copy
Browse files- README.md +32 -0
- config.json +53 -0
- pytorch_model.bin +3 -0
- rust_model.ot +3 -0
- source.spm +3 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- translation
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
### opus-mt-en-ru
|
| 8 |
+
|
| 9 |
+
* source languages: en
|
| 10 |
+
* target languages: ru
|
| 11 |
+
* OPUS readme: [en-ru](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-ru/README.md)
|
| 12 |
+
|
| 13 |
+
* dataset: opus
|
| 14 |
+
* model: transformer-align
|
| 15 |
+
* pre-processing: normalization + SentencePiece
|
| 16 |
+
* download original weights: [opus-2020-02-11.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.zip)
|
| 17 |
+
* test set translations: [opus-2020-02-11.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.test.txt)
|
| 18 |
+
* test set scores: [opus-2020-02-11.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.eval.txt)
|
| 19 |
+
|
| 20 |
+
## Benchmarks
|
| 21 |
+
|
| 22 |
+
| testset | BLEU | chr-F |
|
| 23 |
+
|-----------------------|-------|-------|
|
| 24 |
+
| newstest2012.en.ru | 31.1 | 0.581 |
|
| 25 |
+
| newstest2013.en.ru | 23.5 | 0.513 |
|
| 26 |
+
| newstest2015-enru.en.ru | 27.5 | 0.564 |
|
| 27 |
+
| newstest2016-enru.en.ru | 26.4 | 0.548 |
|
| 28 |
+
| newstest2017-enru.en.ru | 29.1 | 0.572 |
|
| 29 |
+
| newstest2018-enru.en.ru | 25.4 | 0.554 |
|
| 30 |
+
| newstest2019-enru.en.ru | 27.1 | 0.533 |
|
| 31 |
+
| Tatoeba.en.ru | 48.4 | 0.669 |
|
| 32 |
+
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 3,
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "swish",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"MarianMTModel"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bad_words_ids": [
|
| 12 |
+
[
|
| 13 |
+
62517
|
| 14 |
+
]
|
| 15 |
+
],
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"classif_dropout": 0.0,
|
| 18 |
+
"d_model": 512,
|
| 19 |
+
"decoder_attention_heads": 8,
|
| 20 |
+
"decoder_ffn_dim": 2048,
|
| 21 |
+
"decoder_layerdrop": 0.0,
|
| 22 |
+
"decoder_layers": 6,
|
| 23 |
+
"decoder_start_token_id": 62517,
|
| 24 |
+
"dropout": 0.1,
|
| 25 |
+
"encoder_attention_heads": 8,
|
| 26 |
+
"encoder_ffn_dim": 2048,
|
| 27 |
+
"encoder_layerdrop": 0.0,
|
| 28 |
+
"encoder_layers": 6,
|
| 29 |
+
"eos_token_id": 0,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_length": 512,
|
| 43 |
+
"max_position_embeddings": 512,
|
| 44 |
+
"model_type": "marian",
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": false,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 62517,
|
| 50 |
+
"scale_embedding": true,
|
| 51 |
+
"static_position_embeddings": true,
|
| 52 |
+
"vocab_size": 62518
|
| 53 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d15fa58c6bc3efd3629c1b6b86d9aa6d15d2751a4620aa4cdd7eed7b5cbe583b
|
| 3 |
+
size 306991893
|
rust_model.ot
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a950daf8b39c3da63dca70b2b158beac6761a0283393e0ae1a854ee52bec122
|
| 3 |
+
size 563074700
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16bebef1389a0b8ab452772c4e35b9e605e5713f8ac7baa71ca701394eaa086d
|
| 3 |
+
size 802781
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:745998e51ba5b058e38b7ac7765c25c43ed5c1c39cc92b27163b9b2e323c9d7c
|
| 3 |
+
size 1080169
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"target_lang": "ru", "source_lang": "en"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|