feat: init;

README.md

@@ -0,0 +1,34 @@
+---
+language: 
+- en 
+- zh 
+tags:
+- translation
+widget: 
+- text: "我喜欢学习数据科学和机器学习。"
+---
+
+# liam168/trans-opus-mt-zh-en
+
+## Model description
+
+* source group: English 
+* target group: Chinese 
+* model: transformer
+* source language(s): eng
+
+## How to use
+
+```python
+>>> from transformers import AutoModelWithLMHead,AutoTokenizer,pipeline
+>>> mode_name = 'liam168/trans-opus-mt-zh-en'
+>>> model = AutoModelWithLMHead.from_pretrained(mode_name)
+>>> tokenizer = AutoTokenizer.from_pretrained(mode_name)
+>>> translation = pipeline("translation_zh_to_en", model=model, tokenizer=tokenizer)
+>>> translation('我喜欢学习数据科学和机器学习。', max_length=400)
+    [{'translation_text': 'I like to study data science and machine learning.'}]
+```
+
+## Contact
+
+liam168520@gmail.com

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "liam168/trans-opus-mt-zh-en",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 65001,
+  "forced_eos_token_id": 0,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 65001
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"eng-zho","source_languages":"eng","target_languages":"zho","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-zho\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","zh"],"src_constituents":["eng"],"tgt_constituents":["cmn_Hans","nan","nan_Hani","gan","yue","cmn_Kana","yue_Hani","wuu_Bopo","cmn_Latn","yue_Hira","cmn_Hani","cjy_Hans","cmn","lzh_Hang","lzh_Hira","cmn_Hant","lzh_Bopo","zho","zho_Hans","zho_Hant","lzh_Hani","yue_Hang","wuu","yue_Kana","wuu_Latn","yue_Bopo","cjy_Hant","yue_Hans","lzh","cmn_Hira","lzh_Yiii","lzh_Hans","cmn_Bopo","cmn_Hang","hak_Hani","cmn_Yiii","yue_Hant","lzh_Kana","wuu_Hani"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-zho\/opus-2020-07-17.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-zho\/opus-2020-07-17.test.txt","src_alpha3":"eng","tgt_alpha3":"zho","short_pair":"en-zh","chrF2_score":0.268,"bleu":31.4,"brevity_penalty":0.896,"ref_len":110468.0,"src_name":"English","tgt_name":"Chinese","train_date":"2020-07-17","src_alpha2":"en","tgt_alpha2":"zh","prefer_old":false,"long_pair":"eng-zho","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c058648f7c0937d5240c3a3889fb3be1f5c12ed91e9401b71417b6684fc42e
+size 310016901

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "zho", "target_lang": "eng", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "liam168/trans-opus-mt-zh-en", "tokenizer_class": "MarianTokenizer"}