Thanks for your excellent work!
After carefully reading the paper, I still have questions about the trainable setting of ChartAst-S.
Which part of the model is trainable/frozen in pertaining and instruction tuning stages, respectively? Vision tower, projection layer, and LLM?
Thanks for your excellent work! After carefully reading the paper, I still have questions about the trainable setting of ChartAst-S. Which part of the model is trainable/frozen in pertaining and instruction tuning stages, respectively? Vision tower, projection layer, and LLM?
Thx again.