Stars
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference" 논문의 핵심 아이디어를 구현한 순수 Python 라이브러리입니다.
Toolkit for Prompt Compression
Copy equations from ChatGPT and Wikipedia into Word (MathML) and as LaTeX.
A comprehensive Model Context Protocol (MCP) server that provides AI models with powerful Windows system management capabilities. This MCP enables AI assistants to interact with Windows systems thr…
Collection of Slides for David Silver's Reinforcement Learning Course on Youtube
Awesome papers for role-playing with language models
This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story
The nnsight package enables interpreting and manipulating the internals of deep learned models.
Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
A library for mechanistic interpretability of GPT-style language models
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
chu-tianxiang / vllm-gptq
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API.
A high-throughput and memory-efficient inference and serving engine for LLMs
Large Language Model Text Generation Inference
Fastest 5KB JS implementation of secp256k1 signatures and ECDH
Audited pure JS library containing all Ethereum-related cryptographic primitives
Ethereum L1 Protocol Stack and EVM in TypeScript