Upload 8 files

README.md

@@ -0,0 +1,67 @@
+---
+language:
+- en
+- de
+tags:
+- translation
+- opus-mt
+license: cc-by-4.0
+model-index:
+- name: opus-mt-tc-big-eng-deu
+  results:
+  - task:
+      name: Translation eng-deu
+      type: translation
+      args: eng-deu
+    dataset:
+      name: Tatoeba-test.eng-deu
+      type: tatoeba_mt
+      args: eng-deu
+    metrics:
+    - name: BLEU
+      type: bleu
+      value: 45.7	
+---
+
+# Opus Tatoeba English-German
+
+*This model was obtained by running the script [convert_marian_to_pytorch.py](https://github.com/huggingface/transformers/blob/master/src/transformers/models/marian/convert_marian_to_pytorch.py) - [Instruction available here](https://github.com/huggingface/transformers/tree/main/scripts/tatoeba). The original models were trained by [Jörg Tiedemann](https://blogs.helsinki.fi/tiedeman/) using the [MarianNMT](https://marian-nmt.github.io/) library. See all available `MarianMTModel` models on the profile of the [Helsinki NLP](https://huggingface.co/Helsinki-NLP) group.
+
+This is the conversion of checkpoint [opus+bt-2021-04-13.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-deu/opus+bt-2021-04-13.zip)
+*
+
+
+---
+
+### eng-deu
+
+* source language name: English
+* target language name: German
+* OPUS readme: [README.md](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-deu/README.md)
+
+* model: transformer-align
+* source language code: en
+* target language code: de
+* dataset: opus+bt 
+* release date: 2021-02-22
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus+bt-2021-04-13.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-deu/opus+bt-2021-04-13.zip)
+* Test set translations data: [opus+bt-2021-04-13.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-deu/opus+bt-2021-04-13.test.txt)
+* test set scores file: [opus+bt-2021-04-13.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-deu/opus+bt-2021-04-13.eval.txt)
+* Benchmarks
+|Test set|BLEU|chr-F|
+|---|---|---|
+|newssyscomb2009.eng-deu|22.8|0.538|
+|news-test2008.eng-deu|23.7|0.533|	
+|newstest2009.eng-deu|22.6|0.532|	
+|newstest2010.eng-deu|25.5|0.552|	
+|newstest2011.eng-deu|22.6|0.527|	
+|newstest2012.eng-deu|23.4|0.530|	
+|newstest2013.eng-deu|27.1|0.556|	
+|newstest2014-deen.eng-deu|29.6|0.599|	
+|newstest2015-ende.eng-deu|31.6|0.600|	
+|newstest2016-ende.eng-deu|37.2|0.644|	
+|newstest2017-ende.eng-deu|30.6|0.595|	
+|newstest2018-ende.eng-deu|45.6|0.696|	
+|newstest2019-ende.eng-deu|41.3|0.659|	
+|Tatoeba-test.eng-deu|45.7|0.654|	

config.json

@@ -0,0 +1,44 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "decoder_vocab_size": 65001,
+  "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,
+  "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": 65000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732239b875a9428a7cc5191e22c4b44d7edbc3867d202cdd74b1481350e587a5
+size 221612169

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "opus+bt-2021-04-13",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "opus+bt-2021-04",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "opus+bt-2021-04-13/special_tokens_map.json",
+  "target_lang": "13",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}