Re:Fine tune LLAMA3 on million scale dataset in consumer GPU...
by iAkashPaul on Thursday April 25, 2024 @01:00AM
(#40153600)
With unsloth's optimizations you can do llama-3-8b's QLoRA fine-tuning on your 8GB card(mine's a 2070S) with 900MB to spare with BS of 4.
[ Parent
| on HN ]
There are no comments on this comment yet.