Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
danielhanchen
71 days ago
|
parent
|
context
|
favorite
| on:
OpenAI Reinforcement Fine-Tuning Research Program
On the topic of DPO - I have a Colab notebook to finetune with Unsloth 2x faster and use 50% less memory for DPO if it helps anyone!
https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-h...
hackernewds
71 days ago
[–]
thank you !
danielhanchen
71 days ago
|
parent
[–]
:)
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
