Good starting point for working on data science projects. Contains numpy, pandas, matplotlib, tensorflow and more.
Access the OpenAI GPT-4 chat AI model using Python. Create your own LLM-driven AI server!
Access the OpenAI ChatGPT 3.5 Turbo chat AI model using Python.
Access the OpenAI GPT-4 chat AI model using Node.js.
Access the OpenAI Whisper Speech-to-Text AI model using Python.
Make a custom AI writer with a few lines of code!
This Repl uses Cohere AI's language models to generate custom text based on a given "command". It can be adapted to any text generation use-case by adjusting the prompt.
This example generates a short story about learning to code :)
For those interested in forking, you can get a free API key here: https://dashboard.cohere.ai/welcome/register?utm_source=other&utm_medium=social&utm_campaign=nicks-repl
Use this template to create your own prompt app with GPT. This template provides the tools you need to build, deploy, and invoke a production-ready prompt app.
🌟 Learn to train ML models in the Replit x Weights & Biases Hackathon from February 4th - 11th 🌟
Fork this repl and run it to get started with basic machine learning with Weights & Biases
Weights & Biases is a machine learning experiment tracking, model checkpointing and data visualisation tool used by over 200,000 ML practitioners across the world.
Running this repl will::
Run some dummy logging to show the basics of logging to Weights & Biases
Run a mini-experiment varying the amount of Dropout in your model and logging the results to Weights & Biases
To log results to your own Weights & Biases account, create an account at the link below, then enter your API key when prompted. Otherwise just select the option to log anonymously, without entering an API key.
Sign up to Weights & Biases here to get started!
An example project to deploy a computer vision model to the web using Roboflow and Replit.
This Replit creates an inference widget that you can use in your web browser with your webcam. Out-of-the-box, this Replit works with a model trained on Microsoft COCO. You can configure the code to work with your own dataset, too!
Want to experiment with building back-end logic with computer vision? Check out our Python Quickstart.
Starter code for using Hugging Face's Transformers pipelines feature to set up an ML inference pipeline for NLP tasks.
This Repl is a template for creating AI-Enabled applications, like 'ChatGPT for my data' with an embeddings store and large language models.
https://www.tensil.ai/ is a generator of Open source ML accelerators for the edge.
This repl runs quick tests on a Tensor Compute Unit (TCU) generated by Tensil deployed in Sabana
See more of our examples:
https://sabana.io
https://github.com/sabanaio/sabana-examples