zhangp365/llama2-webui-cpu
Include the llama2-7b model and use ggml quantization. Ensure you run it with at least 8GB of RAM.
Latest release: about 2 years ago - 617 downloads - 380 dependencies
More details on packages.ecosyste.ms - JSON
Include the llama2-7b model and use ggml quantization. Ensure you run it with at least 8GB of RAM.
Latest release: about 2 years ago - 617 downloads - 380 dependencies
More details on packages.ecosyste.ms - JSON