upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-en-sla (ADR-039 Phase D)

.gitattributes

@@ -1,35 +1,10 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,140 @@
+---
+language: 
+- en
+- be
+- hr
+- mk
+- cs
+- ru
+- pl
+- bg
+- uk
+- sl
+- sla
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-sla
+
+* source group: English 
+* target group: Slavic languages 
+*  OPUS readme: [eng-sla](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-sla/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): bel bel_Latn bos_Latn bul bul_Latn ces csb_Latn dsb hrv hsb mkd orv_Cyrl pol rue rus slv srp_Cyrl srp_Latn ukr
+* 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: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sla/opus2m-2020-08-01.zip)
+* test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sla/opus2m-2020-08-01.test.txt)
+* test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sla/opus2m-2020-08-01.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newssyscomb2009-engces.eng.ces 	| 20.1 	| 0.484 |
+| news-test2008-engces.eng.ces 	| 17.7 	| 0.461 |
+| newstest2009-engces.eng.ces 	| 19.1 	| 0.479 |
+| newstest2010-engces.eng.ces 	| 19.3 	| 0.483 |
+| newstest2011-engces.eng.ces 	| 20.4 	| 0.486 |
+| newstest2012-engces.eng.ces 	| 18.3 	| 0.461 |
+| newstest2012-engrus.eng.rus 	| 27.4 	| 0.551 |
+| newstest2013-engces.eng.ces 	| 21.5 	| 0.489 |
+| newstest2013-engrus.eng.rus 	| 20.9 	| 0.490 |
+| newstest2015-encs-engces.eng.ces 	| 21.1 	| 0.496 |
+| newstest2015-enru-engrus.eng.rus 	| 24.5 	| 0.536 |
+| newstest2016-encs-engces.eng.ces 	| 23.6 	| 0.515 |
+| newstest2016-enru-engrus.eng.rus 	| 23.0 	| 0.519 |
+| newstest2017-encs-engces.eng.ces 	| 19.2 	| 0.474 |
+| newstest2017-enru-engrus.eng.rus 	| 25.0 	| 0.541 |
+| newstest2018-encs-engces.eng.ces 	| 19.3 	| 0.479 |
+| newstest2018-enru-engrus.eng.rus 	| 22.3 	| 0.526 |
+| newstest2019-encs-engces.eng.ces 	| 20.4 	| 0.486 |
+| newstest2019-enru-engrus.eng.rus 	| 24.0 	| 0.506 |
+| Tatoeba-test.eng-bel.eng.bel 	| 22.9 	| 0.489 |
+| Tatoeba-test.eng-bul.eng.bul 	| 46.7 	| 0.652 |
+| Tatoeba-test.eng-ces.eng.ces 	| 42.7 	| 0.624 |
+| Tatoeba-test.eng-csb.eng.csb 	| 1.4 	| 0.210 |
+| Tatoeba-test.eng-dsb.eng.dsb 	| 1.4 	| 0.165 |
+| Tatoeba-test.eng-hbs.eng.hbs 	| 40.3 	| 0.616 |
+| Tatoeba-test.eng-hsb.eng.hsb 	| 14.3 	| 0.344 |
+| Tatoeba-test.eng-mkd.eng.mkd 	| 44.1 	| 0.635 |
+| Tatoeba-test.eng.multi 	| 41.0 	| 0.610 |
+| Tatoeba-test.eng-orv.eng.orv 	| 0.3 	| 0.014 |
+| Tatoeba-test.eng-pol.eng.pol 	| 42.0 	| 0.637 |
+| Tatoeba-test.eng-rue.eng.rue 	| 0.3 	| 0.012 |
+| Tatoeba-test.eng-rus.eng.rus 	| 40.5 	| 0.612 |
+| Tatoeba-test.eng-slv.eng.slv 	| 18.8 	| 0.357 |
+| Tatoeba-test.eng-ukr.eng.ukr 	| 38.8 	| 0.600 |
+
+
+### System Info: 
+- hf_name: eng-sla
+
+- source_languages: eng
+
+- target_languages: sla
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-sla/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'be', 'hr', 'mk', 'cs', 'ru', 'pl', 'bg', 'uk', 'sl', 'sla']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: {'bel', 'hrv', 'orv_Cyrl', 'mkd', 'bel_Latn', 'srp_Latn', 'bul_Latn', 'ces', 'bos_Latn', 'csb_Latn', 'dsb', 'hsb', 'rus', 'srp_Cyrl', 'pol', 'rue', 'bul', 'ukr', 'slv'}
+
+- src_multilingual: False
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sla/opus2m-2020-08-01.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sla/opus2m-2020-08-01.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: sla
+
+- short_pair: en-sla
+
+- chrF2_score: 0.61
+
+- bleu: 41.0
+
+- brevity_penalty: 0.976
+
+- ref_len: 64809.0
+
+- src_name: English
+
+- tgt_name: Slavic languages
+
+- train_date: 2020-08-01
+
+- src_alpha2: en
+
+- tgt_alpha2: sla
+
+- prefer_old: False
+
+- long_pair: eng-sla
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-en-sla",
+  "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": [
+    [
+      58878
+    ]
+  ],
+  "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": 58878,
+  "decoder_vocab_size": 58879,
+  "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": 58879,
+  "forced_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": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58878,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 58879
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      58878
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 58878,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 58878,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.0.dev0"
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"eng-sla","source_languages":"eng","target_languages":"sla","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-sla\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","be","hr","mk","cs","ru","pl","bg","uk","sl","sla"],"src_constituents":["eng"],"tgt_constituents":["bel","hrv","orv_Cyrl","mkd","bel_Latn","srp_Latn","bul_Latn","ces","bos_Latn","csb_Latn","dsb","hsb","rus","srp_Cyrl","pol","rue","bul","ukr","slv"],"src_multilingual":false,"tgt_multilingual":true,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-sla\/opus2m-2020-08-01.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-sla\/opus2m-2020-08-01.test.txt","src_alpha3":"eng","tgt_alpha3":"sla","short_pair":"en-sla","chrF2_score":0.61,"bleu":41.0,"brevity_penalty":0.976,"ref_len":64809.0,"src_name":"English","tgt_name":"Slavic languages","train_date":"2020-08-01","src_alpha2":"en","tgt_alpha2":"sla","prefer_old":false,"long_pair":"eng-sla","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 sha256:1352ae4ef442420c47e9a9693a4baa2628be4579b167e04a801e57096f390196
+size 299524665

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e262c2e51f67f8ddc3b08ca37381938ecc5cf43b52165054bb965483c3a4e68
+size 791358

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948df13e89a108c933ffbf25f620ebf9b817cd68596179284329429469f27f8c
+size 860404

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0366283f91ba21933f12b9f64a052050ce58fa2e72a3b9661c1ee54392dea6c
+size 299993768

tokenizer_config.json

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