Upload tokenizer

special_tokens_map.json

@@ -7,14 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -27,4 +20,4 @@
     "rstrip": false,
     "single_word": false
   }
-}
+}

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": false,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -22,9 +20,9 @@
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "32000": {
       "content": "<|endoftext|>",
@@ -116,14 +114,9 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "legacy": false,
-  "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}