Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
| Date | Stars |
|---|---|
| 2026-07-30 | 1947 |
| 2026-08-07 | 1950 |
| 2026-08-15 | 1958 |
| 2026-08-18 | 1959 |
| 2026-08-19 | 1959 |
| 2026-08-20 | 1958 |
| 2026-08-22 | 1959 |
| 2026-08-26 | 1960 |
| 2026-08-28 | 1959 |
| 2026-08-29 | 1960 |
| 2026-08-30 | 1960 |
| 2026-08-31 | 1962 |
| 2026-09-01 | 1961 |
| 2026-09-02 | 1961 |
| 2026-09-03 | 1961 |
| 2026-09-04 | 1962 |
| 2026-09-07 | 1964 |
| 2026-09-08 | 1965 |
| 2026-09-10 | 1967 |
| 2026-09-11 | 1967 |
| 2026-09-12 | 1967 |
| 2026-09-15 | 1969 |
| 2026-09-16 | 1968 |
| 2026-09-17 | 1969 |
| 2026-09-19 | 1968 |
| 2026-09-21 | 1969 |
| 2026-09-23 | 1970 |
| 2026-09-26 | 1971 |
| 2026-09-29 | 1972 |
| 2026-09-30 | 1975 |
| 2026-10-01 | 1977 |
| 2026-10-03 | 1978 |
| 2026-10-05 | 1977 |
| 2026-10-08 | 1978 |
| 2026-10-09 | 1977 |
| 2026-10-10 | 1978 |
| 2026-10-12 | 1979 |
| 2026-10-14 | 1980 |
| 2026-10-16 | 1981 |
| 2026-10-19 | 1980 |
| 2026-10-23 | 1981 |
| 2026-10-24 | 1979 |
| 2026-10-25 | 1979 |
| 2026-10-27 | 1980 |
| 2026-10-31 | 1981 |
| 2026-11-04 | 1981 |
Today
— stars today
This week
+1 stars this week
This month
+4 stars this month
Momentum
0.0
growth rate 0.05%/day
# Fine-tuning Qwen-VL Series
This repository contains a script for training [Qwen2-VL](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), [Qwen2.5-VL](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
, [Qwen3-VL](https://huggingface.co/Qwen/Qwen3-VL-4B-Thinking) and [Qwen3.5](https://huggingface.co/Qwen/Qwen3.5-4B) with only using HuggingFace and [Liger-Kernel](https://github.com/linkedin/Liger-Kernel).
## Other projects
**[[Phi3-Vision Finetuning]](https://github.com/2U1/Phi3-Vision-Finetune)**<br>
**[[Llama3.2-Vision Finetuning]](https://github.com/2U1/Llama3.2-Vision-Ft)**<br>
**[[Molmo Finetune]](https://github.com/2U1/Molmo-Finetune)**<br>
**[[Pixtral Finetune]](https://github.com/2U1/Pixtral-Finetune)**<br>
**[[SmolVLM Finetune]](https://github.com/2U1/SmolVLM-Finetune)**<br>
**[[Gemma3 Finetune]](https://github.com/2U1/Gemma3-Finetune)**
## Update
- [2026/05/18] 🔥**Upgrade to `liger_kernel==0.8.0`.**
- [2026/03/07] 🔥**Supports reasoning mode training for Qwen3-VL and Qwen3.5**
- [2026/03/07] 🔥**Supports Qwen3.5 Series.**
- [2026/03/07] Supports Qwen3-VL classification
- [2026/03/07] Update codebase to `transformers==5.3.0`
- [2025/11/28] 🔥**Supports video training with DPO and GRPO.**
- [2025/11/27] 🔥**Supports Qwen3-VL-MoE**
- [2025/11/26] Update support for liger-kernel in Qwen3-VL.
- [2025/10/16] 🔥**Supports Qwen3-VL(non-moe)**
- [2025/08/21] Add option for using 2-layer mlp for classification.
- [2025/08/21] Add option for unfreeze only few layers for llm and vision tower.
- [2025/08/08] 🔥Monkey patch Qwen2.5-VL's window attention and forward for using less memory and speedups.
- [2025/07/25] Updated Classification training script.
- [2025/05/29] 🔥Supports GRPO training.
- [2025/04/16] 🔥Supports DPO training.
- [2025/03/04] Add Option for using liger kernel.
- [2025/02/18] 🔥Supports mixed-modality dataset with zero3.
- [2025/02/05] Fixed code for properly use image.
- [2025/02/03] Support Liger-kernel for Qwen2.5-VL.
- [2025/02/03] 🔥Supports Qwen2.5-VL.
- [2025/01/24] Add option for using DoRA.
- [2025/01/24] Fix error in LoRA training.
- [2025/01/18] 🔥Supports mixed-modality data.
- [2024/09/12] 🔥Now the model is trained using [Liger-Kernel](https://github.com/linkedin/Liger-Kernel).
- [2024/09/11] Supports setting different learning rates to projector and vision model.
- [2024/09/11] 🔥Supports multi-image and video training.
## Table of Contents
- [Fine-tuning Qwen-VL Series](#fine-tuning-qwen-vl-series)
- [Other projects](#other-projects)
- [Update](#update)
- [Table of Contents](#table-of-contents)
- [Supported Features](#supported-features)
- [Docker](#docker)
- [Installation](#installation)
- [Environments](#environments)
- [Using `requirements.txt`](#using-requirementstxt)
- [Using `environment.yaml`](#using-environmentyaml)
- [Training Notes](#training-notes)
- [Dataset Preparation](#dataset-preparation)
- [Reasoning Format](#reasoning-format)
- [Supervised Fine Tuning](#supervised-fine-tuning)
- [Full Finetuning](#full-finetuning)
- [Finetune with LoRA](#finetune-with-lora)
- [Train with video dataset](#train-with-video-dataset)
- [Image Resolution for vram usage](#image-resolution-for-vram-usage)
- [Merge LoRA Weights](#merge-lora-weights)
- [Evaluation during Training](#evaluation-during-training)
- [Step 1: Prepare Evaluation Dataset](#step-1-prepare-evaluation-dataset)
- [Step 2: Define compute\_metrics Function](#step-2-define-compute_metrics-function)
- [Step 3: Modify Training Script](#step-3-modify-training-script)
- [Step 4: Add Evaluation Arguments](#step-4-add-evaluation-arguments)
- [DPO Finetuning](#dpo-finetuning)
- [GRPO Finetuning](#grpo-finetuning)
- [Prerequisites](#prerequisites)
- [Classification Finetuning](#classification-finetuning)
- [Experimental Features](#experimental-features)
- [Inference](#inference)
- [Gradio Infernce (WebUI)](#gradio-infernce-webExcerpt of 36,058 characters
Read on GitHub
192
2
2
1
1
1
1
1
1
1
1
Qingyun · ByteDance Seed · China
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5dec3c0bc7f85252, topic:multimodal, topic:vision-language-model, topic:vlm
matched fp:5dec3c0bc7f85252, desc:fine-tuning, readme:fine-tuning, desc:fine tuning