dLLM PRM Gap
Collection
Adapters and trajectory artifacts for matched-compute PRM guidance and ORM reranking in discrete diffusion reasoning. • 13 items • Updated • 1
How to use YanZhanPKU/dLLM-PRM-Gap-c3c-bidir-meanpool-dream7b-s42 with PEFT:
Task type is invalid.
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.
adapter.safetensors — compact adapter weightsconfig.json — public base-model id, architecture, and provenancefrom huggingface_hub import snapshot_download
from prm.checkpointing import load_diffusion_prm
path = snapshot_download("YanZhanPKU/dLLM-PRM-Gap-c3c-bidir-meanpool-dream7b-s42")
model, report = load_diffusion_prm(
checkpoint=path,
model_path="Dream-org/Dream-v0-Instruct-7B",
local_files_only=False,
)
Role: C3C bidirectional mean-pool ORM-protocol control.
Paper: https://arxiv.org/abs/2609.35472.
Base model
Dream-org/Dream-v0-Instruct-7B