Feature Extraction
Transformers
Safetensors
llada
diffusion-language-model
dllm
LLaDA
WINO
WINO-plus
custom_code
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QinFFF/WINO-plus-LLaDA-8B-Instruct", trust_remote_code=True, dtype="auto")Quick Links
WINO-plus-LLaDA-8B-Instruct
This repository contains the full merged 8B model weights of WINO+, initialized from LLaDA-8B-Instruct.
WINO+ is a trajectory-injection method for diffusion large language models. It transfers the verified denoising order discovered by WINO into model parameters, enabling faster and higher-quality generation.
The model corresponds to the WINO+ method described in Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers.
- Downloads last month
- 27
Model tree for QinFFF/WINO-plus-LLaDA-8B-Instruct
Base model
GSAI-ML/LLaDA-8B-Instruct
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="QinFFF/WINO-plus-LLaDA-8B-Instruct", trust_remote_code=True)