upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-en-cpp (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 +1,101 @@
+---
+language: 
+- en
+- id
+- cpp
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-cpp
+
+* source group: English 
+* target group: Creoles and pidgins, Portuguese-based 
+*  OPUS readme: [eng-cpp](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-cpp/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): ind max_Latn min pap tmw_Latn zlm_Latn zsm_Latn
+* 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-cpp/opus2m-2020-08-01.zip)
+* test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpp/opus2m-2020-08-01.test.txt)
+* test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpp/opus2m-2020-08-01.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.eng-msa.eng.msa 	| 32.6 	| 0.573 |
+| Tatoeba-test.eng.multi 	| 32.7 	| 0.574 |
+| Tatoeba-test.eng-pap.eng.pap 	| 42.5 	| 0.633 |
+
+
+### System Info: 
+- hf_name: eng-cpp
+
+- source_languages: eng
+
+- target_languages: cpp
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-cpp/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'id', 'cpp']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: {'zsm_Latn', 'ind', 'pap', 'min', 'tmw_Latn', 'max_Latn', 'zlm_Latn'}
+
+- src_multilingual: False
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpp/opus2m-2020-08-01.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpp/opus2m-2020-08-01.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: cpp
+
+- short_pair: en-cpp
+
+- chrF2_score: 0.574
+
+- bleu: 32.7
+
+- brevity_penalty: 0.996
+
+- ref_len: 34010.0
+
+- src_name: English
+
+- tgt_name: Creoles and pidgins, Portuguese-based
+
+- train_date: 2020-08-01
+
+- src_alpha2: en
+
+- tgt_alpha2: cpp
+
+- prefer_old: False
+
+- long_pair: eng-cpp
+
+- 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-cpp",
+  "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": [
+    [
+      57765
+    ]
+  ],
+  "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": 57765,
+  "decoder_vocab_size": 57766,
+  "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": 57766,
+  "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": 57765,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 57766
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      57765
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 57765,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 57765,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.0.dev0"
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"eng-cpp","source_languages":"eng","target_languages":"cpp","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-cpp\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","id","cpp"],"src_constituents":["eng"],"tgt_constituents":["zsm_Latn","ind","pap","min","tmw_Latn","max_Latn","zlm_Latn"],"src_multilingual":false,"tgt_multilingual":true,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-cpp\/opus2m-2020-08-01.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-cpp\/opus2m-2020-08-01.test.txt","src_alpha3":"eng","tgt_alpha3":"cpp","short_pair":"en-cpp","chrF2_score":0.574,"bleu":32.7,"brevity_penalty":0.996,"ref_len":34010.0,"src_name":"English","tgt_name":"Creoles and pidgins, Portuguese-based","train_date":"2020-08-01","src_alpha2":"en","tgt_alpha2":"cpp","prefer_old":false,"long_pair":"eng-cpp","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 sha256:8ed7b390038603a7462cc10d917e8addb85b165a41ba67129557b8a8a91d30eb
+size 297240789

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4973cb405c4fae12f805bd90046e2b8da164c150e66f8dd482f66fc2d24e0f
+size 811729

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f8b87f2c0ede22a422ddad1404ba3d4919d454d8893915c704b5c80754706b
+size 814255

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a9ea68b6a011d4d40685cb6308a8b521b01377842db65f029a771a14e92cd5
+size 297705440

tokenizer_config.json

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