mirror of
https://github.com/hwchase17/langchain
synced 2024-11-11 19:11:02 +00:00
0a9f04bad9
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
1.3 KiB
1.3 KiB
GPT4All
This page covers how to use the GPT4All wrapper within LangChain.
It is broken into two parts: installation and setup, and then usage with an example.
Installation and Setup
- Install the Python package with
pip install pyllamacpp - Download a GPT4All model and place it in your desired directory
Usage
GPT4All
To use the GPT4All wrapper, you need to provide the path to the pre-trained model file and the model's configuration.
from langchain.llms import GPT4All
# Instantiate the model
model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8)
# Generate text
response = model("Once upon a time, ")
You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
Example:
model = GPT4All(model="./models/gpt4all-model.bin", n_predict=55, temp=0)
response = model("Once upon a time, ")
Model File
You can find links to model file downloads at the GPT4all repository. They will need to be converted to ggml format to work, as specified in the pyllamacpp repository.
For a more detailed walkthrough of this, see this notebook