lucidrains / self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

lucidrains/self-rewarding-lm-pytorch Issues

UnboundLocalError: local variable 'self_reward_model' referenced before assignment
Updated 3 months ago3
ModuleNotFoundError: No module named 'x_transformers'
Updated 3 months ago1
What changes should I make to apply the method on Llama2?
Updated 4 months ago
I encountered the following error when trying to run usage
Updated 4 months ago1
How to use HF Transformers model
Updated 4 months ago3
TypeError: tuple indices must be integers or slices, not tuple
Updated 4 months ago1
RuntimeError: Placeholder storage has not been allocated on MPS device!
Closed 5 months ago2
Multiple GPUs
Closed 5 months ago
Why use a custom sample function instead of original HuggingFace generate() function?
Closed 5 months ago1
The reward prompt is weak.
Closed 5 months ago6
Default `iteration` about SPIN. (Reward model~Policy model)
Closed 5 months ago1
run spin demo
Closed 5 months ago3
Is this work in progress?
Closed 5 months ago4
Help with Setting up and running ?
Closed 5 months ago1
code and dataset？
Closed 5 months ago