[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

这个项目是一个Jupyter notebook的集合，专门用于学习和探索LangChain框架。

Code for "Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free"

小红书、微信公众号、马蜂窝爬虫

The official repository for the paper: Evaluation of Retrieval-Augmented Generation: A Survey.

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

[EMNLP 2024 Industry Track & KDD UrbComp 2024 Best Paper Award] ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

[ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

将知乎专栏文章转换为 Markdown 文件保存到本地

LUFY: A RAG Chatbot that forgets unimportant conversations

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

OLMoE: Open Mixture-of-Experts Language Models

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

A family of compressed models obtained via pruning and knowledge distillation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Advanced Multi-Turn QA System with LLM and Intent Recognition. 基于LLM大语言模型意图识别、参数抽取结合slot词槽技术实现多轮问答、NL2API. 打造Function Call多轮问答最佳实践

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Expert Specialized Fine-Tuning

High-Resolution Image Synthesis with Latent Diffusion Models

Start building LLM-empowered multi-agent applications in an easier way.

中文nlp解决方案(大模型、数据、模型、训练、推理)

Making large AI models cheaper, faster and more accessible

SEED-Story: Multimodal Long Story Generation with Large Language Model

The Memory layer for your AI apps

Implementation of BEAST adversarial attack for language models (ICML 2024)