gpt4all/gpt4all-chat
Jared Van Bortel c13b33fb4d WIP
2024-08-23 11:51:08 -04:00
..
cmake Remove support for GPT-J models. (#2676) 2024-07-17 16:07:37 -04:00
flatpak-manifest Update Flatpak appdata (#2727) 2024-07-25 16:05:17 -04:00
icons chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
metadata Models: Add Qwen2-1.5B-Instruct (#2759) 2024-07-29 09:57:33 -04:00
qml chat: faster KV shift, continue generating, fix stop sequences (#2781) 2024-08-07 11:25:24 -04:00
resources additional new ui changes, part 4 (#2481) 2024-06-28 17:11:12 -04:00
translations translations: update Italian translation (#2786) 2024-08-05 10:49:52 -04:00
usearch@22cfa3bd00 chat: fix build on Windows and Nomic Embed path on macOS (#2467) 2024-06-25 17:22:51 -04:00
build_and_run.md support the llama.cpp CUDA backend (#2310) 2024-05-15 15:27:50 -04:00
CHANGELOG.md chat: add CHANGELOG.md (#2699) 2024-08-07 11:20:15 -04:00
chat.cpp replace setShouldBeLoaded with loadModelAsync/releaseModelAsync 2024-08-09 11:31:03 -04:00
chat.h WIP 2024-08-23 11:51:08 -04:00
chatapi.cpp rename ChatLLM to LlamaCppModel 2024-08-08 15:14:58 -04:00
chatapi.h rename LLModel -> ModelBackend, EmbLLModel -> EmbCapableBackend 2024-08-07 17:53:58 -04:00
chatlistmodel.cpp Remove support for GPT-J models. (#2676) 2024-07-17 16:07:37 -04:00
chatlistmodel.h rename ChatLLM to LlamaCppModel 2024-08-08 15:14:58 -04:00
chatmodel.h qml: fix hang in ChatView by processing text explicitly (#2543) 2024-07-08 17:24:02 -04:00
chatviewtextprocessor.cpp qml: fix hang in ChatView by processing text explicitly (#2543) 2024-07-08 17:24:02 -04:00
chatviewtextprocessor.h qml: fix hang in ChatView by processing text explicitly (#2543) 2024-07-08 17:24:02 -04:00
CMakeLists.txt WIP 2024-08-23 11:51:08 -04:00
contributing_translations.md Update contributing_translations.md 2024-07-12 14:27:57 -04:00
database.cpp localdocs: fail fast on bad path, more detailed 'invalid' error (#2679) 2024-07-16 16:21:25 -04:00
database.h Case insensitive compare that pairs with issue #2609 and previous commit (#2684) 2024-07-17 16:08:09 -04:00
download.cpp WIP 2024-08-23 11:51:08 -04:00
download.h chat: fix comparison of versions with suffixes (#2772) 2024-07-30 13:20:52 -04:00
embllm.cpp rename LLModel -> ModelBackend, EmbLLModel -> EmbCapableBackend 2024-08-07 17:53:58 -04:00
embllm.h backend: move more stuff into LlamaCppBackend 2024-08-07 11:33:50 -04:00
LICENSE Update the license. 2024-06-26 15:07:51 -04:00
llamacpp_model.cpp WIP 2024-08-23 11:51:08 -04:00
llamacpp_model.h replace setShouldBeLoaded with loadModelAsync/releaseModelAsync 2024-08-09 11:31:03 -04:00
llm.cpp rename LlamaCppBackend::Implementation to LlamaCppBackendManager 2024-08-07 17:53:52 -04:00
llm.h chat: fix #includes with include-what-you-use (#2401) 2024-06-04 14:47:11 -04:00
llmodel.cpp WIP 2024-08-23 11:51:08 -04:00
llmodel.h WIP 2024-08-23 11:51:08 -04:00
localdocs.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
localdocs.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
localdocsmodel.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
localdocsmodel.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
logger.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
logger.h chat: fix #includes with include-what-you-use (#2401) 2024-06-04 14:47:11 -04:00
main.cpp rename ChatLLM to LlamaCppModel 2024-08-08 15:14:58 -04:00
main.qml Add scaffolding for translations. (#2612) 2024-07-11 13:02:54 -04:00
modellist.cpp WIP 2024-08-23 11:51:08 -04:00
modellist.h WIP 2024-08-23 11:51:08 -04:00
mysettings.cpp rename LlamaCppBackend::Implementation to LlamaCppBackendManager 2024-08-07 17:53:52 -04:00
mysettings.h settings: use enums for ChatTheme/FontSize, translate choices (#2667) 2024-07-16 16:12:44 -04:00
network.cpp cleanup function braces 2024-08-08 16:10:28 -04:00
network.h feat: add openai-compatible api models (#2683) 2024-07-25 10:02:52 -04:00
qa_checklist.md Update qa_checklist.md 2024-06-25 13:50:19 -04:00
README.md Update README.md of gpt4all-chat (#2698) 2024-07-25 09:20:31 -04:00
server.cpp replace setShouldBeLoaded with loadModelAsync/releaseModelAsync 2024-08-09 11:31:03 -04:00
server.h rename ChatLLM to LlamaCppModel 2024-08-08 15:14:58 -04:00

gpt4all-chat

Cross platform Qt based GUI for GPT4All versions with GPT-J as the base model. NOTE: The model seen in the screenshot is actually a preview of a new training run for GPT4All based on GPT-J. The GPT4All project is busy at work getting ready to release this model including installers for all three major OS's. In the meantime, you can try this UI out with the original GPT-J model by following build instructions below.

image

Install

One click installers for macOS, Linux, and Windows at https://gpt4all.io

Features

  • Cross-platform (Linux, Windows, MacOSX)
  • The UI is made to look and feel like you've come to expect from a chatty gpt
  • Check for updates so you can always stay fresh with latest models
  • Easy to install with precompiled binaries available for all three major desktop platforms
  • Multi-modal - Ability to load more than one model and switch between them
  • Multi-chat - a list of current and past chats and the ability to save/delete/export and switch between
  • Supports models that are supported by llama.cpp
  • Model downloader in GUI featuring many popular open source models
  • Settings dialog to change temp, top_p, min_p, top_k, threads, etc
  • Copy your conversation to clipboard
  • RAG via LocalDocs feature
  • Check for updates to get the very latest GUI

Building and running

Getting the latest

If you've already checked out the source code and/or built the program make sure when you do a git fetch to get the latest changes and that you also do git submodule update --init --recursive to update the submodules. (If you ever run into trouble, deinitializing via git submodule deinit -f . and then initializing again via git submodule update --init --recursive fixes most issues)

Contributing

  • Pull requests welcome. See the feature wish list for ideas :)

License

The source code of this chat interface is currently under a MIT license.