README.md

metadata

license: mit
base_model: Dream-org/Dream-v0-Instruct-7B
tags:
  - dllm-prm-gap
  - discrete-diffusion
  - gsm8k
  - process-reward-model
  - dream-7b
pipeline_tag: text-classification
library_name: peft

dLLM PRM Gap · C3A · causal last-token · seed 43

💻 Code   •   🤗 Collection   •   📄 Paper

News

• 2026-09: Accepted at NeurIPS 2026.

Public adapter release for dLLM PRM Gap. a C3 control checkpoint with the stated attention/readout protocol and seed.

This repository contains only trainable adapter parameters and the reward head. It does not include the base model. The release configuration is recorded in config.json; the arXiv paper defines the release scope and citation.

Files

• adapter.safetensors — compact adapter weights
• config.json — public base-model id, architecture, and provenance

Load

from huggingface_hub import snapshot_download
from prm.checkpointing import load_diffusion_prm

path = snapshot_download("YanZhanPKU/dLLM-PRM-Gap-c3a-causal-lasttoken-dream7b-s43")
model, report = load_diffusion_prm(
    checkpoint=path,
    model_path="Dream-org/Dream-v0-Instruct-7B",
    local_files_only=False,
)

Role: C3A causal last-token ORM-protocol control.

Paper: https://arxiv.org/abs/2609.35472.