https://huggingface.co/Skywork/Skywork-OR1-32B
I liked their Preview of the model - I was impressed by how well it could code and reason. This is fully trained version, and consequently, I am very curious how it will perform! Please, if that's alright, quantize it into GGUFs. Since the thing is based on ol' Deepseek Qwen 32B distill (not a new architecture) in theory it should quantize okay.
The Skywork folk also have smaller version (based on ol' 7B distill) at https://huggingface.co/Skywork/Skywork-OR1-7B
While for me, it is not interesting, maybe, it is reasonable to quantize as well, since other people can be curious.
Thank you!
They are both queued! :D
Thanks for the recommendation!
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Skywork-OR1-32B-GGUF and https://hf.tst.eu/model#Skywork-OR1-7B-GGUF for quants to appear.