Phi-3CookBook
Development guide
A resource providing hands-on examples and guides for using Microsoft's Phi-3 models in various software development contexts.
This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open sourced AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.
3k stars
17 watching
281 forks
Language: Jupyter Notebook
last commit: 2 months ago phi3phi3-testingphi3-vision
Related projects:
| Repository | Description | Stars |
|---|---|---|
 phidatahq/phidata | A framework for building multi-modal agents with memory, knowledge, tools, and reasoning | 16,438 |
| microsoft/ai-for-beginners | A 12-week curriculum teaching the basics of Artificial Intelligence through practical lessons, quizzes, and labs using popular frameworks like TensorFlow and PyTorch. | 35,160 |
 llmware-ai/llmware | A framework for building enterprise LLM-based applications using small, specialized models | 8,303 |
 guidance-ai/guidance | An efficient programming paradigm for controlling large language models | 19,259 |
| microsoft/flaml | Automates machine learning workflows and optimizes model performance using large language models and efficient algorithms | 3,968 |
 google-deepmind/alphafold | An implementation of the AlphaFold inference pipeline. | 12,997 |
| microsoft/pica | An empirical study on using GPT-3 for multimodal question answering tasks with few-shot learning. | 85 |
 othersideai/self-operating-computer | A framework that enables multimodal models to control computers. | 8,977 |
 exo-explore/exo | An experimental software framework to run AI models on diverse devices without requiring expensive GPUs. | 17,369 |
 openai/gpt-2 | A repository providing code and models for research into language modeling and multitask learning | 22,644 |
| microsoft/lmops | A research initiative focused on developing fundamental technology to improve the performance and efficiency of large language models. | 3,747 |
| microsoft/unilm | Large-scale pre-training of general-purpose models across multiple tasks and modalities | 20,400 |
| openai/baselines | High-quality implementations of reinforcement learning algorithms for research and development purposes | 15,885 |
 openvinotoolkit/openvino | A toolkit for optimizing and deploying artificial intelligence models in various applications | 7,439 |
 minimaxir/gpt-3-experiments | A collection of test prompts and generated texts for evaluating OpenAI's GPT-3 API | 701 |