What's Changed

• Completely revamp model loading to support explicit unload/reload (https://github.com/nomic-ai/gpt4all/pull/1969)
  • We no longer load a model by default on application start
  • We no longer load a model by default on chat context switch
• Save and restore of window geometry across application starts (https://github.com/nomic-ai/gpt4all/pull/1989)
• Update to latest llama.cpp as of 2/21/2024 and add CPU/GPU support for Gemma (https://github.com/nomic-ai/gpt4all/pull/1992)
  • Also enable Vulkan GPU support for Phi and Phi-2, Qwen2, and StableLM

Fixes

• Fix visual artifact in update reminder dialog (16927d9)
• Blacklist Intel GPUs as they are still not supported (a1471be, https://github.com/nomic-ai/llama.cpp/pull/14)
• Improve chat save/load speed (excluding startup/shutdown with defaults) (6fdec80, https://github.com/nomic-ai/llama.cpp/pull/15)
• Significantly improve handling of chat-style prompt templates, and reupload Mistral OpenOrca (https://github.com/nomic-ai/gpt4all/pull/1970, https://github.com/nomic-ai/gpt4all/pull/1993)

New Contributors

• @simonw made their first contribution in https://github.com/nomic-ai/gpt4all/pull/1964

Full Changelog: https://github.com/nomic-ai/gpt4all/compare/v2.7.0...v2.7.1