Python bindings for llama.cpp

For those who don't know, llama.cpp is a port of Facebook's LLaMA model in pure C/C++:

• Without dependencies
• Apple silicon first-class citizen - optimized via ARM NEON
• AVX2 support for x86 architectures
• Mixed F16 / F32 precision
• 4-bit quantization support
• Runs on the CPU

• Installation
• Usage
• Supported model
  • GPT4All
• Discussions and contributions
• License

1. The easy way is to use the prebuilt wheels

pip install pyllamacpp

However, the compilation process of llama.cpp is taking into account the architecture of the target CPU, so you might need to build it from source:

git clone --recursive https://github.com/abdeladim-s/pyllamacpp && cd pyllamacpp
pip install .

A simple Pythonic API is built on top of llama.cpp C/C++ functions. You can call it from Python as follows:

from pyllamacpp.model import Model

def new_text_callback(text: str):
    print(text, end="")

model = Model(ggml_model='./models/gpt4all-model.bin', n_ctx=512, n_threads=8)
model.generate("Once upon a time, ", n_predict=55, new_text_callback=new_text_callback)

If you don't want to use the callback, you can get the results from the generate method once the inference is finished:

generated_text = model.generate("Once upon a time, ", n_predict=55)
print(generated_text)

• You can pass any llama context parameter as a keyword argument to the Model class
• You can pass any gpt parameter as a keyword argument to the generarte method
• You can always refer to the short documentation for more details.

1. First Get the gpt4all model.
2. Convert it to the new ggml format

On your terminal run:

pyllamacpp-convert-gpt4all path/to/gpt4all_model.bin path/to/llama_tokenizer path/to/gpt4all-converted.bin

If you find any bug, please open an issue.

If you have any feedback, or you want to share how you are using this project, feel free to use the Discussions and open a new topic.

This project is licensed under the same license as llama.cpp (MIT License).