openai / weak-to-strong

openai/weak-to-strong Issues

Why are only binary classification tasks tested for NLP?
Updated 25 days ago
Training stopping criteria: fixed epochs ?
Updated a month ago
How to use GPT-4 as strong model
Updated 2 months ago
Some questions about the anthropic_hh dataset results
Updated 3 months ago
Machine learning newbie hopes to get help
Closed 4 months ago5
I created a code for "autonomous AI". But since I'm an amateur, I don't know how to implement it.
Closed 4 months ago
TypeError: 'type' object is not subscriptable
Closed 4 months ago1
Unexpected keyword argument 'bf16'
Closed 4 months ago14
UnboundLocalError: local variable 'minibatch_size' referenced before assignment
Closed 4 months ago
Exploring Weak to Strong Generalization from a pre-training standpoint
Updated 5 months ago4
hi guys!
Updated 5 months ago6
Will you guys be releasing code for step 2 of the methodology "Train a strong student model with weak supervision."
Closed 5 months ago2
Preprocessed Chess Puzzle Data
Updated 5 months ago4
what's the meaning of fraction of GPT4?
Closed 5 months ago2
Observing eval accuracy considerably lower than reported?
Updated 5 months ago12
The schedule.step() should be called outside the dataloader loop.
Updated 5 months ago3
Protect main branch and make changes through pull requests
Closed 5 months ago1
Some thoughts
Closed 5 months ago1