Upload tokenizer

special_tokens_map.json

@@ -13,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -2,14 +2,6 @@
   "add_bos_token": true,
   "add_eos_token": false,
   "bos_token": {
-    "__type": "AddedToken",
-    "content": "",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "clean_up_tokenization_spaces": {
     "__type": "AddedToken",
     "content": "<s>",
     "lstrip": false,
@@ -17,6 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": false,
   "eos_token": {
     "__type": "AddedToken",
     "content": "</s>",
@@ -25,10 +18,10 @@
     "rstrip": false,
     "single_word": false
   },
-  "legacy": null,
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": true,
+  "model_max_length": 2048,
   "pad_token": null,
-  "padding_side": "right",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": {
@@ -38,6 +31,5 @@
     "normalized": true,
     "rstrip": false,
     "single_word": false
-  },
-  "use_fast": false
+  }
 }