Qwen2.5-VL-32B: Smarter and Lighter

Re:Qwen2.5-VL-32B: Smarter and Lighter by OsrsNeedsf2P on Monday March 24, 2025 @04:45PM (#43465234)

> We haven't hit the wall yet.

The models are iterative improvements, but I haven't seen night and day differences since GPT3 and 3.5

[ Parent | on HN ]

Re:Qwen2.5-VL-32B: Smarter and Lighter by anon373839 on Monday March 24, 2025 @05:14PM (#43465478)

Yeah. Scaling up pretraining and huge models appears to be done. But I think we're still advancing the frontier in the other direction -- i.e., how much capability and knowledge can we cram into smaller and smaller models?

[ Parent | on HN ]

Re:Qwen2.5-VL-32B: Smarter and Lighter by Davidzheng on Monday March 24, 2025 @09:37PM (#43467288)

Tbh such a big jump from current capability would be ASI already

[ Parent | on HN ]

Re:Qwen2.5-VL-32B: Smarter and Lighter by YetAnotherNick on Tuesday March 25, 2025 @01:05AM (#43468261)

Because 3.5 has a new capability which is following instructions. Right now we are in 3.5 range in conversation AI and native image generation, both of which feels magical.

[ Parent | on HN ]