two new "surgeries" on Qwen 3.8
https://huggingface.co/etemiz
these are past loras, applied to new model. they work because they have similar architecture and 3.8 itself is a further training of previous versions.
https://huggingface.co/etemiz
these are past loras, applied to new model. they work because they have similar architecture and 3.8 itself is a further training of previous versions.
