---
license: mit
---

This is [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl), converted to the GGUF format.

The full-precision GGUF model is provided along with q8_0 and q4_K_S quantizations.

Conversion and quantization is performed with llama.cpp commit [ed9d285](https://github.com/ggerganov/llama.cpp/tree/ed9d2854c9de4ae1f448334294e61167b04bec2a).