add tokenizer

.gitattributes

@@ -30,3 +30,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* 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

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9129bf81ef9d5fcc1797ea3061e789dc5f9e5602786b0490238d207d4219e0f5
+size 790473

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0a52318dac3247455ec889eb3bd8da9bdf234974be8b9b0f99ad5378f474c9
+size 706659

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "mod_translate",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "mul",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}