hghaan commited on
Commit
f1ccd6c
·
verified ·
1 Parent(s): a41601a
config.json CHANGED
@@ -1,51 +1,26 @@
1
  {
2
- "_name_or_path": "Alibaba-NLP/gte-multilingual-reranker-base",
3
  "architectures": [
4
- "NewForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
- "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
- "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
- "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
- "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
- "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
- "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
- },
16
- "classifier_dropout": 0.0,
17
  "hidden_act": "gelu",
18
  "hidden_dropout_prob": 0.1,
19
  "hidden_size": 768,
20
- "id2label": {
21
- "0": "LABEL_0"
22
- },
23
  "initializer_range": 0.02,
24
  "intermediate_size": 3072,
25
- "label2id": {
26
- "LABEL_0": 0
27
- },
28
  "layer_norm_eps": 1e-12,
29
- "layer_norm_type": "layer_norm",
30
- "logn_attention_clip1": false,
31
- "logn_attention_scale": false,
32
- "max_position_embeddings": 8192,
33
- "model_type": "new",
34
  "num_attention_heads": 12,
35
  "num_hidden_layers": 12,
36
- "pack_qkv": true,
37
- "pad_token_id": 1,
38
- "position_embedding_type": "rope",
39
- "problem_type": "regression",
40
- "rope_scaling": {
41
- "factor": 8.0,
42
- "type": "ntk"
43
- },
44
- "rope_theta": 20000,
45
  "torch_dtype": "float32",
46
- "transformers_version": "4.47.0",
47
- "type_vocab_size": 1,
48
- "unpad_inputs": false,
49
- "use_memory_efficient_attention": false,
50
- "vocab_size": 250048
51
  }
 
1
  {
 
2
  "architectures": [
3
+ "BertForSequenceClassification"
4
  ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
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",
 
 
 
16
  "num_attention_heads": 12,
17
  "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.51.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 28996
 
26
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06182f4497ff7469e9a41b09e64e130b3e858c5a828c844ce665bffbd3ba607e
3
- size 1223854204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebaadb06be2de77d494015abd58176d10628aa76ab9c37fb58f31d3b9eb5aff2
3
+ size 433270768
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
- size 17082999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea3479edc0ed107960cd26c4921fc5a4456ee8fa9e52b2a88cc8c71231d66e5
3
+ size 669188
tokenizer_config.json CHANGED
@@ -1,62 +1,56 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
- "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
- "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
- "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
- "mask_token": "<mask>",
50
- "max_length": 512,
51
- "model_max_length": 32768,
52
- "pad_to_multiple_of": null,
53
- "pad_token": "<pad>",
54
- "pad_token_type_id": 0,
55
- "padding_side": "right",
56
- "sep_token": "</s>",
57
- "stride": 0,
58
- "tokenizer_class": "XLMRobertaTokenizer",
59
- "truncation_side": "right",
60
- "truncation_strategy": "longest_first",
61
- "unk_token": "<unk>"
62
  }
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
 
47
  "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
 
 
 
 
 
56
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff