this post was submitted on 28 Apr 2025
39 points (97.6% liked)
LocalLLaMA
2929 readers
37 users here now
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I'm actually more medium on this!
Only 32K context without yarn, and with yarn Qwen 2.5 was kinda hit/miss.
No 32B base model. Is that a middle finger to the Deepseek distils?
It really feels like "more of qwen 2.5/1.5" architecture wise. I was hoping for better attention mechanisms, QAT, a bitnet test, logit distillation... something new other than some training data optimizations and more scale.
There actually is a 32b dense
Yeah, but only an Instruct version. They didn't leave any 32B base model like they did for for the 30B MoE.
That could be intentional, to stop anyone from building on their 32B dense model.
Huh. I didn't realize that thanks. Lame that they would hold back the one that is the biggest size most consumers would ever run.
It could be an oversight, no one has answered yet. Not many people asking either, heh.