This extension enhances the capabilities of textgen-webui by integrating advanced vision models, allowing users to have contextualized conversations about images with their favorite language models; and allowing direct communication with vision models.
Hi there.
it seems the extension relies on huggingface repositories like MiniCPM-Llama3-V-2_5
Could it support gguf files as i already have MiniCPM-Llama3-V-2_5 ggml-model-Q4_K_M.gguf and mmproj-model-f16.gguf downloaded from https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf/