Duplicate from Helsinki-NLP/opus-mt-en-zh

Co-authored-by: Satya <Satya10@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,9 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,96 @@
+---
+language:
+- en
+- zh
+tags:
+- translation
+license: apache-2.0
+---
+
+### eng-zho
+
+* source group: English 
+* target group: Chinese 
+*  OPUS readme: [eng-zho](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-zho/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): cjy_Hans cjy_Hant cmn cmn_Hans cmn_Hant gan lzh lzh_Hans nan wuu yue yue_Hans yue_Hant
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
+* download original weights: [opus-2020-07-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.zip)
+* test set translations: [opus-2020-07-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.test.txt)
+* test set scores: [opus-2020-07-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zho/opus-2020-07-17.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.eng.zho 	| 31.4 	| 0.268 |
+
+
+### System Info: 
+- 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: 0.8959999999999999
+
+- 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

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "./",
+  "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,
+  "do_blenderbot_90_layernorm": false,
+  "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": 0,
+  "force_bos_token_to_be_generated": false,
+  "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": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65001
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de82e23a535e25896ebdf433ec2b72706a428fb8e47bb87ef72531426edee8c3
+size 309944974

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 65000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 65000,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.0.dev0"
+}

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 sha256:69a1d6ec829cee349360b3b677ac0aa99a7d88822d1a6578370029efffdca3f5
+size 312087009

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9863d8dc7fd640182d93454f9a0d0f986aca5da7ffebaae1892fa43413578d15
+size 578358061

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43941ec7f52f3352a2bc7436fa85d93966f2ad19e6b3ffaa4b0bb97731630e67
+size 312580600

tokenizer_config.json

@@ -0,0 +1 @@
+{"target_lang": "zho", "source_lang": "eng"}