Pumpkin's starred repositories
shallow-vs-deep-alignment
Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Riemannian_Preconditioned_LoRA
source code for paper "Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models"
ConfusionXL
ConfusionXL V2.0 - 世界上最好的2次元模型
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
open-gpu-kernel-modules
NVIDIA Linux open GPU with P2P support
SMDL-Attribution
[ICLR 2024 Oral] Less is More: Fewer Interpretable Region via Submodular Subset Selection
easy-to-hard
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision