Support Falcon H1 models #109
Description
Thank you for your great work - when trying to run the command:
docker model run hf.co/tiiuae/Falcon-H1-0.5B-Instruct-GGUF
I get:
Unable to find model 'hf.co/tiiuae/Falcon-H1-0.5B-Instruct-GGUF' locally. Pulling from the server.
Downloaded: 299.89 MB
Model pulled successfully
Interactive chat mode started. Type '/bye' to exit.
> Hi
Failed to generate a response: error response: status=500 body=unable to load runner: error waiting for runner to be ready: llama.cpp terminated unexpectedly: llama.cpp exit status: exit status 1
with output: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'falcon-h1'
This is because falcon-h1 has been only recently added into llama.cpp: ggml-org/llama.cpp#14534 - is there a way to update llama.cpp to its latest version in order to support recently added models?