Upload tokenizer

special_tokens_map.json

@@ -1,7 +1,19 @@
 {
   "additional_special_tokens": [
-    "<|user|>",
-    "<|assistant|>"
+    {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
   "bos_token": {
     "content": "<|im_start|>",

tokenizer.json

@@ -2,12 +2,14 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 8192,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
-    "strategy": "BatchLongest",
+    "strategy": {
+      "Fixed": 256
+    },
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 2,

tokenizer_config.json

@@ -163,16 +163,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "max_length": 256,
   "model_max_length": 8192,
-  "pad_to_multiple_of": null,
   "pad_token": "<|im_end|>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152
 }