Downloads · 30 days
69
24% of all-time downloads
ME-DLM-Stage3
renhouxing/ME-DLM-Stage3
ME-DLM-Stage3 is a text generation model from renhouxing. Use it when you need the model to write or continue text. It is set up for transformers.
<p align="center" <a href="https://arxiv.org/abs/2605.09603"📄 Paper</a • <a href="https://github.com/renhouxing/ME-DLM"🏠 Repo</a • <a href="https://huggingface.co/renhouxing/ME-DLM-Stage3"🤖 Models</a </p
All-time downloads
286
Public
Parameters
8.5B
17.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llada
- Access
- Public
- Created
- May 12, 2026
- Updated
- May 13, 2026
- SHA
- d705e5fa
Try a prompt
Base models
Model card
From the Hugging Face model README
Edit-Based Refinement for Parallel Masked Diffusion Language Models
<p align="center"> <a href="https://arxiv.org/abs/2605.09603">📄 Paper</a> • <a href="https://github.com/renhouxing/ME-DLM">🏠 Repo</a> • <a href="https://huggingface.co/renhouxing/ME-DLM-Stage3">🤖 Models</a> </p>Introduction
ME-DLM is a lightweight edit-based refinement framework for masked diffusion language models. It first generates a complete response through parallel diffusion decoding, then refines the output with minimal edit operations such as replacement, deletion, and insertion, conditioned on the full sequence. By using edit distance as deterministic training supervision, ME-DLM improves sequence-level consistency while preserving the decoding efficiency of diffusion models. Built on LLaDA, it achieves consistent gains on HumanEval and GSM8K while using only one-eighth of the total diffusion steps.
Models
Acknowledgments
We thank the following amazing projects that truly inspired us:
- Task
- Text Generation
- Library
- transformers
- Type
- llada
- Languages
- en
- Created
- May 12, 2026
- Updated
- May 13, 2026