NousResearch

/

Hermes-2-Pro-Llama-3-8B

like 406

Follow

NousResearch 828

Hi there,

I have used the yaml file https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b but during the inference the model does reply with a single word or it hallucinates like crazy ... might i ask you the yaml file used and if you are aware of any issue with llama3 and chatml prompt setup ?