Finetuning scripts for Qwen2.5-VL (No llama-factory)
#11
by
2U1
- opened
https://github.com/2U1/Qwen2-VL-Finetune
I made a code for who wants to use the huggingface version to finetune, and having difficult using some other frameworks like me.
Also, you can set different learning_rate for vision_model and language_model. ( Also for the merger)
Feedback and issues are welcome!
2U1
changed discussion title from
Finetuning scripts for Qwen2.5-VL
to Finetuning scripts for Qwen2.5-VL (No llama-factory)