microsoft / PhiCookBook
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…
☆3,127Updated this week
Alternatives and similar repositories for PhiCookBook:
Users that are interested in PhiCookBook are comparing it to the libraries listed below
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,601Updated last 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…☆4,984Updated 3 weeks ago
- Everything about the SmolLM2 and SmolVLM family of models☆2,069Updated this week
- PyTorch native post-training library☆5,041Updated this week
- ☆2,485Updated last week
- ☆1,577Updated 2 weeks ago
- Tools for merging pretrained large language models.☆5,498Updated this week
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,548Updated this week
- ☆2,895Updated 6 months ago
- TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.☆2,339Updated this week
- Knowledge Agents and Management in the Cloud☆3,827Updated this week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,358Updated this week
- Composable building blocks to build Llama Apps☆7,597Updated this week
- Modeling, training, eval, and inference code for OLMo☆5,450Updated this week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,886Updated 3 weeks ago
- mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding☆2,141Updated 3 months ago
- Task-Aware Agent-driven Prompt Optimization Framework☆3,073Updated last week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,270Updated last month
- nanoGPT style version of Llama 3.1☆1,350Updated 7 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…☆3,071Updated last week
- AllenAI's post-training codebase☆2,854Updated this week
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,342Updated last month
- Go ahead and axolotl questions☆8,960Updated this week
- Cache-Augmented Generation: A Simple, Efficient Alternative to RAG☆1,155Updated last month
- DataComp for Language Models☆1,268Updated last week
- Sky-T1: Train your own O1 preview model within $450☆3,167Updated last week
- Bringing BERT into modernity via both architecture changes and scaling☆1,297Updated last week
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,454Updated last month
- An Open Large Reasoning Model for Real-World Solutions☆1,477Updated 3 weeks ago
- A framework for serving and evaluating LLM routers - save LLM costs without compromising quality☆3,763Updated 7 months ago