Qingyun Wang's starred repositories
llama-recipes
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
KnowledgeEditingPapers
[知识编辑] Must-read Papers on Knowledge Editing for Large Language Models.
Megatron-LLM
distributed trainer for LLMs
gt4sd-core
GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.
UltraFeedback
A large-scale, fine-grained, diverse preference dataset (and models).
Generative_KG_Construction_Papers
[EMNLP 2022] Generative Knowledge Graph Construction: A Review
csfaculty.github.io
Interview questions for Computer Science faculty jobs
enzyme-datasets
Enzyme datasets used to benchmark enzyme-substrate promiscuity models
Megatron-LLM
distributed trainer for LLMs