ChatGLM is a large-scale pre-trained language model for open-domain chatbot, which is open-sourced by Tsinghua University.
This repository contains the code (Dockerfile, build.envd
) for deploying ChatGLM on Modelz.
This is a template for creating a Gradio app on Modelz.
Building an Gradio app could be straightforward. You will need to provide three key components:
- A
main.py
file: This file contains the code for making predictions. - A
requirements.txt
file: This file lists all the dependencies required for the server code to run. - A
Dockerfile
or a simplerbuild.envd
: This file contains instructions for building a Docker image that encapsulates the server code and its dependencies.
In the Dockerfile
, you need to define the instructions for building a Docker image that encapsulates the server code and its dependencies.
In most cases, you could use the template in the repository.
docker build -t docker.io/USER/IMAGE .
docker push docker.io/USER/IMAGE
On the other hand, a build.envd
is a simplified alternative to a Dockerfile. It provides python-based interfaces that contains configuration settings for building a image.
It is easier to use than a Dockerfile as it involves specifying only the dependencies of your machine learning model, not the instructions for CUDA, conda, and other system-level dependencies.
envd build --output type=image,name=docker.io/USER/IMAGE,push=true
Please refer to the Modelz documentation for more details.