Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
verl: Volcano Engine Reinforcement Learning for LLMs
Train transformer language models with reinforcement learning.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
The official implementation of Phased Instruction Fine-Tuning for Large Language Models，ACL 2024 Findings
Structured state space sequence models
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
A framework for few-shot evaluation of language models.
Alpaca dataset from Stanford, cleaned and curated
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
A large-scale, fine-grained, diverse preference dataset (and models).
Code and documentation to train Stanford's Alpaca models, and generate the data.
An Instruction-tuned Large Language Model for E-commerce
LAVIS - A One-stop Library for Language-Vision Intelligence
A series of large language models developed by Baichuan Intelligent Technology
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Stable Diffusion web UI
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型