InternLM / InternLM-XComposer

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.
1.92k stars 121 forks source link

DualFocus SFT Data #253

Open LengSicong opened 2 months ago

LengSicong commented 2 months ago

Hi authors, congrats on the great work!

May I know when do you plan to release DualFocus training data curated from Visual Genome?