I’ve read it’s in 2 hours and 17 minutes.

Confirmed: https://x.com/justinlin610/status/1855874692260991039?s=46

The model is already on HF (source: https://x.com/cognitivecompai/status/1855486479088464203)

Maybe in couple of hours or days?

I've read we're 2 weeks ago yes, it converge.

A 32B version of Qwen2.5-Coder is coming soon as you can check out in the README of their repository.

In HuggingFace: "Qwen2.5-Coder-32B has become the current state-of-the-art open-source coderLLM, with its coding abilities matching those of GPT-4o." - https://huggingface.co/Qwen/Qwen2.5-Coder-7B

Interesting paper and work but the model doesn't seems to be better than Qwen2.5-Coder in some languages including Ruby.

I’ve tried a bunch of different models that are essentially different instruction tuning on base models, and that seems to be generally true in my experience. I don’t think you can fine tune your way into a significantly better code model. At best, one that can follow instructions better, but not one that can usually write noticeably better code or solve harder problems.

I'm waiting for the 32B! https://news.ycombinator.com/item?id=42096027