Upload tokenizer

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>"
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -2055,6 +2055,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
+  "max_length": 4096,
   "model_input_names": [
     "input_ids",
     "attention_mask"
@@ -2062,5 +2063,8 @@
   "model_max_length": 4096,
   "pad_token": "<|eot_id|>",
   "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizer"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }