CarlosJefte
/

llama-3-8b-bnb-4bit

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

CarlosJefte commited on May 20

Commit

630008f

•

1 Parent(s): 26b0098

Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -2067,6 +2067,6 @@
   ],
   "model_max_length": 8192,
   "pad_token": "[PAD]",
-  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

   ],
   "model_max_length": 8192,
   "pad_token": "[PAD]",
+  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }