sglucas

Is it possible to release a code based on jax?

2

Is it possible to release a code based on jax?

[Feature] I try to use instruction tuning to fine-tune llama model and get a new alpaca model. How to use compass to evaluate the local alpaca model on MMLU and other datasets

2

### Describe the feature How to use compass to evaluate the local alpaca model on MMLU and other datasets ### Will you implement it? - [ ] I would like...

About DQN replay dataset

2

Hi Thank you so much for your contribution. This is a really great repo for students. I think it will be very nice if we can try the atari offline...

Hi I try to evaluate the accuracy of chavinlo/alpaca-native on MMLU. I find the final accuracy is about 36 and I cannot reproduce the result about 41.6. May I ask...

Hi, May I ask is it possible to release the code based on jax. Best

Hi, very great repo for students and researchers. May I ask is it possible to release the code based on Jax? Best

May I ask the global batch size when I use `gpt2.yaml`. When I run the code on v3-32, that means the global batch size is 16 (batch size) * 4...

[FEATURE]: Add more training models and RLHF algorithms

1

### Describe the feature Add more training models and RLHF algorithms for the branch `grpo-latest`.