Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Try Llama-3 in a Colab Notebook
(
colab.research.google.com
)
5 points
by
danielhanchen
on April 18, 2024
|
hide
|
past
|
favorite
|
1 comment
danielhanchen
on April 18, 2024
[–]
Made a Colab notebook to finetune Llama-3 2x faster and use 70% less VRAM on free T4 GPUs, but you can also directly inference with it etc!
15 trillion tokens is yikes!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
15 trillion tokens is yikes!