Initial commit

README.md

@@ -0,0 +1,96 @@
+---
+language:
+- af
+- ru
+
+tags:
+- translation
+
+license: apache-2.0
+---
+### af-ru
+
+* source group: Afrikaans 
+* target group: Russian 
+*  OPUS readme: [afr-rus](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-rus/README.md)
+
+*  model: transformer-align
+* source language(s): afr
+* target language(s): rus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-09-10.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-09-10.zip)
+* test set translations: [opus-2020-09-10.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-09-10.test.txt)
+* test set scores: [opus-2020-09-10.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-09-10.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.afr.rus 	| 38.2 	| 0.580 |
+
+
+### System Info: 
+- hf_name: af-ru
+
+- source_languages: afr
+
+- target_languages: rus
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afr-rus/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['af', 'ru']
+
+- src_constituents: ('Afrikaans', {'afr'})
+
+- tgt_constituents: ('Russian', {'rus'})
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- long_pair: afr-rus
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-09-10.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afr-rus/opus-2020-09-10.test.txt
+
+- src_alpha3: afr
+
+- tgt_alpha3: rus
+
+- chrF2_score: 0.58
+
+- bleu: 38.2
+
+- brevity_penalty: 0.992
+
+- ref_len: 1213
+
+- src_name: Afrikaans
+
+- tgt_name: Russian
+
+- train_date: 2020-01-01 00:00:00
+
+- src_alpha2: af
+
+- tgt_alpha2: ru
+
+- prefer_old: False
+
+- short_pair: af-ru
+
+- helsinki_git_sha: e8c308a96c1bd0b4ca6a8ce174783f93c3e30f25
+
+- transformers_git_sha: 31245775e5772fbded1ac07ed89fbba3b5af0cb9
+
+- port_machine: LM0-400-22516.local
+
+- port_time: 2021-02-12-14:52

config.json

@@ -0,0 +1,43 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62841
+    ]
+  ],
+  "bos_token_id": 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": 62841,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62841,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 62842
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"af-ru","source_languages":"afr","target_languages":"rus","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/afr-rus\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["af","ru"],"src_constituents":["Afrikaans",["afr"]],"tgt_constituents":["Russian",["rus"]],"src_multilingual":false,"tgt_multilingual":false,"long_pair":"afr-rus","prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/afr-rus\/opus-2020-09-10.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/afr-rus\/opus-2020-09-10.test.txt","src_alpha3":"afr","tgt_alpha3":"rus","chrF2_score":0.58,"bleu":38.2,"brevity_penalty":0.992,"ref_len":1213,"src_name":"Afrikaans","tgt_name":"Russian","train_date":1577836800000,"src_alpha2":"af","tgt_alpha2":"ru","prefer_old":false,"short_pair":"af-ru","helsinki_git_sha":"e8c308a96c1bd0b4ca6a8ce174783f93c3e30f25","transformers_git_sha":"31245775e5772fbded1ac07ed89fbba3b5af0cb9","port_machine":"LM0-400-22516.local","port_time":"2021-02-12-14:52"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6419499b7ba43d84ae070b20508ed3690e4a1cca47e1404b953cb1e1f5551bb2
+size 217191077

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "afr", "target_lang": "rus", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "marian_ckpt/afr-rus"}