upload files

README.md

@@ -1,3 +1,58 @@
 ---
-license: cc-by-nc-4.0
+language:
+- zh
+- ja
+- en
+
+tags:
+- translation
+
+widget:
+- text: "ja2zh: 吾輩は猫である。名前はまだ無い。"
+
+license: cc-by-nc-sa-4.0
 ---
+
+This model is finetuned from [mt5-base](https://huggingface.co/google/mt5-base).
+
+The model vocabulary is trimmed to ~1/3 by selecting top 85000 tokens in the traning data.
+
+Usage:
+```python
+from transformers import (
+  T5Tokenizer,
+  MT5ForConditionalGeneration,
+  Text2TextGenerationPipeline,
+)
+
+path = "K024/mt5-zh-ja-en-trimmed"
+pipe = Text2TextGenerationPipeline(
+  model=MT5ForConditionalGeneration.from_pretrained(path),
+  tokenizer=T5Tokenizer.from_pretrained(path),
+)
+
+sentence = "ja2zh: 吾輩は猫である。名前はまだ無い。"
+res = pipe(sentence, max_length=100, num_beams=4)
+res[0]['generated_text']
+```
+
+Training data:
+```
+wikimedia-en-ja
+wikimedia-en-zh
+wikimedia-ja-zh
+wikititles-ja-en
+wikititles-zh-en
+wikimatrix-ja-zh
+news-commentary-en-ja
+news-commentary-en-zh
+news-commentary-ja-zh
+ted2020-en-ja
+ted2020-en-zh
+ted2020-ja-zh
+```
+
+License: [![CC BY-NC-SA 4.0][cc-by-nc-sa-image]][cc-by-nc-sa]
+
+[cc-by-nc-sa]: http://creativecommons.org/licenses/by-nc-sa/4.0/
+[cc-by-nc-sa-image]: https://licensebuttons.net/l/by-nc-sa/4.0/88x31.png

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "K024/mt5-zh-ja-en-trimmed",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 85292
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696549da574a103650f23fa7dc8fb2dc838c2d7e5473e85d5637350d44628b7d
+size 1317077965

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8557a50825d59b58c004cb4dc566ff98926d864c51fd153fb32cf5c5f19643e
+size 1511055

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "K024/mt5-zh-ja-en-trimmed", "tokenizer_class": "T5Tokenizer"}