nbroad HF staff commited on
Commit
71a64f9
1 Parent(s): 2084fe4

add files for TEI

Browse files
.gitattributes CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,15 +1,23 @@
1
  {
2
- "_name_or_path": "/data/KILT/qa/nq/models/reranker_stage1",
3
  "architectures": [
4
  "BertForSequenceClassification"
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": 768,
 
 
 
11
  "initializer_range": 0.02,
12
  "intermediate_size": 3072,
 
 
 
 
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
  "model_type": "bert",
@@ -18,7 +26,8 @@
18
  "output_past": true,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
- "transformers_version": "4.3.2",
 
22
  "type_vocab_size": 2,
23
  "use_cache": true,
24
  "vocab_size": 30522
 
1
  {
2
+ "_name_or_path": "ibm/re2g-reranker-nq",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
  "initializer_range": 0.02,
16
  "intermediate_size": 3072,
17
+ "label2id": {
18
+ "negative": 0,
19
+ "positive": 1
20
+ },
21
  "layer_norm_eps": 1e-12,
22
  "max_position_embeddings": 512,
23
  "model_type": "bert",
 
26
  "output_past": true,
27
  "pad_token_id": 0,
28
  "position_embedding_type": "absolute",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.1",
31
  "type_vocab_size": 2,
32
  "use_cache": true,
33
  "vocab_size": 30522
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e60ebd6c86ccbb58217ba05a5056bfb4c53fe589077d498c3d6b7eb1bdeebf9
3
+ size 437958648
special_tokens_map.json CHANGED
@@ -1 +1,7 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
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 CHANGED
@@ -1 +1,58 @@
1
- {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/4d0fa11bbe1deb7997febb2e52bd0163cbe96e544e88da5610c4c2517ca7386f.60fcb958324e8baca172b9bf464ef31dd71d694d16137059005be28205a96366", "tokenizer_file": null, "name_or_path": "/data/KILT/qa/nq/models/reranker_stage1"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }