A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

Scalable RL solution for advanced reasoning of language models

Named Entity Recognition as Dependency Parsing

A brief and partial summary of RLHF algorithms.

Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.

PyTorch library for Active Fine-Tuning

A recipe for online RLHF and online iterative DPO.

FeatureAlignment = Alignment + Mechanistic Interpretability

[NeurIPS 2024] Can Language Models Learn to Skip Steps?

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

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

O1 Replication Journey

Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)

Your finetuned model's back to its original safety standards faster than you can say "SafetyLock"!

🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Official implementation of "DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning" in ICML'24

This is the official repository for paper: "Human Simulacra: Benchmarking the Personification of Large Language Models"

Personality Alignment of Language Models

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Training Sparse Autoencoders on Language Models

LLM training in simple, raw C/CUDA

[ACL'24] A Knowledge-grounded Interactive Evaluation Framework for Large Language Models

LLM training in simple, raw C/CUDA