gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
Go to file
2023-04-09 07:38:41 -04:00
ggml@c9f702ac57 Initial commit. 2023-04-08 23:28:39 -04:00
icons Initial commit. 2023-04-08 23:28:39 -04:00
.gitignore Initial commit. 2023-04-08 23:28:39 -04:00
.gitmodules Initial commit. 2023-04-08 23:28:39 -04:00
CMakeLists.txt Initial commit. 2023-04-08 23:28:39 -04:00
gptj.cpp Don't display the endoftext token. 2023-04-09 01:22:12 -04:00
gptj.h Initial commit. 2023-04-08 23:28:39 -04:00
LICENSE Initial commit. 2023-04-08 23:28:39 -04:00
llm.cpp Initial commit. 2023-04-08 23:28:39 -04:00
llm.h Initial commit. 2023-04-08 23:28:39 -04:00
main.cpp Initial commit. 2023-04-08 23:28:39 -04:00
main.qml Fix padding. 2023-04-09 07:38:41 -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 :)