Starred repositories
🚀 AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys, etc. 🗃️ Llama3, Mistral, etc. 🧑💻 Vi…
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A modular graph-based Retrieval-Augmented Generation (RAG) system
A complete computer science study plan to become a software engineer.
Interactive SQL generation via editable step-by-step explanation
Some code and data for the paper: "Labeling Programs with Non-Programmers Indirectly via Active Examples: A Case Study with Text-to-SQL"
scripts and baselines for Spider: Yale complex and cross-domain semantic parsing and text-to-SQL challenge
A large annotated semantic parsing corpus for developing natural language interfaces.
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…
Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.
A collection of datasets that pair questions with SQL queries.
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
[ACL 2024] Long-Context Language Modeling with Parallel Encodings
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems
A playbook for systematically maximizing the performance of deep learning models.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
[WWW'23] PyTorch implementation for "Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders".
Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper
This is a re-implementation of TransGAN: Two Pure Transformers Can Make One Strong GAN (NeurIPS 2021) in PyTorch.
[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang
This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.
Lossless Training Speed Up by Unbiased Dynamic Data Pruning