SH4P3S author hub
apertus 4b r2 Q5 K M Round 2 QLoRA tool use fine tune of swiss ai/Apertus v1.1 4B Instruct https://huggingface.co/swiss ai/Apertus v1.1 4B Instruct , quantized to Q5 K M for llama.cpp converted from f16, never quant→quant . Round 2 changes vs round 1 https://huggingface.co/SH4P3…
Models
3
Downloads
0
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.