kuleshov-group/e2d2-gsm8k-finetune-Qwen3-2B

Quick start guide

To use this models, follow the snippet below:

from transformers import AutoModelForMaskedLM

# model_config_overrides = {}  # Use this to optionally override config parameters
model = AutoModelForMaskedLM.from_pretrained(
    "kuleshov-group/e2d2-gsm8k-finetune-Qwen3-2B",
    trust_remote_code=True,
    # **model_config_overrides,
)

Model details

• Fine-tuned from Qwen/Qwen3-1.7B-Base on openai/gsm8k
• Qwen3 tokenizer: Qwen/Qwen3-1.7B-Base
• Block diffusion parameterization, with block size 4

See the project site for more details and link to the paper and code: https://m-arriola.com/e2d2/

Citation

@inproceedings{
  arriola2025e2d2,
  title={Encoder-Decoder Diffusion Language Models for Efficient Training and Inference},
  author={Marianne Arriola and Yair Schiff and Hao Phung and Aaron Gokaslan and Volodymyr Kuleshov},
  booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
  year={2025},
  url={https://arxiv.org/abs/2510.22852}
}