upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-cpp-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: 
+- id
+- cpp
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### cpp-cpp
+
+* source group: Creoles and pidgins, Portuguese-based 
+* target group: Creoles and pidgins, Portuguese-based 
+*  OPUS readme: [cpp-cpp](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-cpp/README.md)
+
+*  model: transformer
+* source language(s): ind pap
+* target language(s): ind pap
+* 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: [opus-2020-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.zip)
+* test set translations: [opus-2020-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.test.txt)
+* test set scores: [opus-2020-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.msa-msa.msa.msa 	| 0.7 	| 0.149 |
+| Tatoeba-test.msa-pap.msa.pap 	| 31.7 	| 0.577 |
+| Tatoeba-test.multi.multi 	| 21.1 	| 0.369 |
+| Tatoeba-test.pap-msa.pap.msa 	| 17.7 	| 0.197 |
+
+
+### System Info: 
+- hf_name: cpp-cpp
+
+- source_languages: cpp
+
+- target_languages: cpp
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-cpp/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['id', 'cpp']
+
+- src_constituents: {'zsm_Latn', 'ind', 'pap', 'min', 'tmw_Latn', 'max_Latn', 'zlm_Latn'}
+
+- tgt_constituents: {'zsm_Latn', 'ind', 'pap', 'min', 'tmw_Latn', 'max_Latn', 'zlm_Latn'}
+
+- src_multilingual: True
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.test.txt
+
+- src_alpha3: cpp
+
+- tgt_alpha3: cpp
+
+- short_pair: cpp-cpp
+
+- chrF2_score: 0.369
+
+- bleu: 21.1
+
+- brevity_penalty: 0.882
+
+- ref_len: 18.0
+
+- src_name: Creoles and pidgins, Portuguese-based
+
+- tgt_name: Creoles and pidgins, Portuguese-based
+
+- train_date: 2020-07-26
+
+- src_alpha2: cpp
+
+- tgt_alpha2: cpp
+
+- prefer_old: False
+
+- long_pair: cpp-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-cpp-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": [
+    [
+      31988
+    ]
+  ],
+  "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": 31988,
+  "decoder_vocab_size": 31989,
+  "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": 31989,
+  "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": 31988,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 31989
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      31988
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 31988,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 31988,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.0.dev0"
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"cpp-cpp","source_languages":"cpp","target_languages":"cpp","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/cpp-cpp\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["id","cpp"],"src_constituents":["zsm_Latn","ind","pap","min","tmw_Latn","max_Latn","zlm_Latn"],"tgt_constituents":["zsm_Latn","ind","pap","min","tmw_Latn","max_Latn","zlm_Latn"],"src_multilingual":true,"tgt_multilingual":true,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/cpp-cpp\/opus-2020-07-26.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/cpp-cpp\/opus-2020-07-26.test.txt","src_alpha3":"cpp","tgt_alpha3":"cpp","short_pair":"cpp-cpp","chrF2_score":0.369,"bleu":21.1,"brevity_penalty":0.882,"ref_len":18.0,"src_name":"Creoles and pidgins, Portuguese-based","tgt_name":"Creoles and pidgins, Portuguese-based","train_date":"2020-07-26","src_alpha2":"cpp","tgt_alpha2":"cpp","prefer_old":false,"long_pair":"cpp-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 sha256:9909cf0327b05075c6cf43059bd7b147ffc00002917775126d71edc6512a9654
+size 244346385

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cc6ac66cf8727264edcbbe258acfd3c6b1a9ebc89f0523af41ab7a0570385c
+size 831150

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77f1367469313d52b0d39f4ab41fc9cf8ffb90f21802742939265b39c2bf082
+size 831150

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a1272bd60107d24c1ccbdc5d629683ba941789654d160e31ff39899bda1fb5
+size 244707928

tokenizer_config.json

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