byte-perfect re-sync from Helsinki-NLP/opus-mt-bnt-en (Phase D upgrade)

.gitattributes

@@ -6,6 +6,5 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
-model.safetensors filter=lfs diff=lfs merge=lfs -text
 source.spm filter=lfs diff=lfs merge=lfs -text
 target.spm filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-bnt-en",
+  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-bnt-en",
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,
@@ -8,6 +8,11 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      61728
+    ]
+  ],
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
@@ -38,19 +43,18 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": null,
+  "max_length": 512,
   "max_position_embeddings": 512,
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": null,
+  "num_beams": 4,
   "num_hidden_layers": 6,
   "pad_token_id": 61728,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.1",
+  "transformers_version": "4.22.0.dev0",
   "use_cache": true,
   "vocab_size": 61729
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 61728,
   "renormalize_logits": true,
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.32.0.dev0"
 }

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"bnt-eng","source_languages":"bnt","target_languages":"eng","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/bnt-eng\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["sn","zu","rw","lg","ts","ln","ny","xh","rn","bnt","en"],"src_constituents":["sna","zul","kin","lug","tso","lin","nya","xho","swh","run","toi_Latn","umb"],"tgt_constituents":["eng"],"src_multilingual":true,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/bnt-eng\/opus2m-2020-07-31.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/bnt-eng\/opus2m-2020-07-31.test.txt","src_alpha3":"bnt","tgt_alpha3":"eng","short_pair":"bnt-en","chrF2_score":0.394,"bleu":23.1,"brevity_penalty":1.0,"ref_len":14565.0,"src_name":"Bantu languages","tgt_name":"English","train_date":"2020-07-31","src_alpha2":"bnt","tgt_alpha2":"en","prefer_old":false,"long_pair":"bnt-eng","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9484324a67bbb072d3c9e06fb77427fd60f7f4868876073a064f651d72064fee
+size 305372865

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97d234ce70495267cb3b1c026808a3186705c9d2e30d58ca93729b0a078643f
+size 305853368

tokenizer_config.json

@@ -1,38 +1 @@
-{
-  "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
-    },
-    "61728": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "separate_vocabs": false,
-  "source_lang": "bnt",
-  "sp_model_kwargs": {},
-  "target_lang": "eng",
-  "tokenizer_class": "MarianTokenizer",
-  "unk_token": "<unk>"
-}
+{"target_lang": "eng", "source_lang": "bnt"}