copy

README.md

@@ -0,0 +1,33 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-ru-en
+
+* source languages: ru
+* target languages: en
+*  OPUS readme: [ru-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ru-en/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/ru-en/opus-2020-02-26.zip)
+* test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ru-en/opus-2020-02-26.test.txt)
+* test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ru-en/opus-2020-02-26.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newstest2012.ru.en 	| 34.8 	| 0.603 |
+| newstest2013.ru.en 	| 27.9 	| 0.545 |
+| newstest2014-ruen.ru.en 	| 31.9 	| 0.591 |
+| newstest2015-enru.ru.en 	| 30.4 	| 0.568 |
+| newstest2016-enru.ru.en 	| 30.1 	| 0.565 |
+| newstest2017-enru.ru.en 	| 33.4 	| 0.593 |
+| newstest2018-enru.ru.en 	| 29.6 	| 0.565 |
+| newstest2019-ruen.ru.en 	| 31.4 	| 0.576 |
+| Tatoeba.ru.en 	| 61.1 	| 0.736 |
+

config.json

@@ -0,0 +1,53 @@
+{
+  "_num_labels": 3,
+  "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": [
+    [
+      62517
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_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": 62517,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "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": 62517,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "vocab_size": 62518
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535450eb5613f3cc912f9ca3e54cfef6c14d201b319c24a88faf776a65538b5d
+size 306991893

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e910b59f7b030d38937da12f8d26a5ef48d5390131528fe08b1078e4dee4b2a
+size 563074700

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745998e51ba5b058e38b7ac7765c25c43ed5c1c39cc92b27163b9b2e323c9d7c
+size 1080169

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bebef1389a0b8ab452772c4e35b9e605e5713f8ac7baa71ca701394eaa086d
+size 802781

tokenizer_config.json

@@ -0,0 +1 @@
+{"target_lang": "en", "source_lang": "ru"}