Community releases layer-selective abliterated DeepSeek-V4.1 finetune on Hugging Face
AIFlow_ML · x · 2026-10-26
A developer released DeepSeek-V4.1-1017-Ablitrated-Efficient, an abliterated finetune of DeepSeek-V4.1-Flash-1017 using layer-selective abliteration plus targeted fixes for thinking loops and re-verification. The MIT-licensed FP8 MoE model is on Hugging Face and supports vLLM, with 50 downloads so far.
More from Models
- LlamaIndex releases OCRia-1, topping ParseBench at 87.4 with 2-4x faster decoding — llama_index · 2026-10-26
- "90% of tokens local, 10% frontier": HF engineer's model allocation take — TheZachMueller · 2026-10-26
- Iranian users report Qwen chat access blocked; blogger says sanctions aren't Alibaba's call — dotey · 2026-10-26
- Hugging Face releases Carbon-X, an open 14.8B DNA language model that reads genomes in chat — _lewtun · 2026-10-26
- Users annoyed as ChatGPT keeps lecturing them with "Kevin, ..." openers — kevinkern · 2026-10-26
- Best sub-40B model on Terminal-Bench 4.0: Nanbeige4.3-33B at 23.8% accuracy — NielsRogge · 2026-10-26