210 1 year ago

GGUF quantization of Llama 13B model that is instruction fine-tuned on medical Q/A.

1 year ago

485865f9155e · 52GB ·

llama
·
13B
·
F32
{{ if .System }}Instruction: {{ .System }}{{ end }} Input: {{ .Prompt }} Response:

Readme

Unofficial GGUF quantization of “PMC-LLaMA: Towards Building Open-source Language Models for Medicine”. Instruction fine-tuned medical language Llama 13B variant.