2U1/Qwen-VL-Series-Finetune
Open-source fine-tuning scripts for Alibaba Cloud's Qwen-VL vision-language model series.
Not currently ranked — collecting fresh signals.
star history
This repository provides training scripts for fine-tuning Qwen2-VL, Qwen2.5-VL, Qwen3-VL, and Qwen3.5 vision-language models. It supports supervised fine-tuning (SFT), DPO, and GRPO training methods, with options for video training, reasoning mode training, and MoE model support. The implementation uses HuggingFace transformers and Liger-Kernel for efficient training.
Frequently asked
- What is 2U1/Qwen-VL-Series-Finetune?
- Open-source fine-tuning scripts for Alibaba Cloud's Qwen-VL vision-language model series.
- Is Qwen-VL-Series-Finetune open source?
- Yes — 2U1/Qwen-VL-Series-Finetune is open source, released under the Apache-2.0 license.
- What language is Qwen-VL-Series-Finetune written in?
- 2U1/Qwen-VL-Series-Finetune is primarily written in Python.
- How popular is Qwen-VL-Series-Finetune?
- 2U1/Qwen-VL-Series-Finetune has 1.9k stars on GitHub.
- Where can I find Qwen-VL-Series-Finetune?
- 2U1/Qwen-VL-Series-Finetune is on GitHub at https://github.com/2U1/Qwen-VL-Series-Finetune.