Questions about the paper about xraygpt HOT 3 OPEN

Dear @ResonWang

Thanks for interest in our work.

Our MedVicuna and RadVicuna is fine-tuned version of vicuna on medical and radiologist conversation data provided.
We fine-tuned llm (vicuna) on medical and radiology conversation data separately prior to the training of linear layer.
We kept Llm and Image Encoder frozen while training linear layer.

from xraygpt.

Hi Dear Authors,

So whether you trained LLM or Image encoder in this training stage-1 or stage-2?

from xraygpt.

Dear @awaisahmednuces,
We train llm separately on medical and radiology conversation.
In our method, in stage-1 and stage-2 training, we train projection layer between image encoder and llm on MIMIC & OpenI data.

from xraygpt.