Matt Hoffner

@jonthomp @lukejacksonn I went ahead and forked this with React 17 rc published to npm here: https://unpkg.com/es-react-rc

I don't think the MPT models work with Llama.cpp at this point? https://github.com/ggerganov/llama.cpp/issues/1333 I know there is [ggml-js](https://github.com/cztomsik/ggml-js). Maybe there are others. I'm using Python and [ctransformers](https://github.com/marella/ctransformers) to try out...

I'm not as familiar with gpt4all, but noticed they are adding langchain support, maybe there is some overlap: https://github.com/hwchase17/langchainjs/pull/1204

Hey, thanks for pointing this out. I can reproduce it, and I'm aware that styles don't work via imports. I'll see if I can get this fix into future versions....

https://github.com/yoheinakajima/babyagi/pull/299

Updated #299 to `>=` so it picks up latest by default

Starcoder works for me with ctransformers but not llama.cpp. I have some examples here: https://huggingface.co/spaces/matthoffner/starchat-ggml Llama.cpp has great M1 support with Metal now. Edit: Falcon is now working with ctransformers

Hello, I've built a simple demo linked in this project that uses transformers.js embeddings for a simple vector store search: https://huggingface.co/spaces/matthoffner/web-llm-embed/blob/main/src/components/ChatWindow.jsx#L40-L66 The full space is linked in the examples: https://github.com/mlc-ai/web-llm/tree/main/examples...

@ggaabe True, I believe it was built before the library was available. It uses react-llm which uses the web-llm model.

Awesome @craigmassie it could probably go into langchain eventually too.