LlamaFactory

Visit Tool

LlamaFactory is an open-source AI Agents & Automation tool that provides unified and efficient fine-tuning for over 100 LLMs and VLMs. It offers zero-code CLI and Web UI for easy model customization.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is LlamaFactory?

LlamaFactory is an open-source platform designed for the unified and efficient fine-tuning of over 100 large language models (LLMs) and vision-language models (VLMs). It simplifies the complex process of model customization through both a zero-code command-line interface (CLI) and a user-friendly Web UI. The tool integrates various advanced methods including continuous pre-training, supervised fine-tuning, reward modeling, PPO, DPO, and KTO. It supports scalable resources with 16-bit full-tuning, freeze-tuning, and various LoRA/QLoRA techniques. LlamaFactory also incorporates practical tricks like FlashAttention-2 and Unsloth for enhanced performance and offers faster inference via OpenAI-style API, Gradio UI, and CLI with vLLM or SGLang workers.

Best used for

Ideal for developers and data scientists who need to efficiently fine-tune large language models and vision-language models, customize them for specific applications, and deploy them with optimized inference. Especially valuable for those seeking an open-source solution with broad model support and advanced training techniques.

Common actions

fine-tune LLMs

customize AI models

optimize language models

deploy fine-tuned models

github copilotface swappingcollaborationlow-code/no-code"AI Agents"open-sourceworkflowsautomated workflowdeepfake

Capabilities

Key features

Unified LLM/VLM fine-tuning
Zero-code CLI/Web UI
100+ models supported
Multiple training approaches
Scalable resource optimization
Faster inference options

Target Audience

developerdata scientist

Integrations

wandbmlflowtensorboard

Pricing & Plans

Open Source

Free

FAQs

What types of models can be fine-tuned with LlamaFactory?

LlamaFactory supports the fine-tuning of over 100 large language models (LLMs) and vision-language models (VLMs), including popular architectures like LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Gemma, and GLM. It offers day-N support for cutting-edge models as they are released.

Does LlamaFactory offer a user-friendly interface for fine-tuning?

Yes, LlamaFactory provides both a zero-code command-line interface (CLI) and a Web UI (LLaMA Board GUI) for fine-tuning models. This allows users to easily customize and optimize models without extensive coding knowledge, making the process accessible.

What advanced training algorithms and tricks does LlamaFactory incorporate?

LlamaFactory integrates advanced algorithms such as GaLore, BAdam, APOLLO, DPO, KTO, and ORPO. It also includes practical tricks like FlashAttention-2, Unsloth, Liger Kernel, and NEFTune to enhance training speed, reduce memory usage, and improve overall efficiency.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce