-
Hong Kong University of Science and Technology
- http://home.cse.ust.hk/~zjiangaj
Highlights
- Pro
Stars
The related works and background techniques about Openai o1
This repository contains a collection of the best system prompts for ChatGPT, a conversational AI model developed by OpenAI. Star this repository to help us reach 5,000 stars!
utilities for decoding deep representations (like sentence embeddings) back to text
microsoft / Megatron-DeepSpeed
Forked from NVIDIA/Megatron-LMOngoing research training transformer language models at scale, including: BERT & GPT-2
Self-Teaching Notes on Gradient Leakage Attacks against GPT-2 models.
Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".
[EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674
Repo for ICML23 "Why do Nearest Neighbor Language Models Work?"
A library for efficient similarity search and clustering of dense vectors.
Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Reference implementation for DPO (Direct Preference Optimization)
This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Efficient word ordering with pretrained language models
Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)
LAMP: Extracting Text from Gradients with Language Model Priors (NeurIPS '22)
Breaching privacy in federated learning scenarios for vision and text
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
Simulation framework for accelerating research in Private Federated Learning
[TMLR 2024] Efficient Large Language Models: A Survey