-
Harbin Institute of Technology
- Milky Way
Stars
assistant tools for attention visualization in deep learning
Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Tracking the most popular Github repos, update daily(Python version)
Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]
TrustAgent: Towards Safe and Trustworthy LLM-based Agents
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Virtual whiteboard for sketching hand-drawn like diagrams
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)
Code and data for COLING2024 paper "Characteristic AI Agents via Large Language Models".
An index of algorithms for reinforcement learning from human feedback (rlhf))
The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language Detection
Repository for the paper "RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?"
CRiskEval is a Chinese dataset meticulously designed for gauging the risk proclivities inherent in LLMs.
The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
DSIR large-scale data selection framework for language model training
Data Structures and Information Retrieval in Python
基于U3D实现的桌宠,全部代码,项目目录结构可在本人b站视频中对照查看。因为模型不能公布,代码有需要的部分自取,有疑问可交流。以前做的,编程习惯和命名做得不好请见谅,不用来提醒我