Qwen2 VL 7B Captioner Relaxed Q4 K M GGUF

🚀 alecccdd/Qwen2-VL-7B-Captioner-Relaxed-Q4_K_M-GGUF

This model is a conversion of the original model into the GGUF format. It's transformed from Ertugrul/Qwen2-VL-7B-Captioner-Relaxed using llama.cpp via the ggml.ai's GGUF-my-repo space. For more in - depth information about the model, please refer to the original model card.

📦 Installation

Install llama.cpp via brew (Works on Mac and Linux)

brew install llama.cpp

💻 Usage Examples

Use with llama.cpp

CLI

llama-cli --hf-repo alecccdd/Qwen2-VL-7B-Captioner-Relaxed-Q4_K_M-GGUF --hf-file qwen2-vl-7b-captioner-relaxed-q4_k_m.gguf -p "The meaning to life and the universe is"

Server

llama-server --hf-repo alecccdd/Qwen2-VL-7B-Captioner-Relaxed-Q4_K_M-GGUF --hf-file qwen2-vl-7b-captioner-relaxed-q4_k_m.gguf -c 2048

Direct Usage through Llama.cpp Repo

Step 1: Clone llama.cpp from GitHub

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it

Move into the llama.cpp directory and build it with the LLAMA_CURL = 1 flag, along with other hardware - specific flags (e.g., LLAMA_CUDA = 1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference

./llama-cli --hf-repo alecccdd/Qwen2-VL-7B-Captioner-Relaxed-Q4_K_M-GGUF --hf-file qwen2-vl-7b-captioner-relaxed-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo alecccdd/Qwen2-VL-7B-Captioner-Relaxed-Q4_K_M-GGUF --hf-file qwen2-vl-7b-captioner-relaxed-q4_k_m.gguf -c 2048

📄 License

This project is licensed under the Apache 2.0 license.