serverless-template-gptj
所属分类:GPT/ChatGPT
开发工具:Python
文件大小:6KB
下载次数:0
上传日期:2022-10-07 11:04:03
上 传 者:
sh-1993
说明: 无服务器模板gptj,,
(serverless-template-gptj,,)
文件列表:
Dockerfile (528, 2022-10-07)
LICENSE (1063, 2022-10-07)
app.py (1359, 2022-10-07)
client.py (270, 2022-10-07)
download.py (702, 2022-10-07)
requirements.txt (38, 2022-10-07)
server.py (1271, 2022-10-07)
test.py (272, 2022-10-07)
# Banana Serverless
This repo gives a basic framework for serving ML models in production using simple HTTP servers.
## Quickstart:
The repo is already set up to run a basic [HuggingFace GPTJ](https://huggingface.co/EleutherAI/gpt-j-6B) model.
1. Run `pip3 install -r requirements.txt` to download dependencies.
2. Run `python3 server.py` to start the server.
3. Run `python3 test.py` in a different terminal session to test against it.
## Make it your own:
1. Edit `app.py` to load and run your model.
2. Make sure to test with `test.py`!
if deploying using Docker:
3. Edit `download.py` (or the `Dockerfile` itself) with scripts download your custom model weights at build time.
## Move to prod:
At this point, you have a functioning http server for your ML model. You can use it as is, or package it up with our provided `Dockerfile` and deploy it to your favorite container hosting provider!
If Banana is your favorite GPU hosting provider (and we sure hope it is), read on!
#
# Deploy to Banana Serverless:
- Log in to the [Banana App](https://app.banana.dev)
- Select your customized repo for deploy!
It'll then be built from the dockerfile, optimized, then deployed on our Serverless GPU cluster and callable with any of our SDKs:
- [Python](https://github.com/bananaml/banana-python-sdk)
- [Node JS / Typescript](https://github.com/bananaml/banana-node-sdk)
- [Go](https://github.com/bananaml/banana-go)
You can monitor buildtime and runtime logs by clicking the logs button in the model view on the Banana Dashboard](https://app.banana.dev)
## Use Banana for scale.
近期下载者:
相关文件:
收藏者: