18 points | by de_sty an hour ago ago
4 comments
Snap, no gguf to download, will wait for one to appear to test, any improvement over an already good model is good news.
"18 days on 144 H200 GPUs" insane.. didn't thought so much hardware would be needed to train Qwen.
FWIW that is about $331,000 on low-onboarding-grief clouds (e.g. vast.ai) right now using the SXM variants they used.
You might be able to shave that down using a different flavor of H200 (like PCIe) but it would take more hours, so benefits are unclear.
I look forward to testing this against my private eval set to determine if it's benchmaxxing or actual improvement based on just 1200 tasks. downloading it now
Is it post-training or bench-maxxing?
Snap, no gguf to download, will wait for one to appear to test, any improvement over an already good model is good news.
"18 days on 144 H200 GPUs" insane.. didn't thought so much hardware would be needed to train Qwen.
FWIW that is about $331,000 on low-onboarding-grief clouds (e.g. vast.ai) right now using the SXM variants they used.
You might be able to shave that down using a different flavor of H200 (like PCIe) but it would take more hours, so benefits are unclear.
I look forward to testing this against my private eval set to determine if it's benchmaxxing or actual improvement based on just 1200 tasks. downloading it now
Is it post-training or bench-maxxing?