Library/LLaMA-FactoryForked

hiyouga/LlamaFactory

LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

View on GitHub↗Upstream hiyouga/LlamaFactory↗

Builder

hiyouga

hiyouga • individual

Stars

69,424

Using upstream star count

Forks

8,445

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

May 28, 2023

Project creation date

README Summary

LlamaFactory is a unified platform for efficient fine-tuning of over 100 large language models and vision-language models, accepted at ACL 2024. It provides a comprehensive toolkit with various training methods including supervised fine-tuning, reward modeling, PPO, DPO, and more. The platform offers both web UI and API interfaces for easy model training and deployment.

AI Dev Skills

Unmapped

Tags

Parameter-Efficient Fine-Tuning (PEFT)LoRA Fine-tuningQLoRA QuantizationSupervised Fine-Tuning (SFT)Reinforcement Learning from Human Feedback (RLHF)Direct Preference Optimization (DPO)Proximal Policy Optimization (PPO)Model QuantizationDistributed TrainingVision-Language Model Fine-tuningMulti-GPU TrainingGradient CheckpointingMixed Precision TrainingModel Merging TechniquesCustom Dataset IntegrationModel Evaluation and BenchmarkingCross-lingual Model AdaptationVision-Language Task Fine-tuningInstruction Following Model TrainingTextMulti-GPU ClustersCloud GPUHuman Preference LearningParameter-Efficient TrainingEfficient Model CustomizationSelf-hostedMulti-turn Conversation TrainingOpen Source LLMsMultimodalMultimodal AICode Generation Model Fine-tuningModel Alignment and Safety TrainingCustom Chatbot DevelopmentOn-premiseModel AlignmentDemocratized AI TrainingImageMathematical Reasoning EnhancementDomain-Specific Language Model AdaptationFew-shot Learning EnhancementPython

Taxonomy

AI Trends

Parameter-Efficient Training Model Alignment Multimodal AI Open Source LLMs Democratized AI Training Efficient Model Customization Human Preference Learning

Deployment Context

Self-hosted Cloud GPU Multi-GPU Clusters On-premise

Modalities

Text Image Multimodal

Skill Areas

Use Cases

Custom Chatbot Development Domain-Specific Language Model Adaptation Instruction Following Model Training Multi-turn Conversation Training Vision-Language Task Fine-tuning Model Alignment and Safety Training Few-shot Learning Enhancement Cross-lingual Model Adaptation Code Generation Model Fine-tuning Mathematical Reasoning Enhancement

Recent Activity

Updated 5 months ago

7 Days

30 Days

90 Days

Quality

production

Quality: high
Maturity: production

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created: May 28, 2023
Forked: Nov 8, 2025
Your last push: 5 months ago
Upstream last push: 8 days ago
Tracked since: Nov 6, 2025

Similar Repos

pgvector cosine similarity · $0

Loading…