金谷园饺子馆.Skill - 北邮旁的饺子馆

Code implementation for DyNAS-DDI: Dynamic Pairwise Architecture Search for Generalizable Drug-Drug Interaction LLM, accepted by ACM MM 2025.

🚀 Efficient implementations for emerging model architectures

Qwen2.5 0.5B GRPO

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".

off-policy RL on long sequences

A collection of RL baselines in Jax.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

翻墙、免费翻墙、免费科学上网、免费节点、免费梯子、免费ss/v2ray/trojan节点、蓝灯、谷歌商店、翻墙梯子

Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

一个专为1.10.2/1.12.2主流整合包添加手册本地化以及其他本地化的仓库

Python 练习册，每天一个小程序