jefferyb/
granite:7b-lab-Q4_K_M

58 1 year ago

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

1 year ago

b9efffa662cf · 4.1GB ·

model
llama
·
6.74B
·
Q4_K_M
params
{ "num_ctx": 2048, "stop": [ "<|im_end|>", "<|endoftext|>", "</|im_e
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

Readme

No readme