A fully functional pump.fun / letsbonk.fun trading and sniping bot not relying on any 3rd party APIs

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

[NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection

[NeurIPS 2024] Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

A collection of benchmarks and datasets for evaluating LLM.

A survey on harmful fine-tuning attack for large language model

This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation" (ICLR2025 Oral).

This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)

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

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…

Code accompanying the paper Pretraining Language Models with Human Preferences

A toolkit for optimizing machine learning models for practical applications

Reference implementation for DPO (Direct Preference Optimization)

AI-powered pokemon bot on showdown

Monitoring recent cross-research on LLM & RL on arXiv for control. If there are good papers, PRs are welcome.

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

Repository for the paper "Will GPT-4 Run DOOM?"

The first autonomous computer program that can do anything to earn money without human operators.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

The Code Repo for Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning