README.md

@@ -1,104 +0,0 @@
----
-language: 
-- es
-- en
-
-tags:
-- translation
-
-license: apache-2.0
----
-
-### spa-eng
-
-* source group: Spanish 
-* target group: English 
-*  OPUS readme: [spa-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-eng/README.md)
-
-*  model: transformer
-* source language(s): spa
-* target language(s): eng
-* model: transformer
-* pre-processing: normalization + SentencePiece (spm32k,spm32k)
-* download original weights: [opus-2020-08-18.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.zip)
-* test set translations: [opus-2020-08-18.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.test.txt)
-* test set scores: [opus-2020-08-18.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.eval.txt)
-
-## Benchmarks
-
-| testset               | BLEU  | chr-F |
-|-----------------------|-------|-------|
-| newssyscomb2009-spaeng.spa.eng 	| 30.6 	| 0.570 |
-| news-test2008-spaeng.spa.eng 	| 27.9 	| 0.553 |
-| newstest2009-spaeng.spa.eng 	| 30.4 	| 0.572 |
-| newstest2010-spaeng.spa.eng 	| 36.1 	| 0.614 |
-| newstest2011-spaeng.spa.eng 	| 34.2 	| 0.599 |
-| newstest2012-spaeng.spa.eng 	| 37.9 	| 0.624 |
-| newstest2013-spaeng.spa.eng 	| 35.3 	| 0.609 |
-| Tatoeba-test.spa.eng 	| 59.6 	| 0.739 |
-
-
-### System Info: 
-- hf_name: spa-eng
-
-- source_languages: spa
-
-- target_languages: eng
-
-- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-eng/README.md
-
-- original_repo: Tatoeba-Challenge
-
-- tags: ['translation']
-
-- languages: ['es', 'en']
-
-- src_constituents: {'spa'}
-
-- tgt_constituents: {'eng'}
-
-- src_multilingual: False
-
-- tgt_multilingual: False
-
-- prepro:  normalization + SentencePiece (spm32k,spm32k)
-
-- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.zip
-
-- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.test.txt
-
-- src_alpha3: spa
-
-- tgt_alpha3: eng
-
-- short_pair: es-en
-
-- chrF2_score: 0.7390000000000001
-
-- bleu: 59.6
-
-- brevity_penalty: 0.9740000000000001
-
-- ref_len: 79376.0
-
-- src_name: Spanish
-
-- tgt_name: English
-
-- train_date: 2020-08-18 00:00:00
-
-- src_alpha2: es
-
-- tgt_alpha2: en
-
-- prefer_old: False
-
-- long_pair: spa-eng
-
-- helsinki_git_sha: d2f0910c89026c34a44e331e785dec1e0faa7b82
-
-- transformers_git_sha: f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9
-
-- port_machine: brutasse
-
-- port_time: 2020-08-24-18:20

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-es-en",
+  "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,
@@ -10,28 +10,23 @@
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      65000
+      58378
     ]
   ],
   "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_start_token_id": 58378,
-  "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,
-  "force_bos_token_to_be_generated": false,
-  "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -49,13 +44,10 @@
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": 4,
+  "num_beams": 6,
   "num_hidden_layers": 6,
-  "pad_token_id": 65000,
+  "pad_token_id": 58378,
   "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "transformers_version": "4.22.0.dev0",
+  "vocab_size": 58379
-  "use_cache": true,
-  "vocab_size": 65001
 }

generation_config.json

@@ -1,16 +0,0 @@
-{
-  "_from_model_config": true,
-  "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,
-  "transformers_version": "4.27.0.dev0"
-}

metadata.json

@@ -1 +0,0 @@
-{"hf_name":"spa-eng","source_languages":"spa","target_languages":"eng","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/spa-eng\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["es","en"],"src_constituents":["spa"],"tgt_constituents":["eng"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/spa-eng\/opus-2020-08-18.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/spa-eng\/opus-2020-08-18.test.txt","src_alpha3":"spa","tgt_alpha3":"eng","short_pair":"es-en","chrF2_score":0.739,"bleu":59.6,"brevity_penalty":0.974,"ref_len":79376.0,"src_name":"Spanish","tgt_name":"English","train_date":1597708800000,"src_alpha2":"es","tgt_alpha2":"en","prefer_old":false,"long_pair":"spa-eng","helsinki_git_sha":"d2f0910c89026c34a44e331e785dec1e0faa7b82","transformers_git_sha":"f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9","port_machine":"brutasse","port_time":"2020-08-24-18:20"}

tokenizer_config.json

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