Official PyTorch Code for SAFF (ICCV 2023)

Sparse Autoencoder for Mechanistic Interpretability

Using sparse coding to find distributed representations used by neural networks.

The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".

A Closer Look into Mixture-of-Experts in Large Language Models

Mode Connectivity and Fast Geometric Ensembles in PyTorch

A 100x faster SVD for PyTorch⚡️

🏆 [CVPRW 2024] COVER: A Comprehensive Video Quality Evaluator. 🥇 Winner solution for Video Quality Assessment Challenge at the 1st AIS 2024 workshop @ CVPR 2024

Implementation of LPLR algorithm for matrix compression

A method of ensemble learning for heterogeneous large language models.

[CHIL 2024] Interpretation of Intracardiac Electrograms Through Textual Representations

LLM101n: Let's build a Storyteller

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Evaluating Durability: Benchmark Insights into Multimodal Watermarking

Analysis of token routing for different implementations of Mixture of Experts

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Conversions of Fairseq models in HuggingFace-style

[SIGIR'24] The official implementation code of MOELoRA.

DeepSeek LLM: Let there be answers

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".

AdaMoLE: Adaptive Mixture of Low-Rank Adaptation Experts

LLM-Merging: Building LLMs Efficiently through Merging

The official code for AISTATS 2024 "Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations"