Running uncensored DeepSeek v4.1 locally with Heretic: an abliteration walkthrough
David Ondrej · youtube · 2026-11-02
David Ondrej published a video walkthrough on running an uncensored (abliterated) DeepSeek model.
- Explains what abliteration means: removing refusal behavior by modifying model weights
- Demonstrates local setup using the open-source Heretic tool, HuggingFace models, and Ollama
- Frames the use case around ethical purposes
- Video is sponsored by PostHog; the author is also hiring for Cloudroom
More from Infra
- How LLM inference actually works: from 140GB weights to GPUs and model serving, explained as a story — _jaydeepkarale · 2026-11-04
- Running 4x RTX 3090 on a consumer board: a Qwen3.8 local inference build — Civil_Fee_7862 · 2026-11-04
- LlamaIndex speeds up doc-parsing model OCRia-1 10x to 2800 tok/s on one B200 — llama_index · 2026-11-04
- Coding agents more than double every released speculative decoding system, DFlash2 hits 10.87x — berkeley_ai · 2026-11-04
- Scaling Python Without a Dockerfile: Metaflow, DuckDB and Parquet in Practice — anacondainc · 2026-11-04
- Enterprise AI spend hits $177B, up 5.4x; Anthropic and OpenAI take 86% of API spend — deedydas · 2026-11-04