antoinelouis commited on
Commit
d874809
1 Parent(s): 50eda11

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - fr
5
+ library_name: transformers
6
+ inference: false
7
+ ---
8
+ # CamemBERT-L10
9
+
10
+ This model is a pruned version of the pre-trained [CamemBERT](https://huggingface.co/camembert-base) checkpoint, obtained by [dropping the top-layers](https://arxiv.org/abs/2004.03844) from the original model.
11
+
12
+ ![](illustration.jpeg)
13
+
14
+ ## Usage
15
+
16
+ ```python
17
+ from transformers import AutoTokenizer, AutoModel
18
+
19
+ tokenizer = AutoTokenizer.from_pretrained('antoinelouis/camembert-L10')
20
+ model = AutoModel.from_pretrained('antoinelouis/camembert-L10')
21
+ ```
22
+
23
+ ## Comparison
24
+
25
+ | Model | #Params | Size | Pruning |
26
+ |--------------------------------------------------------------------|:-------:|:-----:|:-------:|
27
+ | [CamemBERT](https://huggingface.co/camembert-base) | 110.6M | 445MB | - |
28
+ | | | | |
29
+ | **CamemBERT-L10** | 96.4M | 368MB | -13% |
30
+ | [CamemBERT-L8](https://huggingface.co/antoinelouis/camembert-L8) | 82.3M | 314MB | -26% |
31
+ | [CamemBERT-L6](https://huggingface.co/antoinelouis/camembert-L6) | 68.1M | 260MB | -38% |
32
+ | [CamemBERT-L4](https://huggingface.co/antoinelouis/camembert-L4) | 53.9M | 206MB | -51% |
33
+ | [CamemBERT-L2](https://huggingface.co/antoinelouis/camembert-L2) | 39.7M | 159MB | -64% |
34
+
35
+ ## Citation
36
+
37
+ ```bibtex
38
+ @online{louis2023,
39
+ author = 'Antoine Louis',
40
+ title = 'CamemBERT-L2: A Pruned Version of CamemBERT',
41
+ publisher = 'Hugging Face',
42
+ month = 'october',
43
+ year = '2023',
44
+ url = 'https://huggingface.co/antoinelouis/camembert-L2',
45
+ }
46
+ ```
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 6,
3
+ "</s>NOTUSED": 2,
4
+ "<mask>": 32004,
5
+ "<pad>": 1,
6
+ "<s>": 5,
7
+ "<s>NOTUSED": 0,
8
+ "<unk>": 4
9
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "camembert-base",
3
+ "architectures": [
4
+ "CamembertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "camembert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 10,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 32005
28
+ }
illustration.jpeg ADDED
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7903edba4f0882f5fd59637d20ef90d0d0c5a56dfb67d556508c718daa917387
3
+ size 385838886
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": "<mask>",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
60
+ "additional_special_tokens": [
61
+ "<s>NOTUSED",
62
+ "</s>NOTUSED"
63
+ ],
64
+ "bos_token": "<s>",
65
+ "clean_up_tokenization_spaces": true,
66
+ "cls_token": "<s>",
67
+ "eos_token": "</s>",
68
+ "mask_token": "<mask>",
69
+ "model_max_length": 512,
70
+ "pad_token": "<pad>",
71
+ "sep_token": "</s>",
72
+ "tokenizer_class": "CamembertTokenizer",
73
+ "unk_token": "<unk>"
74
+ }