microsoft / Phi-3CookBook
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.
☆2,501Updated this week
Related projects ⓘ
Alternatives and complementary repositories for Phi-3CookBook
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,393Updated this week
- One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure☆1,882Updated 3 weeks ago
- PyTorch native finetuning library☆4,346Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,159Updated 2 weeks ago
- ☆1,968Updated this week
- Agentic components of the Llama Stack APIs☆3,900Updated this week
- Composable building blocks to build Llama Apps☆4,615Updated this week
- A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!☆3,267Updated 3 months ago
- Tools for merging pretrained large language models.☆4,830Updated this week
- Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.☆2,835Updated this week
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆1,841Updated 3 months ago
- Deploy your agentic worfklows to production☆1,839Updated this week
- ☆2,754Updated 2 months ago
- Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM☆1,332Updated this week
- tiny vision language model☆5,798Updated this week
- Parse files for optimal RAG☆3,199Updated last week
- The easiest way to use Agentic RAG in any enterprise☆3,872Updated this week
- LLM-powered multiagent persona simulation for imagination enhancement and business insights.☆3,906Updated last week
- nanoGPT style version of Llama 3.1☆1,248Updated 3 months ago
- ☆1,222Updated 2 weeks ago
- g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains☆3,911Updated last month
- 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…☆2,581Updated last week
- A native PyTorch Library for large model training☆2,635Updated this week
- Set of tools to assess and improve LLM security.☆2,729Updated this week
- Go ahead and axolotl questions☆7,950Updated this week
- A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.☆6,917Updated last week
- RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry☆3,334Updated this week
- [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…☆4,666Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆6,171Updated this week
- VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and…☆2,004Updated 3 weeks ago