moussaKam commited on
Commit
728123c
1 Parent(s): 566a41e

Initial commit

Browse files
Files changed (5) hide show
  1. README.md +23 -0
  2. config.json +51 -0
  3. pytorch_model.bin +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. tokenizer.json +0 -0
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - text-classification
4
+
5
+ language:
6
+ - fr
7
+
8
+ widget:
9
+ - text: Barthez est le meilleur gardien du monde.
10
+
11
+ ---
12
+ ### Barthez model finetuned on opinion classification task.
13
+
14
+ paper: https://arxiv.org/abs/2010.12321
15
+
16
+ ```
17
+ @article{eddine2020barthez,
18
+ title={BARThez: a Skilled Pretrained French Sequence-to-Sequence Model},
19
+ author={Eddine, Moussa Kamal and Tixier, Antoine J-P and Vazirgiannis, Michalis},
20
+ journal={arXiv preprint arXiv:2010.12321},
21
+ year={2020}
22
+ }
23
+ ```
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "moussaKam/barthez",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForSequenceClassification"
9
+ ],
10
+ "id2label": {
11
+ "0": "Negative",
12
+ "1": "Positive"
13
+ },
14
+ "attention_dropout": 0.1,
15
+ "bos_token_id": 0,
16
+ "classif_dropout": 0.1,
17
+ "classifier_dropout": 0.0,
18
+ "d_model": 768,
19
+ "decoder_attention_heads": 12,
20
+ "decoder_ffn_dim": 3072,
21
+ "decoder_layerdrop": 0.0,
22
+ "decoder_layers": 6,
23
+ "decoder_start_token_id": 2,
24
+ "do_blenderbot_90_layernorm": false,
25
+ "dropout": 0.1,
26
+ "early_stopping": true,
27
+ "encoder_attention_heads": 12,
28
+ "encoder_ffn_dim": 3072,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 2,
32
+ "extra_pos_embeddings": 2,
33
+ "force_bos_token_to_be_generated": false,
34
+ "gradient_checkpointing": false,
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "max_position_embeddings": 1024,
38
+ "model_type": "mbart",
39
+ "no_repeat_ngram_size": 3,
40
+ "normalize_before": true,
41
+ "normalize_embedding": true,
42
+ "num_beams": 4,
43
+ "num_hidden_layers": 6,
44
+ "pad_token_id": 1,
45
+ "scale_embedding": false,
46
+ "static_position_embeddings": false,
47
+ "tokenizer_class": "BarthezTokenizer",
48
+ "transformers_version": "4.4.0.dev0",
49
+ "use_cache": true,
50
+ "vocab_size": 50002
51
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5965bf92934d02a1ea631b6c091be5c12717778fdef4abe51feca150306db6
3
+ size 559360082
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582403da7cb525c4cac90b495e553cb766b818be71755e6bd885072a1067314a
3
+ size 1115393
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff