AdvertiseWatchSubscribe
Updated , rescanned every two hoursSaturday, November 7, 2026

331 likesNew · 8d old

Uncensored 9B Math Model Slashes Refusals, Keeps Reasoning Power

LLMs

xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic: preview

What is DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic?

This 9-billion-parameter model, distilled from DeepSeek-V4-Pro, is tuned for math and STEM problem solving. Using the Heretic tool it removes most safety filters, dropping refusal rate from 100 % to 3 % while staying close to the original’s output quality.

Who it is for

Researchers and developers who need a compact, high-performing math assistant without heavy content blocks can fine-tune or deploy it directly.

Get the signal first.

Join the list for the morning email: the day's biggest AI launches, explained in five minutes. Unsubscribe any time.

Prefer a reader? Follow the RSS feed.