Llava Llama 3 8b V1 1 Q3 K S GGUF

🚀 djward888/llava-llama-3-8b-v1_1-Q3_K_S-GGUF

This project provides a model converted to GGUF format, enabling efficient interaction with the model through llama.cpp.

🚀 Quick Start

This model was converted to GGUF format from xtuner/llava-llama-3-8b-v1_1 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

📦 Installation

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

💻 Usage Examples

Basic Usage

Invoke the llama.cpp CLI:

llama-cli --hf-repo djward888/llava-llama-3-8b-v1_1-Q3_K_S-GGUF --model llava-llama-3-8b-v1_1.Q3_K_S.gguf -p "The meaning to life and the universe is"

Advanced Usage

Start the llama.cpp server:

llama-server --hf-repo djward888/llava-llama-3-8b-v1_1-Q3_K_S-GGUF --model llava-llama-3-8b-v1_1.Q3_K_S.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m llava-llama-3-8b-v1_1.Q3_K_S.gguf -n 128