[Model Request] Guanaco

[rndompc]

⚙️ Request New Models

• Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/TheBloke/guanaco-33B-GGML
• Is this model architecture supported by MLC-LLM? (the list of supported models) Yes

Additional context

This model have shown good performance within the Llama model. I would like to test it in different hardware. I also would appreciate If you can give me some recommendations about how to compile for a GPU Target: gfx90a.