---
base_model: GSAI-ML/LLaDA-8B-Base
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:GSAI-ML/LLaDA-8B-Base
- lora
- rainbow-padding
- instruct-tuning
---

# Rainbow Padding LLaDA Instruct

We introduce Rainbow Padding, a cyclic multi-token padding scheme
that eliminates early termination and restores length robustness in instruction-tuned diffusion LLMs.

This checkpoint is a LoRA adapter for LLaDA-8B-Base with Rainbow Padding applied.


### Model Details

- **Project Page:** [Rainbow Padding Official Website](https://ai-isl.github.io/rainbow-padding.html)
- **GitHub Repository:** [Rainbow Padding Implementation](https://github.com/quasar529/rainbow-padding)
- **Paper:** [Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs](https://arxiv.org/abs/2510.03680)