Hugging Face's logo

sparse-encoder
/
example-inference-free-splade-distilbert-base-uncased-nq

Feature Extraction
sentence-transformers
Safetensors
English
sparse-encoder
sparse
asymmetric
inference-free
splade
Generated from Trainer
dataset_size:99000
loss:SpladeLoss
loss:SparseMultipleNegativesRankingLoss
loss:FlopsLoss
Eval Results (legacy)
Model card Files
xet
 Community
Tom Aarsen commited on
Commit
56ccabc
·
1 Parent(s): 4a6a63b

IDF -> SparseStaticEmbedding

Browse files
Files changed (8) hide show
  1. .vscode/settings.json +3 -0
  2. {query_0_IDF → query_0_SparseStaticEmbedding}/config.json +2 -2
  3. {query_0_IDF → query_0_SparseStaticEmbedding}/model.safetensors +0 -0
  4. {query_0_IDF → query_0_SparseStaticEmbedding}/special_tokens_map.json +7 -7
  5. {query_0_IDF → query_0_SparseStaticEmbedding}/tokenizer.json +0 -0
  6. {query_0_IDF → query_0_SparseStaticEmbedding}/tokenizer_config.json +56 -56
  7. {query_0_IDF → query_0_SparseStaticEmbedding}/vocab.txt +0 -0
  8. router_config.json +2 -2
.vscode/settings.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "iis.configDir": ""
3
+ }
{query_0_IDF → query_0_SparseStaticEmbedding}/config.json RENAMED
@@ -1,3 +1,3 @@
1
- {
2
- "frozen": false
3
  }
 
1
+ {
2
+ "frozen": false
3
  }
{query_0_IDF → query_0_SparseStaticEmbedding}/model.safetensors RENAMED
File without changes
{query_0_IDF → query_0_SparseStaticEmbedding}/special_tokens_map.json RENAMED
@@ -1,7 +1,7 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
{query_0_IDF → query_0_SparseStaticEmbedding}/tokenizer.json RENAMED
File without changes
{query_0_IDF → query_0_SparseStaticEmbedding}/tokenizer_config.json RENAMED
@@ -1,56 +1,56 @@
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": true,
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": "DistilBertTokenizer",
55
- "unk_token": "[UNK]"
56
- }
 
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": true,
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": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
{query_0_IDF → query_0_SparseStaticEmbedding}/vocab.txt RENAMED
File without changes
router_config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "types": {
3
- "query_0_IDF": "sentence_transformers.sparse_encoder.models.IDF.IDF",
4
  "document_0_MLMTransformer": "sentence_transformers.sparse_encoder.models.MLMTransformer.MLMTransformer",
5
  "document_1_SpladePooling": "sentence_transformers.sparse_encoder.models.SpladePooling.SpladePooling"
6
  },
7
  "structure": {
8
  "query": [
9
- "query_0_IDF"
10
  ],
11
  "document": [
12
  "document_0_MLMTransformer",
 
1
  {
2
  "types": {
3
+ "query_0_SparseStaticEmbedding": "sentence_transformers.sparse_encoder.models.SparseStaticEmbedding.SparseStaticEmbedding",
4
  "document_0_MLMTransformer": "sentence_transformers.sparse_encoder.models.MLMTransformer.MLMTransformer",
5
  "document_1_SpladePooling": "sentence_transformers.sparse_encoder.models.SpladePooling.SpladePooling"
6
  },
7
  "structure": {
8
  "query": [
9
+ "query_0_SparseStaticEmbedding"
10
  ],
11
  "document": [
12
  "document_0_MLMTransformer",