This repo currently contains the version of generation_config.json from Llama 3 8B Instruct that declares both 128001 and 128009 to be eos tokens. This file can be used to "repair" both full weight models and exl2 quants thereto. Just drop a copy of the file in the same directory as the safetensors files.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support