Stars
Minimalistic large language model 3D-parallelism training
The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
A throughput-oriented high-performance serving framework for LLMs
Chat first code editor. To download the packaged app:
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
machine learning and deep learning tutorials, articles and other resources
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)
A full Python Implementation of the ROUGE Metric (not a wrapper)
The repository is about 100+ python programming exercise problem discussed, explained, and solved in different ways
The official evaluation suite and dynamic data release for MixEval.
复旦大学自然语言处理组发布的自然语言入门练习项目的代码与报告
an intro to retrieval augmented large language model
李白 👤 作为唐代杰出诗人，其诗歌作品在中国文学史上具有重要地位。近年来，随着数字技术和人工智能的快速发展，传统文化普及推广的形式也面临着创新与变革。国内外对于李白诗歌的研究虽已相当深入，但在数字化、智能化普及方面仍存在不足。因此，本项目旨在通过构建李白知识图谱，结合大模型训练出专业的AI智能体，以生成式对话应用的形式，推动李白文化的普及与推广。
Instruction Tuning with GPT-4
llama3 implementation one matrix multiplication at a time
The GPU RAM Estimator provides a simple tool for estimating GPU memory usage during training and inference.
本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/
A library for mechanistic interpretability of GPT-style language models
An advanced guide to learn English which might benefit you a lot 🎉 . 离谱的英语学习指南/英语学习教程。