sjo/deepseek-r1-8b-llama-distill-abliterated-q8_0

sjo/

deepseek-r1-8b-llama-distill-abliterated-q8_0:latest

2,420 Downloads Updated 10 months ago

The mradermacher model of DeepSeek-r1 llama distilled with abliteration applied

Updated 10 months ago

10 months ago

96aac7391c27 · 8.5GB ·

archllama

·

parameters8.03B

·

quantizationQ8_0

8.5GB

MIT License Copyright (c) 2023 DeepSeek Permission is hereby granted, free of charge, to any person

1.1kB

{ "stop": [ "<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>",

148B

{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice

387B

Readme

Model adapted from the Modelfile in original non-abliterated llama distill version of r1 and this model downloaded from huggingface - https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Abliterated-GGUF

hope others find it useful