Text Generation Web UI Files

Changes

• Chat tab improvements:
• Move the 'Enable thinking' checkbox from the Parameters tab to the right sidebar
• Keep the last chat message visible as the input area grows
• Optimize chat scrolling again (I think that will be the last time—it's really responsive now)
• Replace 'Generate' with 'Send' in the main button
• Support installing user extensions in user_data/extensions/ for convenience
• Small UI optimizations and style improvements
• Block model and session backend events in --multi-user mode (#7098). Thanks @Alidr79
• One-click installer: Use miniforge instead of miniconda to avoid Anaconda licensing issues for organizations with 200+ people

Bug fixes

• Fix the DuckDuckGo search
• Fix scrolling during streaming when thinking blocks are present
• Fix chat history getting lost if the UI is inactive for a long time
• Fix chat sidebars toggle buttons disappearing (#7106). Thanks @philipp-classen
• Fix autoscroll after initial fonts loading
• Handle either missing <think> start or </think> end tags (#7102). Thanks @zombiegreedo
• Fix custom stopping strings being reset when switching models

Backend updates

• Bump llama.cpp to https://github.com/ggml-org/llama.cpp/commit/6491d6e4f1caf0ad2221865b4249ae6938a6308c

Portable builds

Below you can find portable builds: self-contained packages that work with GGUF models (llama.cpp) and require no installation! Just download the right version for your system, unzip, and run.

Which version to download:

• Windows/Linux:
• NVIDIA GPU: Use cuda12.4 for newer GPUs or cuda11.7 for older GPUs and systems with older drivers.
• AMD/Intel GPU: Use vulkan builds.

• CPU only: Use cpu builds.

• Mac:

• Apple Silicon: Use macos-arm64.
• Intel CPU: Use macos-x86_64.

Updating a portable install:

1. Download and unzip the latest version.
2. Replace the user_data folder with the one in your existing install. All your settings and models will be moved.