<div align="center"> <img src="https://huggingface.co/datasets/llama-research/assets/resolve/main/llama.png" width="300"> <h1>OpenAlpaca 7B GGML 4-Bit Quantized</h1> <p>This is a quantized version of <a href="openllmplayground/openalpaca_7b_700bt_preview" target="_blank">OpenAlpaca 7B</a>, a finetuned version of <a href="openlm-research/open_llama_7b">OpenLLaMA 7B</a>.</p> <p>OpenLLaMA and OpenAlpaca are licensed under the Apache 2.0 license, a permissive license that allows for commercial use.</p> <p>This model, in the GGML format, allows you to easily use <a href="https://github.com/ggerganov/llama.cpp">llama.cpp</a> with this model.</p> <p><small>This model has been quantized by LLaMA Research.</small></p> </div>