Experimental GPT-OSS support!

I have obtained some success with the GGUF models under

https://huggingface.co/ggml-org/gpt-oss-20b-GGUF/tree/main
https://huggingface.co/ggml-org/gpt-oss-120b-GGUF/tree/main

It may be necessary to re-download those models in the next days if bugs are found, so make sure to recheck those pages.

Changes

• Add a new Reasoning effort UI element in the chat tab, with low, medium, and high options for GPT-OSS
• Support standalone .jinja chat templates -- makes it possible to load GPT-OSS through Transformers
• Make web search functional with thinking models

Bug fixes

• Fix an edge case in chat history loading that caused a crash (closes #7155)
• Handle both int and str types in grammar char processing (fixes a rare crash when using grammar)

Backend updates

• Update llama.cpp to https://github.com/ggml-org/llama.cpp/tree/fd1234cb468935ea087d6929b2487926c3afff4b
• Update Transformers to 4.55 (adds GPT-OSS support)

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.