Hugging Face's logo

sparse-encoder
/
splade-camembert-base-v2

Feature Extraction
sentence-transformers
Safetensors
French
camembert
sparse-encoder
sparse
splade
Generated from Trainer
dataset_size:483497
loss:SpladeLoss
loss:SparseMarginMSELoss
loss:FlopsLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
1
arthurbresnu commited on
Commit
eb096f5
·
verified ·
1 Parent(s): de75575

Add new SparseEncoder model

Browse files
Files changed (10) hide show
  1. 1_SpladePooling/config.json +5 -0
  2. README.md +0 -0
  3. config.json +27 -0
  4. config_sentence_transformers.json +14 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +20 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +84 -0
1_SpladePooling/config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "pooling_strategy": "max",
3
+ "activation_function": "relu",
4
+ "word_embedding_dimension": 32005
5
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CamembertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 5,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 6,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "camembert",
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": "4.53.1",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 32005
27
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SparseEncoder",
3
+ "__version__": {
4
+ "sentence_transformers": "5.1.0.dev0",
5
+ "transformers": "4.53.1",
6
+ "pytorch": "2.7.1+cu126"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "dot"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef2cd382cb34fcc069a15957e39819bc3c674294908baf77b53cab5fb8cb58a
3
+ size 442646188
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.sparse_encoder.models.MLMTransformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_SpladePooling",
12
+ "type": "sentence_transformers.sparse_encoder.models.SpladePooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<unk>NOTUSED"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
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>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32005": {
60
+ "content": "<unk>NOTUSED",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<unk>NOTUSED"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": false,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "extra_special_tokens": {},
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 512,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
84
+ }