Add files using upload-large-folder tool

Helsinki-NLP-opus-mt-fi-ZH/README.md

@@ -0,0 +1,26 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi-ZH
+
+* source languages: fi
+* target languages: cmn,cn,yue,ze_zh,zh_cn,zh_CN,zh_HK,zh_tw,zh_TW,zh_yue,zhs,zht,zh
+*  OPUS readme: [fi-cmn+cn+yue+ze_zh+zh_cn+zh_CN+zh_HK+zh_tw+zh_TW+zh_yue+zhs+zht+zh](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi-cmn+cn+yue+ze_zh+zh_cn+zh_CN+zh_HK+zh_tw+zh_TW+zh_yue+zhs+zht+zh/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* 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-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/fi-cmn+cn+yue+ze_zh+zh_cn+zh_CN+zh_HK+zh_tw+zh_TW+zh_yue+zhs+zht+zh/opus-2020-01-16.zip)
+* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-cmn+cn+yue+ze_zh+zh_cn+zh_CN+zh_HK+zh_tw+zh_TW+zh_yue+zhs+zht+zh/opus-2020-01-16.test.txt)
+* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-cmn+cn+yue+ze_zh+zh_cn+zh_CN+zh_HK+zh_tw+zh_TW+zh_yue+zhs+zht+zh/opus-2020-01-16.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| bible-uedin.fi.zh 	| 23.4 	| 0.326 |
+

Helsinki-NLP-opus-mt-fi-ZH/config.json

@@ -0,0 +1,55 @@
+{
+  "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": 62932,
+  "decoder_vocab_size": 62933,
+  "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": 62932,
+  "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": 62933
+}

Helsinki-NLP-opus-mt-fi-ZH/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62932
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62932,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62932,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-fi-ZH/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi-ZH/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
+    },
+    "62932": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "cmn+cn+yue+ze_zh+zh_cn+zh_CN+zh_HK+zh_tw+zh_TW+zh_yue+zhs+zht+zh",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-fi-wls/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi-wls
+
+* source languages: fi
+* target languages: wls
+*  OPUS readme: [fi-wls](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi-wls/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/fi-wls/opus-2020-01-24.zip)
+* test set translations: [opus-2020-01-24.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-wls/opus-2020-01-24.test.txt)
+* test set scores: [opus-2020-01-24.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-wls/opus-2020-01-24.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.fi.wls 	| 24.7 	| 0.466 |
+

Helsinki-NLP-opus-mt-fi-wls/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi-wls/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
+    },
+    "42341": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "wls",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-fi-xh/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi-xh
+
+* source languages: fi
+* target languages: xh
+*  OPUS readme: [fi-xh](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi-xh/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/fi-xh/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-xh/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-xh/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.fi.xh 	| 25.3 	| 0.554 |
+

Helsinki-NLP-opus-mt-fi-xh/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": 61946,
+  "decoder_vocab_size": 61947,
+  "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": 61946,
+  "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": 61947
+}

Helsinki-NLP-opus-mt-fi-xh/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61946
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61946,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61946,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-fi-xh/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi-xh/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
+    },
+    "61946": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "xh",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-fi-yap/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi-yap
+
+* source languages: fi
+* target languages: yap
+*  OPUS readme: [fi-yap](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi-yap/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/fi-yap/opus-2020-01-08.zip)
+* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-yap/opus-2020-01-08.test.txt)
+* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-yap/opus-2020-01-08.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.fi.yap 	| 25.4 	| 0.445 |
+

Helsinki-NLP-opus-mt-fi-yap/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": 47160,
+  "decoder_vocab_size": 47161,
+  "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": 47160,
+  "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": 47161
+}

Helsinki-NLP-opus-mt-fi-yap/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      47160
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 47160,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 47160,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-fi-yap/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi-yap/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
+    },
+    "47160": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "yap",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-fi-yo/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi-yo
+
+* source languages: fi
+* target languages: yo
+*  OPUS readme: [fi-yo](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi-yo/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/fi-yo/opus-2020-01-24.zip)
+* test set translations: [opus-2020-01-24.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-yo/opus-2020-01-24.test.txt)
+* test set scores: [opus-2020-01-24.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-yo/opus-2020-01-24.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.fi.yo 	| 25.8 	| 0.427 |
+

Helsinki-NLP-opus-mt-fi-yo/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": 61109,
+  "decoder_vocab_size": 61110,
+  "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": 61109,
+  "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": 61110
+}

Helsinki-NLP-opus-mt-fi-yo/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61109
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61109,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61109,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-fi-yo/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi-yo/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
+    },
+    "61109": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "yo",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-fi-zne/README.md

@@ -0,0 +1,25 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi-zne
+
+* source languages: fi
+* target languages: zne
+*  OPUS readme: [fi-zne](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi-zne/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-01-09.zip](https://object.pouta.csc.fi/OPUS-MT-models/fi-zne/opus-2020-01-09.zip)
+* test set translations: [opus-2020-01-09.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-zne/opus-2020-01-09.test.txt)
+* test set scores: [opus-2020-01-09.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi-zne/opus-2020-01-09.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| JW300.fi.zne 	| 22.7 	| 0.464 |
+

Helsinki-NLP-opus-mt-fi-zne/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": 54788,
+  "decoder_vocab_size": 54789,
+  "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": 54788,
+  "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": 54789
+}

Helsinki-NLP-opus-mt-fi-zne/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      54788
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 54788,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 54788,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-fi-zne/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi-zne/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
+    },
+    "54788": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "zne",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

Helsinki-NLP-opus-mt-fi_nb_no_nn_ru_sv_en-SAMI/README.md

@@ -0,0 +1,26 @@
+---
+tags:
+- translation
+license: apache-2.0
+---
+
+### opus-mt-fi_nb_no_nn_ru_sv_en-SAMI
+
+* source languages: fi,nb,no,nn,ru,sv,en
+* target languages: se,sma,smj,smn,sms
+*  OPUS readme: [fi+nb+no+nn+ru+sv+en-se+sma+smj+smn+sms](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/fi+nb+no+nn+ru+sv+en-se+sma+smj+smn+sms/README.md)
+
+*  dataset: opus+giella
+* model: transformer-align
+* 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+giella-2020-04-18.zip](https://object.pouta.csc.fi/OPUS-MT-models/fi+nb+no+nn+ru+sv+en-se+sma+smj+smn+sms/opus+giella-2020-04-18.zip)
+* test set translations: [opus+giella-2020-04-18.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi+nb+no+nn+ru+sv+en-se+sma+smj+smn+sms/opus+giella-2020-04-18.test.txt)
+* test set scores: [opus+giella-2020-04-18.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/fi+nb+no+nn+ru+sv+en-se+sma+smj+smn+sms/opus+giella-2020-04-18.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| giella.fi.sms 	| 58.4 	| 0.776 |
+

Helsinki-NLP-opus-mt-fi_nb_no_nn_ru_sv_en-SAMI/config.json

@@ -0,0 +1,54 @@
+{
+  "_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,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58100,
+  "decoder_vocab_size": 7176,
+  "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_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 7175,
+  "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": 7176
+}

Helsinki-NLP-opus-mt-fi_nb_no_nn_ru_sv_en-SAMI/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 58100,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "num_beams": 4,
+  "pad_token_id": 7175,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}

Helsinki-NLP-opus-mt-fi_nb_no_nn_ru_sv_en-SAMI/special_tokens_map.json

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

Helsinki-NLP-opus-mt-fi_nb_no_nn_ru_sv_en-SAMI/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
+    },
+    "7175": {
+      "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": "fi+nb+no+nn+ru+sv+en",
+  "sp_model_kwargs": {},
+  "target_lang": "se+sma+smj+smn+sms",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

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

@@ -0,0 +1,128 @@
+---
+language: 
+- se
+- fi
+- hu
+- et
+- fiu
+- en
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### fiu-eng
+
+* source group: Finno-Ugrian languages 
+* target group: English 
+*  OPUS readme: [fiu-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fiu-eng/README.md)
+
+*  model: transformer
+* source language(s): est fin fkv_Latn hun izh kpv krl liv_Latn mdf mhr myv sma sme udm vro
+* target language(s): eng
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus2m-2020-07-31.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fiu-eng/opus2m-2020-07-31.zip)
+* test set translations: [opus2m-2020-07-31.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fiu-eng/opus2m-2020-07-31.test.txt)
+* test set scores: [opus2m-2020-07-31.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fiu-eng/opus2m-2020-07-31.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newsdev2015-enfi-fineng.fin.eng 	| 22.9 	| 0.513 |
+| newsdev2018-enet-esteng.est.eng 	| 26.3 	| 0.543 |
+| newssyscomb2009-huneng.hun.eng 	| 21.2 	| 0.494 |
+| newstest2009-huneng.hun.eng 	| 19.8 	| 0.486 |
+| newstest2015-enfi-fineng.fin.eng 	| 24.1 	| 0.521 |
+| newstest2016-enfi-fineng.fin.eng 	| 25.6 	| 0.541 |
+| newstest2017-enfi-fineng.fin.eng 	| 28.7 	| 0.560 |
+| newstest2018-enet-esteng.est.eng 	| 26.5 	| 0.549 |
+| newstest2018-enfi-fineng.fin.eng 	| 21.2 	| 0.490 |
+| newstest2019-fien-fineng.fin.eng 	| 25.6 	| 0.533 |
+| newstestB2016-enfi-fineng.fin.eng 	| 21.6 	| 0.500 |
+| newstestB2017-enfi-fineng.fin.eng 	| 24.3 	| 0.526 |
+| newstestB2017-fien-fineng.fin.eng 	| 24.3 	| 0.526 |
+| Tatoeba-test.chm-eng.chm.eng 	| 1.2 	| 0.163 |
+| Tatoeba-test.est-eng.est.eng 	| 55.3 	| 0.706 |
+| Tatoeba-test.fin-eng.fin.eng 	| 48.7 	| 0.660 |
+| Tatoeba-test.fkv-eng.fkv.eng 	| 11.5 	| 0.384 |
+| Tatoeba-test.hun-eng.hun.eng 	| 46.7 	| 0.638 |
+| Tatoeba-test.izh-eng.izh.eng 	| 48.3 	| 0.678 |
+| Tatoeba-test.kom-eng.kom.eng 	| 0.7 	| 0.113 |
+| Tatoeba-test.krl-eng.krl.eng 	| 36.1 	| 0.485 |
+| Tatoeba-test.liv-eng.liv.eng 	| 2.1 	| 0.086 |
+| Tatoeba-test.mdf-eng.mdf.eng 	| 0.9 	| 0.120 |
+| Tatoeba-test.multi.eng 	| 47.8 	| 0.648 |
+| Tatoeba-test.myv-eng.myv.eng 	| 0.7 	| 0.121 |
+| Tatoeba-test.sma-eng.sma.eng 	| 1.7 	| 0.101 |
+| Tatoeba-test.sme-eng.sme.eng 	| 7.8 	| 0.229 |
+| Tatoeba-test.udm-eng.udm.eng 	| 0.9 	| 0.166 |
+
+
+### System Info: 
+- hf_name: fiu-eng
+
+- source_languages: fiu
+
+- target_languages: eng
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fiu-eng/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['se', 'fi', 'hu', 'et', 'fiu', 'en']
+
+- src_constituents: {'izh', 'mdf', 'vep', 'vro', 'sme', 'myv', 'fkv_Latn', 'krl', 'fin', 'hun', 'kpv', 'udm', 'liv_Latn', 'est', 'mhr', 'sma'}
+
+- tgt_constituents: {'eng'}
+
+- src_multilingual: True
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/fiu-eng/opus2m-2020-07-31.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/fiu-eng/opus2m-2020-07-31.test.txt
+
+- src_alpha3: fiu
+
+- tgt_alpha3: eng
+
+- short_pair: fiu-en
+
+- chrF2_score: 0.648
+
+- bleu: 47.8
+
+- brevity_penalty: 0.988
+
+- ref_len: 71020.0
+
+- src_name: Finno-Ugrian languages
+
+- tgt_name: English
+
+- train_date: 2020-07-31
+
+- src_alpha2: fiu
+
+- tgt_alpha2: en
+
+- prefer_old: False
+
+- long_pair: fiu-eng
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

Helsinki-NLP-opus-mt-fiu-en/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": 58922,
+  "decoder_vocab_size": 58923,
+  "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": 58923,
+  "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": 58922,
+  "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": 58923
+}

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

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      58922
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 58922,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 58922,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.3"
+}