Our great sponsors
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
looking at https://github.com/LargeWorldModel/LWM - they seem to indeed suggest to use a TPU vm
https://github.com/ggerganov/llama.cpp/discussions/2948
You can run ollama (and a web UI) pretty trivially via docker:
docker run -d --gpus=all -v /some/dir/for/ollama/data:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:latest
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway --name ollama-webui ghcr.io/ollama-webui/ollama-webui:main
That particular webui will let you upload models (with configuration). Other wise, you can use the api directly (you'll need to POST a `blob` first):
https://github.com/ollama/ollama/blob/main/docs/api.md#creat...
Related posts
- What can LLMs never do?
- OpenAI vs Gemini : Function Calling & Autonomous Agent
- Voxel51 Is Hiring AI Researchers and Scientists — What the New Open Science Positions Mean
- I Said Goodbye to ChatGPT and Hello to Llama 3 on Open WebUI - You Should Too
- AMA: I'm Dave Greene, an Accidental Expert on Conway's Game of Life