P2333
Follow
Stars
A fast + lightweight implementation of the GCG algorithm in PyTorch
[NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623
2024中国翻墙软件VPN推荐以及科学上网避坑，稳定好用。对比SSR机场、蓝灯、V2ray、老王VPN、VPS搭建梯子等科学上网与翻墙软件，中国最新科学上网翻墙梯子VPN下载推荐，访问Chatgpt。
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
[NeurIPS 2024] Code release for "Segment Anything without Supervision"
🧬 RegMix: Data Mixture as Regression for Language Model Pre-training
Long Context Transfer from Language to Vision
Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
[NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.
Arena-Hard-Auto: An automatic LLM benchmark.
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
Improved techniques for optimization-based jailbreaking on large language models
A high-throughput and memory-efficient inference and serving engine for LLMs
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
PAL: Proxy-Guided Black-Box Attack on Large Language Models
⚓️ Sailor: Open Language Models for South-East Asia
The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in th…
A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.
[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.