jefferyb/
merlinite:7b-lab-Q4_K_M

17 1 year ago

4-bit quantized version of instructlab/merlinite-7b-lab https://huggingface.co/instructlab/merlinite-7b-lab-GGUF

1 year ago

802f3d48c536 · 4.4GB ·

model
llama
·
7.24B
·
Q4_K_M
params
{ "num_ctx": 32768, "stop": [ "<|im_end|>", "<|endoftext|>" ] }
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

Readme

No readme