Remix clone Hacker News

This is pretty cool. I have a similar model that’s 8 days into training on msmarco.

So far I only have the “cold start” data posted, but I’m planning on posting a full distillation dataset.

What kind of hardware setup would be needed to replicate the paper’s results?

	▲	deepsquirrelnet a day ago \| parent [-]
		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.