Hugging Face's logo

meandyou200175
/
e5-query-sql

Sentence Similarity
sentence-transformers
Safetensors
roberta
feature-extraction
Generated from Trainer
dataset_size:10494
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
meandyou200175 commited on
Commit
9032cad
·
verified ·
1 Parent(s): 88bb101

Add new SentenceTransformer model

Browse files
Files changed (10) hide show
  1. README.md +0 -0
  2. added_tokens.json +3 -0
  3. bpe.codes +0 -0
  4. config.json +5 -5
  5. model.safetensors +2 -2
  6. modules.json +0 -6
  7. sentence_bert_config.json +1 -1
  8. special_tokens_map.json +7 -49
  9. tokenizer_config.json +5 -5
  10. vocab.txt +0 -0
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "architectures": [
3
- "XLMRobertaModel"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "bos_token_id": 0,
@@ -12,16 +12,16 @@
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-05,
15
- "max_position_embeddings": 514,
16
- "model_type": "xlm-roberta",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 12,
19
- "output_past": true,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
 
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.52.4",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
- "vocab_size": 250002
27
  }
 
1
  {
2
  "architectures": [
3
+ "RobertaModel"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "bos_token_id": 0,
 
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 258,
16
+ "model_type": "roberta",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 12,
 
19
  "pad_token_id": 1,
20
  "position_embedding_type": "absolute",
21
+ "tokenizer_class": "PhobertTokenizer",
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.52.4",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
+ "vocab_size": 64001
27
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f45143445c9574deaedcac3b5020996e3f0e3c2dd3bf5f0edae3dad9b17c36b2
3
- size 1112197096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564319c09a8bef2c06d2996e136384e7b4d9ee18e36367137b9d1f58ae5c715f
3
+ size 540015464
modules.json CHANGED
@@ -10,11 +10,5 @@
10
  "name": "1",
11
  "path": "1_Pooling",
12
  "type": "sentence_transformers.models.Pooling"
13
- },
14
- {
15
- "idx": 2,
16
- "name": "2",
17
- "path": "2_Normalize",
18
- "type": "sentence_transformers.models.Normalize"
19
  }
20
  ]
 
10
  "name": "1",
11
  "path": "1_Pooling",
12
  "type": "sentence_transformers.models.Pooling"
 
 
 
 
 
 
13
  }
14
  ]
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "max_seq_length": 512,
3
  "do_lower_case": false
4
  }
 
1
  {
2
+ "max_seq_length": 256,
3
  "do_lower_case": false
4
  }
special_tokens_map.json CHANGED
@@ -1,51 +1,9 @@
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
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
tokenizer_config.json CHANGED
@@ -32,9 +32,9 @@
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,
@@ -42,14 +42,14 @@
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
- "model_max_length": 512,
51
  "pad_token": "<pad>",
52
  "sep_token": "</s>",
53
- "tokenizer_class": "XLMRobertaTokenizer",
54
  "unk_token": "<unk>"
55
  }
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "64000": {
36
  "content": "<mask>",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
 
42
  }
43
  },
44
  "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
+ "model_max_length": 256,
51
  "pad_token": "<pad>",
52
  "sep_token": "</s>",
53
+ "tokenizer_class": "PhobertTokenizer",
54
  "unk_token": "<unk>"
55
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff