Yatit Thakker

I'm having a similar issue. The following log: ``` api-1 | 9:50PM DBG Extracting backend assets files to /tmp/localai/backend_data api-1 | 9:50PM DBG processing api keys runtime update api-1 |...

I'm also interested in this, specifically around the way images can be "retrieved" from existing documentation rather than generated from scratch using something like DALL-E. Embedding images is currently possible...

I started seeing this after upgrading from 0.15.3 to 1.1.x, will likely have to downgrade back to 0.15.5 because of this issue. Makes the app unusable because all embeddings are...

This is also happening with Gemma 2-2b-it when trying to deploy it on Inference Endpoints

> Hi @ytjhai 👋 > > Thanks for bringing this up. Could you specify a bit more what configuration you're using on the Inference Endpoints? E.g. which version, what is...

@ErikKaum Ok thanks for the clarification! I didn't realize that Gemma 2 required Flash Attention 2 for inference. I was running a GGUF quantization locally that seemed fine, so I...

I can't get the phi-3-mini 128k model to publish at all through [inference endpoints](https://ui.endpoints.huggingface.co). Is there a particular tagged version compatible with it? edit: Adding the environment variable `TRUST_REMOTE_CODE` and...

The Jina v3 embedder and v2 reranker have very good performance together. Embedder v3 is now at the level of Cohere's embedder