Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ganeshkrishnan
on Feb 11, 2024
|
parent
|
context
|
favorite
| on:
RLHF a LLM in <50 lines of Python
The dataset is here I presume:
https://huggingface.co/datasets/Intel/orca_dpo_pairs
you can look at the samples. Mostly its questions and accepted/rejected answers.
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
you can look at the samples. Mostly its questions and accepted/rejected answers.