Highlights
- Pro
Stars
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
Official Repository for Dataset Inference for LLMs
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery π§βπ¬
Tools for merging pretrained large language models.
Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Official Implementation of Paper *Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient*
Train and Infer Powerful Sentence Embeddings with AnglE | π₯ SOTA on STS and MTEB Leaderboard
code for piccolo embedding model from SenseTime
A Closer Look into Mixture-of-Experts in Large Language Models
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
π Text-Prompted Generative Audio Model
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
A Honkai Star Rail optimizer, relic scorer, damage calculator, and various other tools for building and gearing characters
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
This is a collection of our research on efficient AI, covering hardware-aware NAS and model compression.
A fast inference library for running LLMs locally on modern consumer-class GPUs
An easy-to-use package for implementing SmoothQuant for LLMs
[ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Models
A curated list of Large Language Model (LLM) Interpretability resources.
A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights iβ¦
Restore safety in fine-tuned language models through task arithmetic
Weak-to-Strong Jailbreaking on Large Language Models
SGLang is a fast serving framework for large language models and vision language models.
Achieving Efficient Alignment through Learned Correction
[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs