initial commit

README.md

@@ -0,0 +1,24 @@
+---
+tags:
+- summarization
+
+language:
+- fr
+
+widget:
+- 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.
+---
+### Barthez model finetuned on orangeSum (abstract generation)
+
+finetuning: examples/seq2seq (as of Feb 08 2021)
+
+paper: https://arxiv.org/abs/2010.12321
+
+```
+@article{eddine2020barthez,
+  title={BARThez: a Skilled Pretrained French Sequence-to-Sequence Model},
+  author={Eddine, Moussa Kamal and Tixier, Antoine J-P and Vazirgiannis, Michalis},
+  journal={arXiv preprint arXiv:2010.12321},
+  year={2020}
+}
+```

config.json

@@ -0,0 +1,53 @@
+{
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "vocab_size": 50002,
+  "tokenizer_class": "BarthezTokenizer" 
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab62b0dc500d41d794f136e8e036441d32270ef57cf92b500f8142b396686cbb
+size 557190519

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582403da7cb525c4cac90b495e553cb766b818be71755e6bd885072a1067314a
+size 1115393