microsoft / PhiCookBookLinks
This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi 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 benchmark…
☆3,617Updated 2 weeks ago
Alternatives and similar repositories for PhiCookBook
Users that are interested in PhiCookBook are comparing it to the libraries listed below
Sorting:
- Everything about the SmolLM and SmolVLM family of models☆3,445Updated 3 weeks ago
- PyTorch native post-training library☆5,615Updated this week
- Generative AI extensions for onnxruntime☆902Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,397Updated 7 months ago
- Agentic components of the Llama Stack APIs☆4,278Updated 4 months ago
- ☆3,040Updated 3 weeks ago
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,620Updated 3 months ago
- [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which ach…☆5,676Updated last month
- Sky-T1: Train your own O1 preview model within $450☆3,358Updated 5 months ago
- Composable building blocks to build LLM Apps☆8,191Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,741Updated 4 months ago
- ☆2,106Updated 3 weeks ago
- Curated list of datasets and tools for post-training.☆4,041Updated last month
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,966Updated this week
- AllenAI's post-training codebase☆3,417Updated this week
- ☆4,219Updated 4 months ago
- The Open Cookbook for Top-Tier Code Large Language Model☆1,957Updated last year
- Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.☆3,153Updated last week
- ☆692Updated 7 months ago
- LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve spee…☆3,103Updated 6 months ago
- DataComp for Language Models☆1,398Updated 3 months ago
- Tools for merging pretrained large language models.☆6,575Updated this week
- ☆1,845Updated this week
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,543Updated 10 months ago
- Open-source AI cookbook☆2,539Updated last month
- Llama-3 agents that can browse the web by following instructions and talking to you☆1,408Updated last year
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆1,801Updated last month
- Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models☆2,836Updated 11 months ago
- VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…☆3,684Updated 2 weeks ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆931Updated 3 weeks ago