Add files using upload-large-folder tool

Helsinki-NLP-opus-mt-ar-en/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62833": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ar",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-eo/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- ar
+- eo
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### ara-epo
+
+* source group: Arabic 
+* target group: Esperanto 
+*  OPUS readme: [ara-epo](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-epo/README.md)
+
+*  model: transformer-align
+* source language(s): apc apc_Latn ara arq arq_Latn arz
+* target language(s): epo
+* model: transformer-align
+* pre-processing: normalization + SentencePiece (spm4k,spm4k)
+* download original weights: [opus-2020-06-16.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-epo/opus-2020-06-16.zip)
+* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-epo/opus-2020-06-16.test.txt)
+* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-epo/opus-2020-06-16.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara.epo 	| 18.9 	| 0.376 |
+
+
+### System Info: 
+- hf_name: ara-epo
+
+- source_languages: ara
+
+- target_languages: epo
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-epo/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['ar', 'eo']
+
+- src_constituents: {'apc', 'ara', 'arq_Latn', 'arq', 'afb', 'ara_Latn', 'apc_Latn', 'arz'}
+
+- tgt_constituents: {'epo'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm4k,spm4k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-epo/opus-2020-06-16.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-epo/opus-2020-06-16.test.txt
+
+- src_alpha3: ara
+
+- tgt_alpha3: epo
+
+- short_pair: ar-eo
+
+- chrF2_score: 0.376
+
+- bleu: 18.9
+
+- brevity_penalty: 0.948
+
+- ref_len: 4506.0
+
+- src_name: Arabic
+
+- tgt_name: Esperanto
+
+- train_date: 2020-06-16
+
+- src_alpha2: ar
+
+- tgt_alpha2: eo
+
+- prefer_old: False
+
+- long_pair: ara-epo
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-ar-eo/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 7740,
+  "decoder_vocab_size": 7741,
+  "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": 7741,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 7740,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 7741
+}

Helsinki-NLP-opus-mt-ar-eo/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      7740
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 7740,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 7740,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-eo/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-eo/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7740": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ara",
+  "sp_model_kwargs": {},
+  "target_lang": "epo",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-es/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- ar
+- es
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### ara-spa
+
+* source group: Arabic 
+* target group: Spanish 
+*  OPUS readme: [ara-spa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-spa/README.md)
+
+*  model: transformer
+* source language(s): apc apc_Latn ara arq
+* target language(s): spa
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-07-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-spa/opus-2020-07-03.zip)
+* test set translations: [opus-2020-07-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-spa/opus-2020-07-03.test.txt)
+* test set scores: [opus-2020-07-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-spa/opus-2020-07-03.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara.spa 	| 46.0 	| 0.641 |
+
+
+### System Info: 
+- hf_name: ara-spa
+
+- source_languages: ara
+
+- target_languages: spa
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-spa/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['ar', 'es']
+
+- src_constituents: {'apc', 'ara', 'arq_Latn', 'arq', 'afb', 'ara_Latn', 'apc_Latn', 'arz'}
+
+- tgt_constituents: {'spa'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-spa/opus-2020-07-03.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-spa/opus-2020-07-03.test.txt
+
+- src_alpha3: ara
+
+- tgt_alpha3: spa
+
+- short_pair: ar-es
+
+- chrF2_score: 0.6409999999999999
+
+- bleu: 46.0
+
+- brevity_penalty: 0.9620000000000001
+
+- ref_len: 9708.0
+
+- src_name: Arabic
+
+- tgt_name: Spanish
+
+- train_date: 2020-07-03
+
+- src_alpha2: ar
+
+- tgt_alpha2: es
+
+- prefer_old: False
+
+- long_pair: ara-spa
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-ar-es/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 62525,
+  "decoder_vocab_size": 62526,
+  "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": 62526,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62525,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 62526
+}

Helsinki-NLP-opus-mt-ar-es/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62525
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62525,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62525,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-es/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-es/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62525": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ara",
+  "sp_model_kwargs": {},
+  "target_lang": "spa",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-fr/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-ar-fr
+
+* source languages: ar
+* target languages: fr
+*  OPUS readme: [ar-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ar-fr/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-24.zip](https://object.pouta.csc.fi/OPUS-MT-models/ar-fr/opus-2020-01-24.zip)
+* test set translations: [opus-2020-01-24.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ar-fr/opus-2020-01-24.test.txt)
+* test set scores: [opus-2020-01-24.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ar-fr/opus-2020-01-24.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba.ar.fr 	| 43.5 	| 0.602 |
+

Helsinki-NLP-opus-mt-ar-fr/config.json

@@ -0,0 +1,56 @@
+{
+  "_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,
+  "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": 64504,
+  "decoder_vocab_size": 64505,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64504,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 64505
+}

Helsinki-NLP-opus-mt-ar-fr/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      64504
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64504,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 64504,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-fr/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-fr/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64504": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ar",
+  "sp_model_kwargs": {},
+  "target_lang": "fr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-he/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- ar
+- he
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### ara-heb
+
+* source group: Arabic 
+* target group: Hebrew 
+*  OPUS readme: [ara-heb](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-heb/README.md)
+
+*  model: transformer
+* source language(s): apc apc_Latn ara arq arz
+* target language(s): heb
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-07-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-heb/opus-2020-07-03.zip)
+* test set translations: [opus-2020-07-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-heb/opus-2020-07-03.test.txt)
+* test set scores: [opus-2020-07-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-heb/opus-2020-07-03.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara.heb 	| 40.4 	| 0.605 |
+
+
+### System Info: 
+- hf_name: ara-heb
+
+- source_languages: ara
+
+- target_languages: heb
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-heb/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['ar', 'he']
+
+- src_constituents: {'apc', 'ara', 'arq_Latn', 'arq', 'afb', 'ara_Latn', 'apc_Latn', 'arz'}
+
+- tgt_constituents: {'heb'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-heb/opus-2020-07-03.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-heb/opus-2020-07-03.test.txt
+
+- src_alpha3: ara
+
+- tgt_alpha3: heb
+
+- short_pair: ar-he
+
+- chrF2_score: 0.605
+
+- bleu: 40.4
+
+- brevity_penalty: 1.0
+
+- ref_len: 6801.0
+
+- src_name: Arabic
+
+- tgt_name: Hebrew
+
+- train_date: 2020-07-03
+
+- src_alpha2: ar
+
+- tgt_alpha2: he
+
+- prefer_old: False
+
+- long_pair: ara-heb
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-ar-he/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 63333,
+  "decoder_vocab_size": 63334,
+  "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": 63334,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 63333,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 63334
+}

Helsinki-NLP-opus-mt-ar-he/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      63333
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 63333,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 63333,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-he/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-he/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63333": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ara",
+  "sp_model_kwargs": {},
+  "target_lang": "heb",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-it/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- ar
+- it
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### ara-ita
+
+* source group: Arabic 
+* target group: Italian 
+*  OPUS readme: [ara-ita](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-ita/README.md)
+
+*  model: transformer
+* source language(s): ara
+* target language(s): ita
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-07-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-ita/opus-2020-07-03.zip)
+* test set translations: [opus-2020-07-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-ita/opus-2020-07-03.test.txt)
+* test set scores: [opus-2020-07-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-ita/opus-2020-07-03.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara.ita 	| 44.2 	| 0.658 |
+
+
+### System Info: 
+- hf_name: ara-ita
+
+- source_languages: ara
+
+- target_languages: ita
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-ita/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['ar', 'it']
+
+- src_constituents: {'apc', 'ara', 'arq_Latn', 'arq', 'afb', 'ara_Latn', 'apc_Latn', 'arz'}
+
+- tgt_constituents: {'ita'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-ita/opus-2020-07-03.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-ita/opus-2020-07-03.test.txt
+
+- src_alpha3: ara
+
+- tgt_alpha3: ita
+
+- short_pair: ar-it
+
+- chrF2_score: 0.6579999999999999
+
+- bleu: 44.2
+
+- brevity_penalty: 0.9890000000000001
+
+- ref_len: 1495.0
+
+- src_name: Arabic
+
+- tgt_name: Italian
+
+- train_date: 2020-07-03
+
+- src_alpha2: ar
+
+- tgt_alpha2: it
+
+- prefer_old: False
+
+- long_pair: ara-ita
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-ar-it/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 63293,
+  "decoder_vocab_size": 63294,
+  "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": 63294,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 63293,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 63294
+}

Helsinki-NLP-opus-mt-ar-it/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      63293
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 63293,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 63293,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-it/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-it/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63293": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ara",
+  "sp_model_kwargs": {},
+  "target_lang": "ita",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-pl/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- ar
+- pl
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### ara-pol
+
+* source group: Arabic 
+* target group: Polish 
+*  OPUS readme: [ara-pol](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-pol/README.md)
+
+*  model: transformer
+* source language(s): ara arz
+* target language(s): pol
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-07-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-pol/opus-2020-07-03.zip)
+* test set translations: [opus-2020-07-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-pol/opus-2020-07-03.test.txt)
+* test set scores: [opus-2020-07-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-pol/opus-2020-07-03.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara.pol 	| 38.0 	| 0.623 |
+
+
+### System Info: 
+- hf_name: ara-pol
+
+- source_languages: ara
+
+- target_languages: pol
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-pol/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['ar', 'pl']
+
+- src_constituents: {'apc', 'ara', 'arq_Latn', 'arq', 'afb', 'ara_Latn', 'apc_Latn', 'arz'}
+
+- tgt_constituents: {'pol'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-pol/opus-2020-07-03.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-pol/opus-2020-07-03.test.txt
+
+- src_alpha3: ara
+
+- tgt_alpha3: pol
+
+- short_pair: ar-pl
+
+- chrF2_score: 0.623
+
+- bleu: 38.0
+
+- brevity_penalty: 0.948
+
+- ref_len: 1171.0
+
+- src_name: Arabic
+
+- tgt_name: Polish
+
+- train_date: 2020-07-03
+
+- src_alpha2: ar
+
+- tgt_alpha2: pl
+
+- prefer_old: False
+
+- long_pair: ara-pol
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-ar-pl/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 65000,
+  "decoder_vocab_size": 65001,
+  "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": 65001,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 65001
+}

Helsinki-NLP-opus-mt-ar-pl/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 65000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 65000,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-pl/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-pl/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ara",
+  "sp_model_kwargs": {},
+  "target_lang": "pol",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-ru/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- ar
+- ru
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### ara-rus
+
+* source group: Arabic 
+* target group: Russian 
+*  OPUS readme: [ara-rus](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-rus/README.md)
+
+*  model: transformer
+* source language(s): apc ara arz
+* target language(s): rus
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-07-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-rus/opus-2020-07-03.zip)
+* test set translations: [opus-2020-07-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-rus/opus-2020-07-03.test.txt)
+* test set scores: [opus-2020-07-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-rus/opus-2020-07-03.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.ara.rus 	| 42.5 	| 0.605 |
+
+
+### System Info: 
+- hf_name: ara-rus
+
+- source_languages: ara
+
+- target_languages: rus
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-rus/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['ar', 'ru']
+
+- src_constituents: {'apc', 'ara', 'arq_Latn', 'arq', 'afb', 'ara_Latn', 'apc_Latn', 'arz'}
+
+- tgt_constituents: {'rus'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-rus/opus-2020-07-03.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-rus/opus-2020-07-03.test.txt
+
+- src_alpha3: ara
+
+- tgt_alpha3: rus
+
+- short_pair: ar-ru
+
+- chrF2_score: 0.605
+
+- bleu: 42.5
+
+- brevity_penalty: 0.97
+
+- ref_len: 21830.0
+
+- src_name: Arabic
+
+- tgt_name: Russian
+
+- train_date: 2020-07-03
+
+- src_alpha2: ar
+
+- tgt_alpha2: ru
+
+- prefer_old: False
+
+- long_pair: ara-rus
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-ar-ru/config.json

@@ -0,0 +1,56 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 62605,
+  "decoder_vocab_size": 62606,
+  "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": 62606,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "is_transformers_support_available": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62605,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 62606
+}

Helsinki-NLP-opus-mt-ar-ru/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62605
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62605,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62605,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-ar-ru/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-ar-ru/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62605": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ara",
+  "sp_model_kwargs": {},
+  "target_lang": "rus",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}