Repository Index

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

• abliteration
• llm
• transformer
• censorship-resistance

Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.

• cuda
• deepseek
• deepseek-v4
• gguf

llama.cpp fork that abliterates at inference

• abliteration
• ai
• inference
• llama-cpp

ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.

• abliteration
• hermes
• inference
• llama-cpp