Here is the link to the blogpost, that actually describe what this is: https://github.com/google-research/timesfm?tab=readme-ov-fil...

▲

nels 10 hours ago | parent | next [-]

I think you meant to link this page: https://research.google/blog/a-decoder-only-foundation-model...

▲

OliverGuy 8 hours ago | parent | prev | next [-]

Wish they gave some numbers for total GPU hours to train this model, seems comparatively tiny when compared to LLMs so interested to know how close this is to something trainable by your average hobbyist/university/small lab

	▲	OliverGuy 8 hours ago \| parent [-]
		Edit, it looks like the paper does TPUv5e with 16 tensor cores for 2 days for the 200M param model. Claude reckons this is 60 hours on a 8xA100 rig, so very accessibile compared to LLMs for smaller labs

▲

refulgentis 10 hours ago | parent | prev [-]

That takes me to the same content as the submission, a GitHub repo (Chrome on iOS)

▲

rockwotj 10 hours ago | parent | next [-]

Probably the better link: https://research.google/blog/a-decoder-only-foundation-model...

	▲	akshayshah 10 hours ago \| parent [-]
		And https://arxiv.org/pdf/2310.10688 if you want the full paper.

▲

Cyuonut 10 hours ago | parent | prev [-]

I suppose they tried to link this: https://research.google/blog/a-decoder-only-foundation-model...