Qwen2.5-VL-3B-Instruct-GGUF

--- license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE language: - en pipeline_tag: image-text-to-text tags: - multimodal library_name: transformers --- These files have been built using a imatrix file and latest llama.cpp build. You must use a fork of llama.cpp to use vision with the model. To utilize the experimental support for Qwen 2.5 VL in `llama.cpp`, follow these steps: Note this uses a fork of llama.cpp. At this time the main branch does not support vision for this model 1. **Clone the lastest llama.cpp Fork**:

翻訳準備中のため原文を表示しています