shisa-ai / shisa-v1-llama3-8b-gguf

There are some stray llama2 </s tokens for some reason, but tested to work correctly with multiturn w/ the llama3 chattemplate: ./server -ngl 99 -m shisa-v1-llama3-8b.Q5KM.gguf --chat-template llama3 -fa -v