Instruct-tune LLaMA on consumer hardware

Use Large Language Models (such as ChatGPT) to automatically generate flashcards from obsidian notes

Data augmentation for NLP

📚 Freely available programming books

Build ChatGPT over your data, all with natural language

通义千问VLLM推理部署DEMO

The latest research progress of Contrastive Learning(CL), Data Augmentation(DA) and Self-Supervised Learning(SSL) in Recommender Systems

Material for gpu-mode lectures

how to optimize some algorithm in cuda.

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.

C++ implementation of Qwen-LM

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

Sample codes for my CUDA programming book

export llama to onnx

LLaMa/RWKV onnx models, quantization and testcase

A primitive library for neural network

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Skeleton code for 61B Spring 2023

Night theme for Zotero UI and PDF

This is an implementation for our SIGIR2023 paper "Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation" based on PyTorch.

[SIGIR'2023] "MAERec: Graph Masked Autoencoder for Sequential Recommendation"

Build Recommender System with PyTorch + Redis + Elasticsearch + Feast + Triton + Flask. Vector Recall, DeepFM Ranking and Web Application.

core for Modeling Dual Period-Varying Preferences for Takeaway Recommendation