pygpt4all 1.1.0

Official Python CPU inference for GPT4All language models based on llama.cpp and ggml

PyGPT4All

Official Python CPU inference for GPT4All language models based on llama.cpp and ggml

• Installation
• Tutorial
  • Model instantiation
  • Simple generation
  • Interactive Dialogue
• API reference
• License

Installation

pip install pygpt4all

Tutorial

You will need first to download the model weights

Model	Download link
GPT4ALL	http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin
GPT4ALL-j	https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin

Model instantiation

Once the weights are downloaded, you can instantiate the models as follows:

• GPT4All model

from pygpt4all import GPT4All

model = GPT4All('path/to/ggml-gpt4all-l13b-snoozy.bin')

• GPT4All-J model

from pygpt4all import GPT4All_J

model = GPT4All_J('path/to/ggml-gpt4all-j-v1.3-groovy.bin')

Simple generation

The generate function is used to generate new tokens from the prompt given as input:

for token in model.generate("Tell me a joke ?\n"):
    print(token, end='', flush=True)

Interactive Dialogue

You can set up an interactive dialogue by simply keeping the model variable alive:

while True:
    try:
        prompt = input("You: ", flush=True)
        if prompt == '':
            continue
        print(f"AI:", end='')
        for token in model.generate(prompt):
            print(f"{token}", end='', flush=True)
        print()
    except KeyboardInterrupt:
        break

API reference

You can check the API reference documentation for more details.

License

This project is licensed under the MIT License.