How to Reproduce BLOOMz-7b and GPT-j-6 results?

AGI-Edgerunners / LLM-Adapters

Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

https://arxiv.org/abs/2304.01933

Apache License 2.0

1.05k stars 99 forks source link

How to Reproduce BLOOMz-7b and GPT-j-6 results? #50

Closed Ocean-627 closed 8 months ago

Ocean-627 commented 10 months ago

Dear Authors, Excellent work! I just wonder how I can reproduce BLOOMz-7b and GPT-j-6 results. It seems that the training command mentioned in the previous issue only applies to llama. Thank you very much.

HZQ950419 commented 9 months ago

Hi,

We have updated the math_running_commands file. You can find the command to reproduce BLOOMz-7b and GPT-j-6B results.