llm-efficiency-challenge / neurips_llm_efficiency_challenge

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day
253 stars 56 forks source link

Should we migrate the starter kit from lit-llama to lit-gpt #6

Closed bkowshik closed 1 year ago

bkowshik commented 1 year ago

Ref: https://github.com/Lightning-AI/lit-llama

The open-source code in this repository works with the original LLaMA weights that are distributed by Meta under a research-only license.

New Apache 2.0 licensed weights are being released as part of the Open LLaMA project. To use the Open LLaMA weights or other LLaMA-like checkpoints such as Vicuna, check out the Lit-GPT repository.

msaroufim commented 1 year ago

We'd be very open to that, if you'd like to send a PR would be happy to review

carmocca commented 1 year ago

Hi! I work on Lit-GPT.

I would encourage that you switch mainly because:

For organizers or participants, feel free to reach out in the Lit-GPT issue page if you have questions about the code or want to share something.

Good luck hacking!

bkowshik commented 1 year ago

Made a Jupyter notebook on Kaggle to get open-llama 3B working based on the documentation and some discussions Ex: https://github.com/Lightning-AI/lit-gpt/issues/254#issuecomment-1632473883 in the repository. Now that we have a working setup of the open-llama 3B model, next steps here would be to make the relevant changes in the toy-example to reflect the same.

Link to the notebook is: https://www.kaggle.com/bkowshik/lightning-ai-lit-gpt