large-language-models

SEAIT is a user-friendly application that simplifies the installation process of AI-related projects

📰 Must-read papers on KV Cache Compression (constantly updating 🤗).

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

GRID: Generative Recommendation with Semantic IDs

Aligning Large Language Models with Human: A Survey

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

A Minecraft MCP Server powered by Mineflayer API. It allows to control a Minecraft character in real-time, allowing AI assistants to build structures, explore the world, and interact with the game environment through natural language instruction

Salesforce open-source LLMs with 8k sequence length.

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

🐋MindChat（漫谈）：漫谈人生路, 笑对风霜途

Serverless LLM Serving for Everyone.

Open-source AI-powered data science platform.

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Large-Scale Visual Representation Model

Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

Repo for "Adaptation of Agentic AI"

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)

Official repository for "Craw4LLM: Efficient Web Crawling for LLM Pretraining"

Querying local documents, powered by LLM

Cell type annotation for single-cell RNA-seq using multi-LLM consensus

Build your own X - Master machine learning by building everything from scratch. It aims to cover everything from linear regression to deep learning to large language models (LLMs).

Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

中文Mixtral-8x7B（Chinese-Mixtral-8x7B）