init

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- translation
+- japanese
+
+language:
+- ja
+- en
+
+license: mit
+
+widget:
+- text: "今日もご安全に"
+
+---
+## mbart-ja-en
+このモデルは[facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25)をベースに[JESC dataset](https://nlp.stanford.edu/projects/jesc/index_ja.html)でファインチューニングしたものです。  
+This model is based on [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) and fine-tuned with [JESC dataset](https://nlp.stanford.edu/projects/jesc/index_ja.html).
+
+## How to use
+```py
+from transformers import (
+    MBartForConditionalGeneration, MBartTokenizer
+)
+
+tokenizer = MBartTokenizer.from_pretrained("ken11/mbart-ja-en")
+model = MBartForConditionalGeneration.from_pretrained("ken11/mbart-ja-en")
+
+inputs = tokenizer("こんにちは", return_tensors="pt")
+translated_tokens = model.generate(**inputs, decoder_start_token_id=tokenizer.lang_code_to_id["en_XX"], early_stopping=True, max_length=48)
+pred = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
+print(pred)
+```
+
+## Training Data
+I used the [JESC dataset](https://nlp.stanford.edu/projects/jesc/index_ja.html) for training.  
+Thank you for publishing such a large dataset.  
+
+## Tokenizer
+The tokenizer uses the [sentencepiece](https://github.com/google/sentencepiece) trained on the JESC dataset.
+
+## Note
+The result of evaluating the sacrebleu score for [JEC Basic Sentence Data of Kyoto University](https://nlp.ist.i.kyoto-u.ac.jp/EN/?JEC+Basic+Sentence+Data#i0163896) was `18.18` .
+
+## Licenese
+[The MIT license](https://opensource.org/licenses/MIT)

config.json

@@ -0,0 +1,54 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "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,
+  "dropout": 0.1,
+  "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": 1024,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 64027
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e00cd3e783c9386041a78e2cdc410f75308449a1289ea001e7263751c4ec091
+size 1681999289

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca26417c3321e76f2243b15ce126c239ce564c6ffb8e5a1bccb18c53ffbaad5
+size 1427810

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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "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"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "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"}, "sp_model_kwargs": {}, "src_lang": "ja_XX", "tgt_lang": "en_XX", "additional_special_tokens": null, "max_length": 32, "max_target_length": 32, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_class": "MBartTokenizer"}