Easily boost the speed of pulling your models and datasets from various of inference runtimes. (e.g. π€ HuggingFace, π« Ollama, vLLM, and more!)
- Out of the mind when dealing with the slow speed from the internet when pulling models and datasets?
- Already downloaded the model or dataset in another cluster or node, maybe Homelab server, but cannot share them easily?
- You got poor connection to HuggingFace or Ollama but got friends locally with models already?
- You want to serve your models and datasets to your friends locally?
demodel here to rescue!
Out of the box support for:
- π€
huggingface-cli - π€
transformers - Ollama
- π€
transformers.js(both Browser and Node.js) - vLLM
- SGLang
