Instruction Following
The ability of a language model to accurately interpret and execute user instructions, often involving complex reasoning, multi-step tasks, or specific formatting requirements. Critical for practical applications of large-language-models in user-facing systems.
Best Small LLMs for Local Inference (for instruction following)
For running well-instructed large-language-models on a 48GB VRAM NVIDIA GPU, the following quantized models are strong contenders:
- Llama 3.1 70B (quantized): Llama 3.1 model (Meta) that effectively runs on 48GB VRAM for instruction-following tasks
- Gemma 2 27B (quantized): Gemma 2 model providing strong performance
Autonomous Skill Creation and Self-Improvement
Recent developments in AI Agents demonstrate advanced instruction following capabilities through autonomous skill acquisition. Notable examples include:
- Hermes Agent: An open-source self-improving AI operator developed by Nous Research. It features a “skills” module and a
/learncommand that allows the agent to autonomously create and integrate new capabilities. See learn Command Introduction and Demo for details.