-
University College London
- London, UK
- https://www.fanghuaye.xyz/
Stars
Official implementation of the paper "Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism".
PKU-DAIR / open-box
Forked from thomas-young-2013/open-boxGeneralized and Efficient Blackbox Optimization System
โจโจA curated list of latest advances on Foundation Models with Federated Learning
๐ OpenHands: Code Less, Make More
Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on
The official PyTorch implementation of Google's Gemma models
Awesome LLM compression research papers and tools.
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Question and Answer based on Anything.
A scikit-learn-compatible module to estimate prediction intervals and control risks based on conformal predictions.
Robust recipes to align language models with human and AI preferences
[IJCAI 2024] FactCHD: Benchmarking Fact-Conflicting Hallucination Detection
https://acl2023-retrieval-lm.github.io/
๐ AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your daโฆ
An Autonomous LLM Agent for Complex Task Solving
21 Lessons, Get Started Building with Generative AI ๐ https://microsoft.github.io/generative-ai-for-beginners/
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
List of papers on hallucination detection in LLMs.
A quick guide (especially) for trending instruction finetuning datasets
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
CORE is a plug-and-play conversational agent for any recommender system.
Collaborative Training of Large Language Models in an Efficient Way
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
AWS Deep Learning Containers are pre-built Docker images that make it easier to run popular deep learning frameworks and tools on AWS.