<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Heretic 2.0 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/heretic-2.0/</link><description>Recent content in Heretic 2.0 on Negi AI Lab</description><image><title>Negi AI Lab</title><url>https://ai.negi-lab.com/images/og-default.png</url><link>https://ai.negi-lab.com/images/og-default.png</link></image><generator>Hugo -- 0.154.5</generator><language>ja</language><lastBuildDate>Wed, 04 Nov 2026 05:36:40 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/heretic-2.0/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLM開発に必須？Heretic 2.0で検閲解除モデルを作るためのGPU比較と選び方</title><link>https://ai.negi-lab.com/posts/heretic-2-released-localllm-gpu-guide/</link><pubDate>Wed, 04 Nov 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/heretic-2-released-localllm-gpu-guide/</guid><description>Heretic 2.0の登場で、Llama 3やGemma 2の「回答拒否」を外すモデル改変が個人でも実用レベルになった。快適な改変・推論には最低VRAM...</description></item></channel></rss>