What kind of hardware setup would be needed to replicate the paper’s results?
I am training phi-4 (14B) using a single A6000. There’s some tricks you have to use to keep VRAM consumption down - mainly LoRA and quantization.
There’s a package called “unsloth” that integrates with huggingface’s TRL library that can help.
alt Hacker News
I am training phi-4 (14B) using a single A6000. There’s some tricks you have to use to keep VRAM consumption down - mainly LoRA and quantization.
There’s a package called “unsloth” that integrates with huggingface’s TRL library that can help.