Where is the instruction/finetuning data for 3d?

OpenGVLab / LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

GNU General Public License v3.0

5.76k stars 375 forks source link

Where is the instruction/finetuning data for 3d? #56

Open mu-cai opened 1 year ago

mu-cai commented 1 year ago

I wonder where is the instruction/finetuning data such that you can use to tune LLM?

ZrrSkywalker commented 1 year ago

Hi, thanks for your interest. The 3D training of LLaMA-Adapter is still under tuning. We will soon update them in the repo. Thanks for your waiting.

gaopengpjlab commented 1 year ago

Our Imagebind-LLM V1 do not need instruction/finetuning for 3D. In the future, we will gather 3D instrution/finetuning dataset and finetune over LLaMa-Adapter Multimodal.