Hugging Face's logo

AntoineD
/
camembert_ccnet_classification_tools_fr

Text Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
AntoineD commited on
Commit
eeeb81c
•
1 Parent(s): a542f74

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. added_tokens.json +1 -1
  2. pytorch_model.bin +1 -1
  3. sentencepiece.bpe.model +2 -2
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +8 -7
  6. training_args.bin +1 -1
added_tokens.json CHANGED
@@ -5,5 +5,5 @@
5
  "<pad>": 1,
6
  "<s>": 5,
7
  "<s>NOTUSED": 0,
8
- "<unk>": 4
9
  }
 
5
  "<pad>": 1,
6
  "<s>": 5,
7
  "<s>NOTUSED": 0,
8
+ "<unk>": 3
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71d1b428302b20c3337044249bebdcc2ddbd734aa49a0b0b59a8b10a754aa5ac
3
  size 442581361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269811464583d5545e0d6c20d830d016333c08fa249a9ce06d0ac47555392ec3
3
  size 442581361
sentencepiece.bpe.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
- size 810912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
3
+ size 808767
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,9 +2,9 @@
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
  },
@@ -18,13 +18,13 @@
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,
@@ -51,7 +51,7 @@
51
  "32004": {
52
  "content": "<mask>",
53
  "lstrip": true,
54
- "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
@@ -66,9 +66,10 @@
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
  }
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<s>NOTUSED",
5
+ "lstrip": true,
6
  "normalized": false,
7
+ "rstrip": true,
8
  "single_word": false,
9
  "special": true
10
  },
 
18
  },
19
  "2": {
20
  "content": "</s>NOTUSED",
21
+ "lstrip": true,
22
  "normalized": false,
23
+ "rstrip": true,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
 
51
  "32004": {
52
  "content": "<mask>",
53
  "lstrip": true,
54
+ "normalized": true,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
 
66
  "cls_token": "<s>",
67
  "eos_token": "</s>",
68
  "mask_token": "<mask>",
69
+ "model_max_length": 1000000000000000019884624838656,
70
  "pad_token": "<pad>",
71
  "sep_token": "</s>",
72
+ "sp_model_kwargs": {},
73
  "tokenizer_class": "CamembertTokenizer",
74
  "unk_token": "<unk>"
75
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39c1df87afb0831c73c95c2e10e23848702e1e8379c991f2c25de764831ac99d
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafb71b133a864e0656103e7cf83a22959344313278105eff719fcdb8f7ec99a
3
  size 4091