microsoft/guidance: A guidance language for controlling large language models.

A guidance language for controlling large language models.

Guidance is an efficient programming paradigm for steering language models. With Guidance, you can control how output is structured and get high-quality output for your use case—while reducing latency and cost vs. conventional prompting or fine-tuning. It allows users to constrain generation (e.g. with regex and CFGs) as well as to interleave control (conditionals, loops, tool use) and generation seamlessly. Install Features Install Guidance is available through PyPI and supports a variety of backends (Transformers, llama.cpp, OpenAI, etc.). If you already have the backend required for…

saved by

• Eric Chang
• Bryan Chiang

related reading

• GitHub - 567-labs/instructor: structured outputs for llmsgithub.com
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• LLM Evaluation doesn't need to be complicatedphilschmid.de
• GitHub - open-compass/opencompass: OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.github.com
• GenAI Handbookgenai-handbook.github.io
• microgptkarpathy.github.io
• Patterns for Building LLM-based Systems & Productseugeneyan.com
• The Llama Hitchiking Guide to Local LLMs – hackerllamaosanseviero.github.io
• Efficient Guided Generation for Large Language Modelsarxiv.org
• GitHub - rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by stepgithub.com
• Productizing Large Language Modelsblog.replit.com
• GPT in 60 Lines of NumPy | Jay Modyjaykmody.com