opd

Open Source, Enterprise and Modern Health Information System

A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

🔥 DanceOPD: On-Policy Generative Field Distillation

Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.

Unofficial PyTorch reproduction of DeepSeek's Thinking with Visual Primitives.

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

Official implementation of On-Policy Delta Distillation (OPD2)

Tiny-R2: A hybrid architecture integrating SWA, CSA, HCA, mHC, and DSMoE under the DeepSeek V4 design paradigm, enabling single-GPU OPD post-training.

The implementation for our paper: TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning.

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

🔥 Learning When to Trust via Selective Context Preference Optimization

Open Source Health Information System. Get your Frappe Health instance ready within a few seconds and uncover the potentials of digitising your operations.

Open Source Health Information System. Get your Frappe Health instance ready within a few seconds and uncover the potentials of digitising your operations.

Repositório do Projeto dos Ensaios de Caracterização dos CCDs do Observatório Pico dos Dias.

This project was realised during our Industrial Project. Real project : https://github.com/Victor804/keithley-software