Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Tim Dettmers: QLoRA finetunes a 65B model on a single 48 GB GPU
(
twitter.com/tim_dettmers
)
3 points
by
convexstrictly
on May 12, 2023
|
hide
|
past
|
favorite
|
1 comment
convexstrictly
on May 12, 2023
[–]
Closed beta runs for a week. 4 bit floats. Quantization on top of quantization. Finetune Alpaca 7B in ~3 hours on an A40 GPU/RTX3090. Paging of optimizer states. Uses LoRA. Integrated with HuggingFace framework
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
