder",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 4,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "projection_dim": 0,
23
+ "revision": null,
24
+ "transformers_version": "4.7.0",
25
+ "type_vocab_size": 2,
26
+ "vocab_size": 30522
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ddc04b664c0a0c8b3e0005312a274d78081b72252fb5d9b6c9d87f7b4ef332
3
+ size 115089165
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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, "special_tokens_map_file": null, "name_or_path": "deepset/bert-small-mm_retrieval-question_encoder", "do_basic_tokenize": true, "never_split": null, "max_len": 512}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff