Models
GitHub
Discord
Docs
Cloud
Sign in
Download
Models
Download
GitHub
Discord
Docs
Cloud
Sign in
sjo
/
llama3.1-8b-instruct-abliterated
:latest
22
Downloads
Updated
11 months ago
Cancel
Updated 11 months ago
11 months ago
c41d89ec5a88 · 8.5GB ·
model
arch
llama
·
parameters
8.03B
·
quantization
Q8_0
8.5GB
params
{ "num_ctx": 8192, "num_keep": 24, "stop": [ "<|start_header_id|>", "<|e
125B
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr
260B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)