fschlatt commited on
Commit
1b207b2
1 Parent(s): 2556e7e

initial commit

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "add_marker_tokens": false,
4
+ "architectures": [
5
+ "ColBertModel"
6
+ ],
7
+ "attend_to_doc_expanded_tokens": false,
8
+ "attend_to_query_expanded_tokens": true,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "backbone_model_type": "bert",
11
+ "classifier_dropout": null,
12
+ "doc_expansion": false,
13
+ "doc_length": 256,
14
+ "doc_pooling_strategy": null,
15
+ "embedding_dim": 128,
16
+ "gradient_checkpointing": false,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 768,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "col",
25
+ "normalize": false,
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "projection": "linear_no_bias",
31
+ "query_aggregation_function": "mean",
32
+ "query_expansion": true,
33
+ "query_length": 32,
34
+ "query_pooling_strategy": null,
35
+ "save_step": 44008,
36
+ "similarity_function": "dot",
37
+ "sparsification": null,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.42.4",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 30522
43
+ }
mask_scoring_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"query": null, "doc": "punctuation"}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f97b614c2a28ba0b9bc6b0c8680fe2e8ebcb473e112f4fb8132914226cd53b
3
+ size 438344632
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_marker_tokens": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "attend_to_doc_expanded_tokens": false,
46
+ "attend_to_query_expanded_tokens": true,
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "[CLS]",
49
+ "do_lower_case": true,
50
+ "doc_expansion": false,
51
+ "doc_length": 256,
52
+ "doc_token": "[DOC]",
53
+ "mask_token": "[MASK]",
54
+ "model_max_length": 512,
55
+ "pad_token": "[PAD]",
56
+ "query_expansion": true,
57
+ "query_length": 32,
58
+ "query_token": "[QUE]",
59
+ "sep_token": "[SEP]",
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizer",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff