Upload tokenizer

special_tokens_map.json

@@ -13,5 +13,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "[PAD]"
+  "pad_token": "<|eot_id|>"
 }

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": 8,
-    "pad_id": 128256,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 128000,
@@ -2318,15 +2306,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 128256,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_eos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2048,14 +2047,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "128256": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",
@@ -2067,6 +2058,6 @@
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }