SGLang is a fast serving framework for large language models and vision language models.

Entropy Based Sampling and Parallel CoT Decoding

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Open-source evaluation toolkit of large vision-language models (LVLMs), support 160+ VLMs, 50+ benchmarks

Code for Quiet-STaR

The LLM Evaluation Framework

The Social-IQ 2.0 Challenge Release for the Artificial Social Intelligence Workshop at ICCV '23

Representation Engineering: A Top-Down Approach to AI Transparency

A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).

Examples in the MLX framework

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

A reading list of up-to-date papers on NLP for Social Good.

FacTool: Factuality Detection in Generative AI

🐫 CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework. https://www.camel-ai.org

SOTA Math Opensource LLM

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

A repo lists papers related to LLM based agent

Must-read Papers on LLM Agents.

Generative Agents: Interactive Simulacra of Human Behavior

LOMO: LOw-Memory Optimization

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

A structurally comprehensive dataset of AMR-to-text alignments for coverage of a larger variety of linguistic phenomena, for research related to AMR parsing, generation, and evaluation.

✨Fast Coreference Resolution in spaCy with Neural Networks

A game theoretic approach to explain the output of any machine learning model.

深度学习经典、新论文逐段精读