Add files using upload-large-folder tool

Helsinki-NLP-opus-mt-en-ROMANCE/README.md

@@ -0,0 +1,26 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-ROMANCE
+
+* source languages: en
+* target languages: fr,fr_BE,fr_CA,fr_FR,wa,frp,oc,ca,rm,lld,fur,lij,lmo,es,es_AR,es_CL,es_CO,es_CR,es_DO,es_EC,es_ES,es_GT,es_HN,es_MX,es_NI,es_PA,es_PE,es_PR,es_SV,es_UY,es_VE,pt,pt_br,pt_BR,pt_PT,gl,lad,an,mwl,it,it_IT,co,nap,scn,vec,sc,ro,la
+*  OPUS readme: [en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/README.md)
+
+*  dataset: opus
+* model: transformer
+* pre-processing: normalization + SentencePiece
+* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
+* download original weights: [opus-2020-04-21.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/opus-2020-04-21.zip)
+* test set translations: [opus-2020-04-21.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/opus-2020-04-21.test.txt)
+* test set scores: [opus-2020-04-21.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/opus-2020-04-21.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba.en.la 	| 50.1 	| 0.693 |
+

Helsinki-NLP-opus-mt-en-ROMANCE/config.json

@@ -0,0 +1,59 @@
+{
+  "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,
+  "do_blenderbot_90_layernorm": false,
+  "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": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "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-en-ROMANCE/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-en-ROMANCE/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-ROMANCE/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": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-rn/README.md

@@ -0,0 +1,97 @@
+---
+language: 
+- en
+- rn
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-run
+
+* source group: English 
+* target group: Rundi 
+*  OPUS readme: [eng-run](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-run/README.md)
+
+*  model: transformer-align
+* source language(s): eng
+* target language(s): run
+* 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/eng-run/opus-2020-06-16.zip)
+* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-run/opus-2020-06-16.test.txt)
+* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-run/opus-2020-06-16.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.eng.run 	| 10.4 	| 0.436 |
+
+
+### System Info: 
+- hf_name: eng-run
+
+- source_languages: eng
+
+- target_languages: run
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-run/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'rn']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: {'run'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm4k,spm4k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-run/opus-2020-06-16.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-run/opus-2020-06-16.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: run
+
+- short_pair: en-rn
+
+- chrF2_score: 0.436
+
+- bleu: 10.4
+
+- brevity_penalty: 1.0
+
+- ref_len: 6710.0
+
+- src_name: English
+
+- tgt_name: Rundi
+
+- train_date: 2020-06-16
+
+- src_alpha2: en
+
+- tgt_alpha2: rn
+
+- prefer_old: False
+
+- long_pair: eng-run
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-en-rn/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": 7527,
+  "decoder_vocab_size": 7528,
+  "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": 7528,
+  "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": 7527,
+  "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": 7528
+}

Helsinki-NLP-opus-mt-en-rn/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      7527
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 7527,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 7527,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-rn/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-rn/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
+    },
+    "7527": {
+      "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": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "run",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-rnd/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-rnd
+
+* source languages: en
+* target languages: rnd
+*  OPUS readme: [en-rnd](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-rnd/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-rnd/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-rnd/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-rnd/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.en.rnd 	| 34.5 	| 0.571 |
+

Helsinki-NLP-opus-mt-en-rnd/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": 53831,
+  "decoder_vocab_size": 53832,
+  "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": 53831,
+  "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": 53832
+}

Helsinki-NLP-opus-mt-en-rnd/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      53831
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 53831,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 53831,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-rnd/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-rnd/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
+    },
+    "53831": {
+      "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": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "rnd",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-ro/README.md

@@ -0,0 +1,27 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-ro
+
+* source languages: en
+* target languages: ro
+*  OPUS readme: [en-ro](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-ro/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2019-12-18.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-ro/opus-2019-12-18.zip)
+* test set translations: [opus-2019-12-18.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ro/opus-2019-12-18.test.txt)
+* test set scores: [opus-2019-12-18.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ro/opus-2019-12-18.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newsdev2016-enro.en.ro 	| 30.8 	| 0.592 |
+| newstest2016-enro.en.ro 	| 28.8 	| 0.571 |
+| Tatoeba.en.ro 	| 45.3 	| 0.670 |
+

Helsinki-NLP-opus-mt-en-ro/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": 59542,
+  "decoder_vocab_size": 59543,
+  "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": 59542,
+  "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": 59543
+}

Helsinki-NLP-opus-mt-en-ro/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      59542
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59542,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59542,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-ro/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-ro/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
+    },
+    "59542": {
+      "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": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "ro",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-roa/README.md

@@ -0,0 +1,161 @@
+---
+language: 
+- en
+- it
+- ca
+- rm
+- es
+- ro
+- gl
+- co
+- wa
+- pt
+- oc
+- an
+- id
+- fr
+- ht
+- roa
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### eng-roa
+
+* source group: English 
+* target group: Romance languages 
+*  OPUS readme: [eng-roa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-roa/README.md)
+
+*  model: transformer
+* source language(s): eng
+* target language(s): arg ast cat cos egl ext fra frm_Latn gcf_Latn glg hat ind ita lad lad_Latn lij lld_Latn lmo max_Latn mfe min mwl oci pap pms por roh ron scn spa tmw_Latn vec wln 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-roa/opus2m-2020-08-01.zip)
+* test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/opus2m-2020-08-01.test.txt)
+* test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/opus2m-2020-08-01.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newsdev2016-enro-engron.eng.ron 	| 27.6 	| 0.567 |
+| newsdiscussdev2015-enfr-engfra.eng.fra 	| 30.2 	| 0.575 |
+| newsdiscusstest2015-enfr-engfra.eng.fra 	| 35.5 	| 0.612 |
+| newssyscomb2009-engfra.eng.fra 	| 27.9 	| 0.570 |
+| newssyscomb2009-engita.eng.ita 	| 29.3 	| 0.590 |
+| newssyscomb2009-engspa.eng.spa 	| 29.6 	| 0.570 |
+| news-test2008-engfra.eng.fra 	| 25.2 	| 0.538 |
+| news-test2008-engspa.eng.spa 	| 27.3 	| 0.548 |
+| newstest2009-engfra.eng.fra 	| 26.9 	| 0.560 |
+| newstest2009-engita.eng.ita 	| 28.7 	| 0.583 |
+| newstest2009-engspa.eng.spa 	| 29.0 	| 0.568 |
+| newstest2010-engfra.eng.fra 	| 29.3 	| 0.574 |
+| newstest2010-engspa.eng.spa 	| 34.2 	| 0.601 |
+| newstest2011-engfra.eng.fra 	| 31.4 	| 0.592 |
+| newstest2011-engspa.eng.spa 	| 35.0 	| 0.599 |
+| newstest2012-engfra.eng.fra 	| 29.5 	| 0.576 |
+| newstest2012-engspa.eng.spa 	| 35.5 	| 0.603 |
+| newstest2013-engfra.eng.fra 	| 29.9 	| 0.567 |
+| newstest2013-engspa.eng.spa 	| 32.1 	| 0.578 |
+| newstest2016-enro-engron.eng.ron 	| 26.1 	| 0.551 |
+| Tatoeba-test.eng-arg.eng.arg 	| 1.4 	| 0.125 |
+| Tatoeba-test.eng-ast.eng.ast 	| 17.8 	| 0.406 |
+| Tatoeba-test.eng-cat.eng.cat 	| 48.3 	| 0.676 |
+| Tatoeba-test.eng-cos.eng.cos 	| 3.2 	| 0.275 |
+| Tatoeba-test.eng-egl.eng.egl 	| 0.2 	| 0.084 |
+| Tatoeba-test.eng-ext.eng.ext 	| 11.2 	| 0.344 |
+| Tatoeba-test.eng-fra.eng.fra 	| 45.3 	| 0.637 |
+| Tatoeba-test.eng-frm.eng.frm 	| 1.1 	| 0.221 |
+| Tatoeba-test.eng-gcf.eng.gcf 	| 0.6 	| 0.118 |
+| Tatoeba-test.eng-glg.eng.glg 	| 44.2 	| 0.645 |
+| Tatoeba-test.eng-hat.eng.hat 	| 28.0 	| 0.502 |
+| Tatoeba-test.eng-ita.eng.ita 	| 45.6 	| 0.674 |
+| Tatoeba-test.eng-lad.eng.lad 	| 8.2 	| 0.322 |
+| Tatoeba-test.eng-lij.eng.lij 	| 1.4 	| 0.182 |
+| Tatoeba-test.eng-lld.eng.lld 	| 0.8 	| 0.217 |
+| Tatoeba-test.eng-lmo.eng.lmo 	| 0.7 	| 0.190 |
+| Tatoeba-test.eng-mfe.eng.mfe 	| 91.9 	| 0.956 |
+| Tatoeba-test.eng-msa.eng.msa 	| 31.1 	| 0.548 |
+| Tatoeba-test.eng.multi 	| 42.9 	| 0.636 |
+| Tatoeba-test.eng-mwl.eng.mwl 	| 2.1 	| 0.234 |
+| Tatoeba-test.eng-oci.eng.oci 	| 7.9 	| 0.297 |
+| Tatoeba-test.eng-pap.eng.pap 	| 44.1 	| 0.648 |
+| Tatoeba-test.eng-pms.eng.pms 	| 2.1 	| 0.190 |
+| Tatoeba-test.eng-por.eng.por 	| 41.8 	| 0.639 |
+| Tatoeba-test.eng-roh.eng.roh 	| 3.5 	| 0.261 |
+| Tatoeba-test.eng-ron.eng.ron 	| 41.0 	| 0.635 |
+| Tatoeba-test.eng-scn.eng.scn 	| 1.7 	| 0.184 |
+| Tatoeba-test.eng-spa.eng.spa 	| 50.1 	| 0.689 |
+| Tatoeba-test.eng-vec.eng.vec 	| 3.2 	| 0.248 |
+| Tatoeba-test.eng-wln.eng.wln 	| 7.2 	| 0.220 |
+
+
+### System Info: 
+- hf_name: eng-roa
+
+- source_languages: eng
+
+- target_languages: roa
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-roa/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['en', 'it', 'ca', 'rm', 'es', 'ro', 'gl', 'co', 'wa', 'pt', 'oc', 'an', 'id', 'fr', 'ht', 'roa']
+
+- src_constituents: {'eng'}
+
+- tgt_constituents: {'ita', 'cat', 'roh', 'spa', 'pap', 'lmo', 'mwl', 'lij', 'lad_Latn', 'ext', 'ron', 'ast', 'glg', 'pms', 'zsm_Latn', 'gcf_Latn', 'lld_Latn', 'min', 'tmw_Latn', 'cos', 'wln', 'zlm_Latn', 'por', 'egl', 'oci', 'vec', 'arg', 'ind', 'fra', 'hat', 'lad', 'max_Latn', 'frm_Latn', 'scn', 'mfe'}
+
+- src_multilingual: False
+
+- tgt_multilingual: True
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/opus2m-2020-08-01.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/opus2m-2020-08-01.test.txt
+
+- src_alpha3: eng
+
+- tgt_alpha3: roa
+
+- short_pair: en-roa
+
+- chrF2_score: 0.636
+
+- bleu: 42.9
+
+- brevity_penalty: 0.978
+
+- ref_len: 72751.0
+
+- src_name: English
+
+- tgt_name: Romance languages
+
+- train_date: 2020-08-01
+
+- src_alpha2: en
+
+- tgt_alpha2: roa
+
+- prefer_old: False
+
+- long_pair: eng-roa
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-en-roa/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": 56670,
+  "decoder_vocab_size": 56671,
+  "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": 56671,
+  "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": 56670,
+  "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": 56671
+}

Helsinki-NLP-opus-mt-en-roa/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      56670
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 56670,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 56670,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-roa/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-roa/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
+    },
+    "56670": {
+      "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": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "roa",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

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

@@ -0,0 +1,32 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-ru
+
+* source languages: en
+* target languages: ru
+*  OPUS readme: [en-ru](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-ru/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-02-11.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-ru/opus-2020-02-11.zip)
+* 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)
+* 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)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newstest2012.en.ru 	| 31.1 	| 0.581 |
+| newstest2013.en.ru 	| 23.5 	| 0.513 |
+| newstest2015-enru.en.ru 	| 27.5 	| 0.564 |
+| newstest2016-enru.en.ru 	| 26.4 	| 0.548 |
+| newstest2017-enru.en.ru 	| 29.1 	| 0.572 |
+| newstest2018-enru.en.ru 	| 25.4 	| 0.554 |
+| newstest2019-enru.en.ru 	| 27.1 	| 0.533 |
+| Tatoeba.en.ru 	| 48.4 	| 0.669 |
+

Helsinki-NLP-opus-mt-en-ru/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": 62517,
+  "decoder_vocab_size": 62518,
+  "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": 62517,
+  "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": 62518
+}

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

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62517
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62517,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62517,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

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

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

Helsinki-NLP-opus-mt-en-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
+    },
+    "62517": {
+      "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": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "ru",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-run/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-run
+
+* source languages: en
+* target languages: run
+*  OPUS readme: [en-run](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-run/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-run/opus-2020-01-20.zip)
+* test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-run/opus-2020-01-20.test.txt)
+* test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-run/opus-2020-01-20.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.en.run 	| 34.2 	| 0.591 |
+

Helsinki-NLP-opus-mt-en-run/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": 61334,
+  "decoder_vocab_size": 61335,
+  "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": 61334,
+  "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": 61335
+}

Helsinki-NLP-opus-mt-en-run/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61334
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61334,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61334,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-en-run/special_tokens_map.json

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

Helsinki-NLP-opus-mt-en-run/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
+    },
+    "61334": {
+      "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": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "run",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-en-rw/README.md

@@ -0,0 +1,26 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-en-rw
+
+* source languages: en
+* target languages: rw
+*  OPUS readme: [en-rw](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-rw/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-rw/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-rw/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-rw/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.en.rw 	| 33.3 	| 0.569 |
+| Tatoeba.en.rw 	| 13.8 	| 0.503 |
+