Abliterated, finetuned and uncensored
1,530 Pulls Updated 5 months ago
Updated 5 months ago
5 months ago
9277924ccb3d · 4.9GB
model
archllama
·
parameters8.03B
·
quantizationQ4_K_M
4.9GB
params
{"num_ctx":8192,"num_keep":24,"stop":["\u003c|start_header_id|\u003e","\u003c|end_header_id|\u003e",
125B
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .P
254B
Readme
This is abliterated and further fine tuned to be uncensored. Q4_k_M version.
This is a fine-tune of the model failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 using the dataset NobodyExistsOnTheInternet/ToxicQAFinal
It is largely uncensored. No system prompt is configured so you could further jailbreak it via system prompt.
source https://huggingface.co/fearlessdots/Llama-3-Alpha-Centauri-v0.1-GGUF