Console • Docs • Templates • Discord
This repo contains helpful AI/ML notebook templates. Each notebook has been coupled with the minimum GPU specs required to use them + setup scripts making a Brev template. Click the deploy badge on any notebook to deploy it.
| Notebook | Description | Min. GPU | Deploy |
|---|---|---|---|
| Fine-tune Llama 2 | Fine-tune Llama 2 on your own dataset | 1x A10G |   |
| Fine-tune Mistral | A Guide to Cheaply Fine-tuning Mistral | 1x A10G | |
| Fine-tune Mistral - Own Data | Fine-tune Mistral on your own dataset | 1x A10G |  |
| Julia Install | Easily Install Julia + Notebooks | any || CPU | |
| Deploy to Replicate | Deploy Model to Replicate | any || CPU | |
| PDF Chatbot (OCR) | PDF Chatbot using OCR | 1x A10G | |
| Zephyr Chatbot | Chatbot with Open Source Models | 1x A10G | |
Brev is a dev tool that makes it really easy to code on a GPU in the cloud. Brev does 3 things: provision, configure, and connect.
Brev provisions a GPU for you. You don't have to worry about setting up a cloud account. We have solid GPU supply, but if you do have AWS or GCP, you can link them.
Brev configures your GPU with the right drivers and libraries. Use our open source tool Verb to point and click the right python and CUDA versions.
Brev.dev CLI automatically edits your ssh config so you can ssh gpu-name or run brev open gpu-name to open VS Code to the remote machine