moussaKam commited on
Commit
d8379ff
1 Parent(s): b368e4a

First model version

Browse files
README.md CHANGED
@@ -1,3 +1,28 @@
1
  ---
 
 
 
 
 
 
 
2
  license: apache-2.0
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - summarization
4
+ - bart
5
+
6
+ language:
7
+ - fr
8
+
9
  license: apache-2.0
10
+
11
+ widget:
12
+ - text: Citant les préoccupations de ses clients dénonçant des cas de censure après la suppression du compte de Trump, un fournisseur d'accès Internet de l'État de l'Idaho a décidé de bloquer Facebook et Twitter. La mesure ne concernera cependant que les clients mécontents de la politique de ces réseaux sociaux.
13
  ---
14
+ ### Barthez model finetuned on orangeSum (abstract generation)
15
+
16
+ finetuning: examples/seq2seq (as of Feb 08 2021)
17
+
18
+ paper: https://arxiv.org/abs/2010.12321 \
19
+ github: https://github.com/moussaKam/BARThez
20
+
21
+ ```
22
+ @article{eddine2020barthez,
23
+ title={BARThez: a Skilled Pretrained French Sequence-to-Sequence Model},
24
+ author={Eddine, Moussa Kamal and Tixier, Antoine J-P and Vazirgiannis, Michalis},
25
+ journal={arXiv preprint arXiv:2010.12321},
26
+ year={2020}
27
+ }
28
+ ```
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "moussaKam/mbarthez",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "mbart",
45
+ "no_repeat_ngram_size": 3,
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 4,
49
+ "num_hidden_layers": 6,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": true,
52
+ "static_position_embeddings": false,
53
+ "tokenizer_class": "BarthezTokenizer",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.27.0.dev0",
56
+ "use_cache": true,
57
+ "vocab_size": 101122
58
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.27.0.dev0"
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a31407e7024f45b75cd1c7238786ebca46106abce7a45babc8773491bc600f
3
+ size 1834072861
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fff580d02c71f72575747fdc1dffa5698f8a88a02dfafa25c0a63df6dbe967
3
+ size 1966695
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 1024,
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "special_tokens_map_file": null,
17
+ "tokenizer_class": "BarthezTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083b7cedd4588044510e103a53158785341b5ebd54407e0c6802f6e985b408ec
3
+ size 3707