An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork

[EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models

The offical realization of InstructERC

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.

LogLLM: Log-based Anomaly Detection Using Large Language Models (system log anomaly detection)

[ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.

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

[NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"

[ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing

Official repository of "Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning"

Official implementation for "Diffusion Instruction Tuning"

EMNLP'2024: Knowledge Verification to Nip Hallucination in the Bud

[AAAI 2025]Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity

Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)

[ACL 2025] Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction

Fine tune Large Language Model on Mathematic dataset

This project streamlines the fine-tuning process, enabling you to leverage Llama-2's capabilities for your own projects.