Initial commit

README.md

@@ -0,0 +1,96 @@
+---
+language:
+- he
+- it
+
+tags:
+- translation
+
+license: apache-2.0
+---
+### he-it
+
+* source group: Hebrew 
+* target group: Italian 
+*  OPUS readme: [heb-ita](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/heb-ita/README.md)
+
+*  model: transformer
+* source language(s): heb
+* target language(s): ita
+* model: transformer
+* pre-processing: normalization + SentencePiece (spm32k,spm32k)
+* download original weights: [opus-2020-12-10.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-ita/opus-2020-12-10.zip)
+* test set translations: [opus-2020-12-10.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-ita/opus-2020-12-10.test.txt)
+* test set scores: [opus-2020-12-10.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/heb-ita/opus-2020-12-10.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.heb.ita 	| 41.1 	| 0.643 |
+
+
+### System Info: 
+- hf_name: he-it
+
+- source_languages: heb
+
+- target_languages: ita
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/heb-ita/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['he', 'it']
+
+- src_constituents: ('Hebrew', {'heb'})
+
+- tgt_constituents: ('Italian', {'ita'})
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- long_pair: heb-ita
+
+- prepro:  normalization + SentencePiece (spm32k,spm32k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/heb-ita/opus-2020-12-10.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/heb-ita/opus-2020-12-10.test.txt
+
+- src_alpha3: heb
+
+- tgt_alpha3: ita
+
+- chrF2_score: 0.643
+
+- bleu: 41.1
+
+- brevity_penalty: 0.997
+
+- ref_len: 11464.0
+
+- src_name: Hebrew
+
+- tgt_name: Italian
+
+- train_date: 2020-12-10 00:00:00
+
+- src_alpha2: he
+
+- tgt_alpha2: it
+
+- prefer_old: False
+
+- short_pair: he-it
+
+- helsinki_git_sha: b317f78a3ec8a556a481b6a53dc70dc11769ca96
+
+- transformers_git_sha: 1310e1a758edc8e89ec363db76863c771fbeb1de
+
+- port_machine: LM0-400-22516.local
+
+- port_time: 2020-12-11-16:01

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,
+  "bad_words_ids": [
+    [
+      63129
+    ]
+  ],
+  "bos_token_id": 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": 63129,
+  "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": 2,
+  "force_bos_token_to_be_generated": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 63129,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "use_cache": true,
+  "vocab_size": 63130
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"he-it","source_languages":"heb","target_languages":"ita","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/heb-ita\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["he","it"],"src_constituents":["Hebrew",["heb"]],"tgt_constituents":["Italian",["ita"]],"src_multilingual":false,"tgt_multilingual":false,"long_pair":"heb-ita","prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/heb-ita\/opus-2020-12-10.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/heb-ita\/opus-2020-12-10.test.txt","src_alpha3":"heb","tgt_alpha3":"ita","chrF2_score":0.643,"bleu":41.1,"brevity_penalty":0.997,"ref_len":11464.0,"src_name":"Hebrew","tgt_name":"Italian","train_date":1607558400000,"src_alpha2":"he","tgt_alpha2":"it","prefer_old":false,"short_pair":"he-it","helsinki_git_sha":"b317f78a3ec8a556a481b6a53dc70dc11769ca96","transformers_git_sha":"1310e1a758edc8e89ec363db76863c771fbeb1de","port_machine":"LM0-400-22516.local","port_time":"2020-12-11-16:01"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71a7fd963bbdfb08fc36b37ff95b6eb686dc23d26cabe14883637672fadcc93
+size 153136027

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "heb", "target_lang": "ita", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "marian_ckpt/heb-ita"}