This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs

AI to play the board game Splendor.

AI agents for the boardgame Splendor

Playing Board Game Splendor with Deep Reinforcement Learning

Python implementation of the conformal prediction framework.

Go ahead and axolotl questions

DeepSeek LLM: Let there be answers

Tools for merging pretrained large language models.

Scalable toolkit for efficient model alignment

Enterprise graph machine learning framework for billion-scale graphs for ML scientists and data scientists.

Checklist for Tesla Model Y

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

(PyTorch re-implementation) Learning to Generate Product Reviews from Attributes, EACL'17

Recipes to train reward model for RLHF.

Machine Learning Engineering Open Book

A benchmark for emotional intelligence in large language models

A curated list of resources for using LLMs to develop more competitive grant applications.

Large Language Model-enhanced Recommender System Papers

RewardBench: the first evaluation tool for reward models.

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Benchmarking LLMs with Challenging Tasks from Real Users