search

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

Fine-tune Support for InternLM-XComposer2-4KHD-7B #269

Open babla9 opened 2 months ago

babla9 commented 2 months ago

Hi, thanks for the great work here! I have 2 questions:

  1. When will you provide fine-tune scripts for InternLM-XComposer2-4KHD-7B?
  2. What is the GPU requirement for fine-tuning InternLM-XComposer2-VL-7B? I have access to 8x V100 clusters, and ~100k training samples, how much time would this take?

Thanks!

yuhangzang commented 2 months ago

Thanks for your attention to our work. Please check the latest code, which contains the 4khd fine-tuning code.

thonglv21 commented 2 months ago

What is the GPU requirement for fine-tuning InternLM-XComposer2-4KHD-7B lora?