Upload tokenizer

special_tokens_map.json

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

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -33,15 +34,12 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "max_length": 2048,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }