llama-factory

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Crater is a cloud-native AI training & inference platform.

Fine-tuning Qwen2.5-VL for vision-language tasks | Optimized for Vision understanding | LoRA & PEFT support.

动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地（含真实实验、曲线与复现脚本）

中文医学多模态大模型 Large Chinese Language-and-Vision Assistant for BioMedicine

This repo is for Amazon ML Challenge 2024. The challenge was to develop a Machine Learning model to extract product details directly from the product images.

Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.

使用LLaMA-Factory微调多模态大语言模型的示例代码 Demo of Finetuning Multimodal LLM with LLaMA-Factory

This repo contains the winning code for Amazon ML Challenge 2024. The challenge was to develop a Machine Learning model to extract product entity details directly from the product images.

这是一个很可爱的色妹妹，送给每一个需要的人~

Practical guide to fine-tuning LLMs like Gemma, LLaMA, and Mistral on custom datasets using popular frameworks.

Qwen2-VL在文旅领域的LLaMA-Factory微调案例 The case for fine-tuning Qwen2-VL in the field of historical literature and museums

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

[ACL 2025 Main] Taming LLMs by Scaling Learning Rates with Gradient Grouping

AVR: Learning Adaptive Reasoning Paths for Efficient Visual Reasoning

This project enables the model to directly generate structured summaries with fixed fields through PEFT/QLoRA fine-tuning

【EN】NEXUS is a multi-agent simulation for modeling information flow, user attention, and strategic decision-making in dynamic social environments. It integrates attention-guided mechanisms, GraphRAG-based retrieval, and narrative-driven agent interactions to generate high-quality insights for scenarios such as social media analysis + public.

An architecture for LLMs' continual-learning and long-term memories

🎯 Fine-tuning LLMs using LlamaFactory for financial intent understanding | Evaluating open-source models on OpenFinData benchmark | Full implementation with multiple models (Qwen2.5/ChatGLM3/Baichuan2/Llama3)

Sample for Fine-Tuning LLMs & VLMs