Abliterated, finetuned and uncensored
1,611 Pulls Updated 7 months ago
Updated 7 months ago
7 months ago
9277924ccb3d · 4.9GB
model
archllama
·
parameters8.03B
·
quantizationQ4_K_M
4.9GB
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 .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