Revert

tokenizer_config.json

@@ -1,32 +1,15 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32000": {
+    "50257": {
       "content": "<|vulgarg|>",
       "lstrip": false,
       "normalized": true,
@@ -34,7 +17,7 @@
       "single_word": false,
       "special": false
     },
-    "32001": {
+    "50258": {
       "content": "[INST]",
       "lstrip": false,
       "normalized": true,
@@ -42,7 +25,7 @@
       "single_word": false,
       "special": false
     },
-    "32002": {
+    "50259": {
       "content": "[/INST]",
       "lstrip": false,
       "normalized": true,
@@ -52,23 +35,12 @@
     }
   },
   "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
+    "<|endoftext|>"
   ],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "max_length": 512,
-  "model_max_length": 1000000000000000019884624838656,
-  "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": true
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }