Kate Silverstein
Kate Silverstein
### Duplicates - [X] I have searched the existing issues ### Summary 💡 Currently the AutoGPT app assumes the underlying LLM supports OpenAI-style function calling. Even though there is a...
It would be useful to have an API endpoint like `/info` that would return a json dict containing 1) the version of llamafile and 2) model metadata/configuration. Llamafile version allows...
A lot of popular & high-quality sentence embedding models are based on the BERT architecture e.g. [sentence-transformers](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). Sentence embedding models are very important for many uses cases e.g. RAG, lightweight...
Misc embeddings fixes: * Fix #303 - `/embeddings` server endpoint returns actual embeddings rather than 0-vector * Fix #322 - Pull in upstream change from llama.cpp to improve locale handling...
## What is the issue? The embeddings produced by a model running in llamafile seem to be substantially different from those produced by llama.cpp. llama.cpp embeddings are very close (~0.99...
Getting segfault from server.cpp /embedding endpoint when using e5-mistral-7b-instruct-f16 and tinyllama-1.1b-chat-v1.0.Q5_K_M. Both of these models work when using llama.cpp. Tested with: * llamafile commit: a2d159e * llama.cpp commit: 947d3ad2 *...
### Background This draft PR is a step toward enabling the use of local models in AutoGPT by adding [llamafile](https://github.com/Mozilla-Ocho/llamafile) as an LLM provider. Implementation notes are included in `forge/forge/llm/providers/llamafile/README.md`...