Xwin-LM 13B V0.1 - GGUF

• Original model: Xwin-LM 13B V0.1
• Original GitHub Xwin-LM

Only doing 4bit quants due to Colab hard-disk limits, wait for TheBloke to do the whole set properly

Uses Vicuna prompt formatting: https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1