Text generation web UI
10 likes
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (GGUF), Llama models.
Cost / License
- Free
- Open Source
Application types
Platforms
- Linux
- Windows
- Mac
Features
Properties
- Privacy focused
Features
- No registration required
- Dark Mode
- No Tracking
- Extensible by Plugins/Extensions
- Ad-free
- AI Chatbot
- AI Writing
Text generation web UI News & Activities
Highlights All activities
Recent activities
POX added Text generation web UI as alternative to Reins
POX added Text generation web UI as alternative to Okara
POX added Text generation web UI as alternative to nanochat
head790 added Text generation web UI as alternative to SPORTS-5
head790 added Text generation web UI as alternative to CRYPTO5
Freeaigeneration added Text generation web UI as alternative to Free AI Generation
POX added Text generation web UI as alternative to Alice AI Assistant
rajmundfrater added Text generation web UI as alternative to AI Chat Assistant
Jqri added Text generation web UI as alternative to Apertus
POX added Text generation web UI as alternative to Yoink AI
Text generation web UI information
Developed by
oobaboogaLicensing
Open Source (AGPL-3.0) and Free product.Written in
Alternatives
67 alternatives listedSupported Languages
- English
AlternativeTo Category
AI Tools & ServicesGitHub repository
- 45,685 Stars
- 5,865 Forks
- 2643 Open Issues
- Updated
What is Text generation web UI?
A Gradio web UI for Large Language Models. Its goal is to become the AUTOMATIC1111/stable-diffusion-webui of text generation.
Features
- 3 interface modes: default (two columns), notebook, and chat
- Multiple model backends: transformers, llama.cpp, ExLlama, ExLlamaV2, AutoGPTQ, GPTQ-for-LLaMa, CTransformers
- Dropdown menu for quickly switching between different models
- LoRA: load and unload LoRAs on the fly, train a new LoRA using QLoRA
- Precise instruction templates for chat mode, including Llama-2-chat, Alpaca, Vicuna, WizardLM, StableLM, and many others
- 4-bit, 8-bit, and CPU inference through the transformers library
- Use llama.cpp models with transformers samplers (llamacpp_HF loader)
- Multimodal pipelines, including LLaVA and MiniGPT-4
- Extensions framework
- Custom chat characters
- Very efficient text streaming
- Markdown output with LaTeX rendering, to use for instance with GALACTICA
- API, including endpoints for websocket streaming (see the examples)
Comments and Reviews
Probably the best privacy, offline gui there is currently. Allows you to not only chat and embed, but also do lora training.
A little bit more difficult to set up than GPT4ALL, but anyone could do it by following the directions.