gxglxy's starred repositories
Gaunt-Tensor-Product
[ICLR 2024 Spotlight] Official Implementation of "Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products"
equiformer_v2
[ICLR'24] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
consistency_models
Official repo for consistency models.
egt_pytorch
Edge-Augmented Graph Transformer
ogb-lsc-pcqm4mv2
The OGB-LSC is the Large Scale Competition by Open Graph Benchmark to help accelerate research into machine learning on graph structured data
Transformer-M
[ICLR 2023] One Transformer Can Understand Both 2D & 3D Molecular Data (official implementation)
Graphormer-GD
[ICLR 2023 notable top-5%] Rethinking the Expressive Power of GNNs via Graph Biconnectivity (official implementation)
Graphormer
Graphormer is a general-purpose deep learning backbone for molecular modeling.
powerful-gnns
How Powerful are Graph Neural Networks?
GNN4NLP-Papers
A list of recent papers about Graph Neural Network methods applied in NLP areas.
ChatGLM-Tuning
基于ChatGLM-6B + LoRA的Fintune方案
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
open_flamingo
An open-source framework for training large multimodal models.
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
openai-cookbook
Examples and guides for using the OpenAI API
ColossalAI
Making large AI models cheaper, faster and more accessible
LLaMA-Adapter
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters