Update model with diverse fine-tuning (104k samples: OPUS-100 + idioms + books)

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb1b5a4c33b5dfa8585de2098b0fb2fb078b249485ecb760dc31790c50e53cb
+oid sha256:5b2457262a30ddcfd17eeaaf9ee10cf00a823b9d10fb55b242071656d838da8b
 size 627739696

special_tokens_map.json

@@ -2,4 +2,4 @@
   "eos_token": "</s>",
   "pad_token": "<pad>",
   "unk_token": "<unk>"
-}
+}

tokenizer_config.json

@@ -1,8 +1,39 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "</s>",
+      "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": "en",
+  "sp_model_kwargs": {},
   "target_lang": "pl",
+  "tokenizer_class": "MarianTokenizer",
   "unk_token": "<unk>"
-}
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0ec6c1dc987435f2dbc846aea5f2da0a3586578273a648722a49448d052685
+oid sha256:6e4c09ce145f741eaf13161b704f86e85fadb2107b4939e20973a33273ac36d7
 size 5969