add files

README.md

@@ -0,0 +1,64 @@
+---
+language: multilingual
+tags:
+- mbart-50
+---
+
+# mBART-50 many to many multilingual machine translation
+
+
+This model is a fine-tuned checkpoint of [mBART-large-50](https://huggingface.co/facebook/mbart-large-50). `mbart-large-50-many-to-many-mmt` is fine-tuned for multilingual machine translation. It was introduced in [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) paper.
+
+
+The model can translate directly between any pair of 50 languages. To translate into a target language, the target language id is forced as the first generated token. To force the target language id as the first generated token, pass the `forced_bos_token_id` parameter to the `generate` method.
+
+
+```python
+from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
+
+article_hi = "संयुक्त राष्ट्र के प्रमुख का कहना है कि सीरिया में कोई सैन्य समाधान नहीं है"
+article_ar = "الأمين العام للأمم المتحدة يقول إنه لا يوجد حل عسكري في سوريا."
+
+model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
+tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
+
+# translate Hindi to French
+tokenizer.src_lang = "hi_IN"
+encoded_hi = tokenizer(article_hi, return_tensors="pt")
+generated_tokens = model.generate(
+    **encoded_hi,
+    forced_bos_token_id=tokenizer.lang_code_to_id["fr_XX"]
+)
+tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
+# => "Le chef de l 'ONU affirme qu 'il n 'y a pas de solution militaire dans la Syrie."
+
+# translate Arabic to English
+tokenizer.src_lang = "ar_AR"
+encoded_ar = tokenizer(article_ar, return_tensors="pt")
+generated_tokens = model.generate(
+    **encoded_ar,
+    forced_bos_token_id=tokenizer.lang_code_to_id["en_XX"]
+)
+tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
+# => "The Secretary-General of the United Nations says there is no military solution in Syria."
+```
+
+
+See the [model hub](https://huggingface.co/models?filter=mbart-50) to look for more fine-tuned versions.
+
+
+## Languages covered
+Arabic (ar_AR), Czech (cs_CZ), German (de_DE), English (en_XX), Spanish (es_XX), Estonian (et_EE), Finnish (fi_FI), French (fr_XX), Gujarati (gu_IN), Hindi (hi_IN), Italian (it_IT), Japanese (ja_XX), Kazakh (kk_KZ), Korean (ko_KR), Lithuanian (lt_LT), Latvian (lv_LV), Burmese (my_MM), Nepali (ne_NP), Dutch (nl_XX), Romanian (ro_RO), Russian (ru_RU), Sinhala (si_LK), Turkish (tr_TR), Vietnamese (vi_VN), Chinese (zh_CN), Afrikaans (af_ZA), Azerbaijani (az_AZ), Bengali (bn_IN), Persian (fa_IR), Hebrew (he_IL), Croatian (hr_HR), Indonesian (id_ID), Georgian (ka_GE), Khmer (km_KH), Macedonian (mk_MK), Malayalam (ml_IN), Mongolian (mn_MN), Marathi (mr_IN), Polish (pl_PL), Pashto (ps_AF), Portuguese (pt_XX), Swedish (sv_SE), Swahili (sw_KE), Tamil (ta_IN), Telugu (te_IN), Thai (th_TH), Tagalog (tl_XX), Ukrainian (uk_UA), Urdu (ur_PK), Xhosa (xh_ZA), Galician (gl_ES), Slovene (sl_SI)
+
+
+## BibTeX entry and citation info
+```
+@article{tang2020multilingual,
+    title={Multilingual Translation with Extensible Multilingual Pretraining and Finetuning},
+    author={Yuqing Tang and Chau Tran and Xian Li and Peng-Jen Chen and Naman Goyal and Vishrav Chaudhary and Jiatao Gu and Angela Fan},
+    year={2020},
+    eprint={2008.00401},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large-many-to-many/",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": 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_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250054
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024ddcc796a33d2e4decd4c1bd5fe90ad295aaba9072edb3796a09ef9b755934
+size 2444714899

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": "<s>", "tokenizer_file": null, "language_codes": "ML50", "special_tokens_map_file": "/home/suraj/projects/mbart-50/mbart-50/special_tokens_map.json", "name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large-many-to-many/"}