latest
5.0GB
a gemma 2 finetune that can work in 6gb and 8gb of vram
2B
32 Pulls Updated 6 months ago
Updated 6 months ago
6 months ago
9395beb0b157 · 5.0GB
model
archgemma
·
parameters2.51B
·
quantizationF16
5.0GB
template
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>
188B
params
{"num_predict":-1,"stop":["<|"],"tfs_z":2,"top_k":100,"top_p":0.99}
73B
Readme
No readme