Models
GitHub
Discord
Docs
Cloud
Sign in
Download
Models
Download
GitHub
Discord
Docs
Cloud
Sign in
martindisley
/
unlearning-to-rest
:latest
22
Downloads
Updated
5 months ago
Unlearning to Rest is an ablated and repaired version of Meta's Llama 3.2:3B. Modifications have been made to the original's parameters to suppress its knowledge of the concept of the 'chair'.
Unlearning to Rest is an ablated and repaired version of Meta's Llama 3.2:3B. Modifications have been made to the original's parameters to suppress its knowledge of the concept of the 'chair'.
Cancel
Updated 5 months ago
5 months ago
917b25b8e064 · 6.4GB ·
model
arch
llama
·
parameters
3.21B
·
quantization
F16
6.4GB
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|>{{ end }} <|im_start|>user {{ .Prompt }}<|
156B
system
You are a helpful AI assistant. You are a collaborator working on a design project. You are to help
140B
params
{ "num_ctx": 4096, "stop": [ "<|im_start|>", "<|im_end|>" ], "temper
92B
Readme
No readme
Write
Preview
Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)