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.
[CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102
| Date | Stars |
|---|---|
| 2026-07-31 | 656 |
| 2026-08-06 | 656 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Empowering LLMs to Understand and Generate Complex Vector Graphics
<div align="center" style="line-height: 1.2;">
[](https://www.python.org/)
[](https://github.com/hiyouga/LLaMA-Factory)
[](https://github.com/unslothai/unsloth)
[](https://huggingface.co/docs/transformers/index)
[](https://huggingface.co/docs/trl/index)
[](https://github.com/vllm-project/vllm)
[](https://arxiv.org/abs/2412.11102)
[](https://arxiv.org/abs/2412.11102)
[](https://ximinng.github.io/LLM4SVGProject/)
[](https://huggingface.co/datasets/xingxm/SVGX-Core-250k)
[](https://huggingface.co/datasets/xingxm/SVGX-SFT-1M)
</div>
---
Official implementation for **"Empowering LLMs to Understand and Generate Complex Vector Graphics"**. This project
enables Large Language Models to process, understand, and generate complex Scalable Vector Graphics (SVG).
## Table of Contents
- [🎉 News](#-news)
- [✨ Highlights](#-highlights)
- [📊 SVGX-SFT Dataset](#-svgx-sft-dataset)
- [📦 Installation & Data Preparation](#-installation--data-preparation)
- [🚀 Training Examples](#-training-examples)
- [Based on `LLaMA-Factory`](#based-on-llama-factory)
- [Based on `unsloth`](#based-on-unsloth)
- [Based on `transformers`](#based-on-transformers)
- [Based on `trl`](#based-on-trl)
- [🔧 Inference using vLLM](#-inference-using-vllm)
- [🔑 Tips for Best Results](#-tips-for-best-results)
- [💘 Acknowledgements](#-acknowledgements)
- [📎 Citation](#-citation)
- [📄 License](#-license)
- [📬 Contact](#-contact)
## 🎉 News
- **[04/2025]** 🎉 Official release of LLM4SVG code,
datasets ([SVGX-Core-250k](https://huggingface.co/datasets/xingxm/SVGX-Core-250k), [SVGX-SFT-1M](https://huggingface.co/datasets/xingxm/SVGX-SFT-1M)),
and [Pretrained Model Weights]()! 🎉 *(Link for weights pending)*
## ✨ Highlights
- 🧠 **Multi-model Support**: Fine-tune a wide range of popular foundation models, including Llama 3.2, Qwen2.5-VL, Gemma
3, DeepSeek, Falcon, Phi-2, GPT2-XL, and more.
- 📦 **Specialized SVGX Dataset**: Includes curated pretraining data (`SVGX-Core-250k`) and extensive supervised
fine-tuning data (`SVGX-SFT-1M`).
- ⚡ **Accelerated Training & Inference**: Leverages efficient training frameworks like `LLaMA-Factory`, `unsloth`,
`transformers`, and `trl`. Integrated with `vLLM` for high-throughput, low-latency inference.
- 🔍 **Multimodal Capabilities**: Fully supports text and vision inputs for comprehensive SVG understanding and
generation tasks.
- ⚙️ **Flexible Training Options**: Supports various training techniques including LoRA and full fine-tuning, along with
distributed training setups (Multi-GPU, Multi-Node).
## 📊 SVGX-SFT Dataset
Our SVGX-SFT Dataset is a comprehensive collection dExcerpt of 9,591 characters
Read on GitHub
11
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8aa47868531f0241, topic:llm