byte-perfect re-sync from Helsinki-NLP/opus-mt-ber-es (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-ber-es",
+  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-ber-es",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",
@@ -9,6 +9,11 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      13295
+    ]
+  ],
   "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": 13295,
   "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": 13296
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 13295,
   "renormalize_logits": true,
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.32.0.dev0"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0726d3aa1cd765f9c9b3ce6c7e99893671df2b688cc72f1ea02bc307e60c449
+size 205988349

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f448ce03709d42e22616d3f2011925b63c1e2e01057a5abaa184ea20f10e124d
+size 206275120

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
-    },
-    "13295": {
-      "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": "ber",
-  "sp_model_kwargs": {},
-  "target_lang": "es",
-  "tokenizer_class": "MarianTokenizer",
-  "unk_token": "<unk>"
-}
+{"target_lang": "es", "source_lang": "ber"}