Hugging Face's logo

antoinelouis
/
crossencoder-camemberta-base-mmarcoFR

Text Classification
sentence-transformers
Safetensors
French
deberta-v2
passage-reranking
Eval Results
Model card Files Community
antoinelouis commited on
Commit
81255f4
•
1 Parent(s): 783fdd0

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. added_tokens.json +4 -0
  2. config.json +46 -0
  3. mmarco_smalldev_scores.csv +6 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +51 -0
  6. spm.model +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +58 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "[PAD]": 32002,
3
+ "[UNK]": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camemberta-base",
3
+ "amp": true,
4
+ "architectures": [
5
+ "DebertaV2ForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 3,
10
+ "embedding_size": 768,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_name": "camemberta-base",
26
+ "model_type": "deberta-v2",
27
+ "norm_rel_ebd": "layer_norm",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "pooler_dropout": 0,
32
+ "pooler_hidden_act": "gelu",
33
+ "pooler_hidden_size": 768,
34
+ "pos_att_type": [
35
+ "p2c",
36
+ "c2p"
37
+ ],
38
+ "position_biased_input": false,
39
+ "position_buckets": 256,
40
+ "relative_attention": true,
41
+ "share_att_key": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.36.2",
44
+ "type_vocab_size": 0,
45
+ "vocab_size": 32008
46
+ }
mmarco_smalldev_scores.csv ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch,steps,cutoff,mrr,recall,r-precision
2
+ 0,20000,5,0.3380229226361032,0.5043099331423113,0.23480181470869146
3
+ 0,20000,10,0.35245599672533773,0.6123089780324736,0.23480181470869146
4
+ 0,20000,20,0.358825584867671,0.7037368672397325,0.23480181470869146
5
+ 0,20000,50,0.36213697442815124,0.8053127984718244,0.23480181470869146
6
+ 0,20000,100,0.36297557332571156,0.8642788920725882,0.23480181470869146
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b29c1266189b075611da8401e1c0e3774279d985b15a534964528c0e68460b3
3
+ size 449609084
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
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": "[SEP]",
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
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf6658b4c5f33b1a6092e07deec6f921e4c6e87bf3068d109a2f1fd44849b50
3
+ size 808787
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "32000": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32001": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32002": {
36
+ "content": "[PAD]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 256,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }