kyegomez / BitNet

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch
https://discord.gg/qUtxnK2NMf
MIT License
1.55k stars 143 forks source link

Consider techniques from official training paper #48

Closed EwoutH closed 3 months ago

EwoutH commented 6 months ago

Microsoft released a new paper, which contains details and tips on training a ternary LLM. Might be useful!

Upvote & Fund

Fund with Polar

kyegomez commented 6 months ago

@EwoutH Yes, i have integrated the new codes!

github-actions[bot] commented 4 months ago

Stale issue message