gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
Go to file
Adam Treat 0ea31487e3 Programmatically get the model name from the LLM. The LLM now searches
for applicable models in the directory of the executable given a pattern
match and then loads the first one it finds.

Also, add a busy indicator for model loading.
2023-04-11 08:29:55 -04:00
cmake Big updates to the UI. 2023-04-10 23:34:34 -04:00
ggml@c9f702ac57 Initial commit. 2023-04-08 23:28:39 -04:00
icons Big updates to the UI. 2023-04-10 23:34:34 -04:00
.gitignore Working on installer for windows. 2023-04-10 15:03:09 -04:00
.gitmodules Initial commit. 2023-04-08 23:28:39 -04:00
CMakeLists.txt Big updates to the UI. 2023-04-10 23:34:34 -04:00
gptj.cpp Fixes for linux and macosx. 2023-04-10 16:33:14 -04:00
gptj.h Compile fix for MacOSX. 2023-04-10 15:04:40 -04:00
LICENSE GPLv3 license was intended. 2023-04-10 09:16:48 -04:00
llm.cpp Programmatically get the model name from the LLM. The LLM now searches 2023-04-11 08:29:55 -04:00
llm.h Programmatically get the model name from the LLM. The LLM now searches 2023-04-11 08:29:55 -04:00
main.cpp Initial commit. 2023-04-08 23:28:39 -04:00
main.qml Programmatically get the model name from the LLM. The LLM now searches 2023-04-11 08:29:55 -04:00
README.md Update README.md 2023-04-09 01:37:12 -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 training a new version with GPT-J as the base, but it isn't read just yet. In the meantime, you can try this UI out with the original GPT-J model. Full instructions for how are included below.

image

Features

  • Cross-platform (Linux, Windows, MacOSX, iOS, Android, Embedded Linux, QNX)
  • Fast CPU based inference using ggml for GPT-J based models
  • The UI is made to look and feel like you've come to expect from a chatty gpt
  • Easy to install... The plan is to create precompiled binaries for major platforms with easy installer including model
  • WORK IN PROGRESS!!

Building and running

git clone --recurse-submodules https://github.com/manyoso/gpt4all-chat.git
cd gpt4all-chat
mkdir build
cd build
cmake ..
cmake --build . --parallel
python3 ../ggml/examples/gpt-j/convert-h5-to-ggml.py /path/to/your/local/copy/of/EleutherAI/gpt-j-6B 0
./bin/gpt-j-quantize /path/to/your/local/copy/of/EleutherAI/gpt-j-6B/ggml-model-f32.bin ./ggml-model-q4_0.bin 2
./chat

Contributing

  • Pull requests welcome :)