Re:Qwen2.5-VL-32B: Smarter and Lighter
by hmottestad on Monday March 24, 2025 @03:46PM
(#43464723)
I tried the R1 distill of llama 8B, which did refuse direct questions about the massacre.
Haven’t tried this new model locally, but I agree with you that it looks like there is a secondary censorship going on. If I ask it to list the 10 worst catastrophes of recent Chinese history with Thinking enabled then it’ll actually think about the massacre. Gets blocked very quickly, but it doesn’t look like the thinking is particularly censored.
Haven’t tried this new model locally, but I agree with you that it looks like there is a secondary censorship going on. If I ask it to list the 10 worst catastrophes of recent Chinese history with Thinking enabled then it’ll actually think about the massacre. Gets blocked very quickly, but it doesn’t look like the thinking is particularly censored.