SUSTechBruce

Open-LLaVA-NeXT

An open-source implementation for training LLaVA-NeXT.

SAWT

Official python implementation for ICML 2024: "Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem"

neuralgcm

Hybrid ML + physics model of the Earth's atmosphere

scaling-with-vocab

📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

LOOK-M

Official implementation of "LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference"

Parameter-Efficient-Transfer-Learning-Benchmark

A Unified Parameter-Efficient Transfer Learning Benchmark for Computer Vision Tasks

Awesome-Efficient-Diffusion

Curated list of methods that focuses on improving the efficiency of diffusion models

qllm-eval

Code Repository of Evaluating Quantized Large Language Models

lm-evaluation-harness

A framework for few-shot evaluation of language models.

LLaVA-PruMerge

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models

f-divergence-dpo

Direct preference optimization with f-divergences.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

2024-sbdd-benchmark

LESS

SVD-LLM

Official Code for "SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression"

Apollo-AAAI-2024-Release

Source code for AAAI-2024 oral paper: Preparing Lessons for Progressive Training on Language Models

struct-iou

structured intersection-over-union ratio for evaluation of (speech) constituency parsing.

generative-models

Generative Models by Stability AI

teco

CEPE

[ACL 2024] Long-Context Language Modeling with Parallel Encodings

Sentimental_analysis_Chinese

Chinese sentences sentimental analysis

MedLLMsPracticalGuide

A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers)

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

Efficient-LLMs-Survey

Efficient Large Language Models: A Survey

adaptively_sparse_attention

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

open-instruct

Paper-list-resource-efficient-large-language-model

RESTC-Source-code

Source code of ACM TOIS accepted paper "Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation"

Moonlit

This is a collection of our research on efficient AI, covering hardware-aware NAS and model compression.