zpointsun / DiBO-TFBind10

DiBO-TFBind10

Final task-specific DiBO model for TFBind10-Exact-v0 , released with Training Diffusion Language Models for Black-Box Optimization (ICML 2026 Spotlight). See also the Hugging Face paper page and the DiBO code repository .

This model completed domain adaptation (DA), supervised fine-tuning (SFT), and reinforcement learning (RL).

Available model formats

This repository provides the same final task-specific DiBO model in two formats.

1. Original PyTorch checkpoint. dibo_tfbind10_final.pt is the canonical paper-faithful checkpoint produced by the DiBO training pipeline. It stores the state dictionary under the model key and is loaded through the DiBO codebase on top of the pinned LLaDA base revision.
2. Transformers/safetensors export. The root-level config, tokenizer, custom modeling code, and sharded safetensors files are a validated convenience export derived deterministically from the original checkpoint. They load directly with AutoModel.from_pretrained(...) .

The safetensors model was not trained separately. The LLaDA base weights are not duplicated in this repository.

Artifact details

• Base model: GSAI-ML/LLaDA-8B-Instruct , revision 08b83a6feb34df1a6011b80c3c00c7563e963b07
• Original checkpoint: dibo_tfbind10_final.pt (16,030,379,937 bytes; SHA-256 c59f6fa207da0bedaa32358d14a5993f82114cd9291cfab43dba07a40762bb2f )
• Original format: PyTorch checkpoint dictionary, state dict at model
• Transformers model class: DiBOLLaDAModelLM loaded with AutoModel
• Tokenizer: PreTrainedTokenizerFast , vocabulary size 126,353
• Input/output vocabulary rows: 126,353 / 126,464
• Required delimiter tokens: |design-start| , |design-end| , |label-start| , |label-end|

The standard export contains the following safetensors shards:

• model-00001-of-00004.safetensors (4,994,672,360 bytes; SHA-256 8257b71a2a1653c727a8ed9d18198fe163c59e1097f4a71667aae74b4974c289 )
• model-00002-of-00004.safetensors (4,999,819,552 bytes; SHA-256 36ad1d3890048e523dea1ad1e0c93c65ad1ccca1fa58a9e78f807756ac59c8ce )
• model-00003-of-00004.safetensors (4,999,802,728 bytes; SHA-256 37a754e45c61bb5c0635738334f933ca9569c99b3c3d81132b61cd28753103fe )
• model-00004-of-00004.safetensors (1,035,993,232 bytes; SHA-256 9b769101354e1a53c62ae5355e76d56c03a5ffcbc82ad6542807168c4ce96f56 )

Its total weight size is 16,030,287,872 bytes. The machine-readable artifact manifest and validation report record source hashes and measured validation results. Validation passed for: candidate parity, config equality, forward parity, remote from pretrained, remote pt download, strict load, task smoke, tokenizer equality, weight equality.

A. Load the standard Transformers export

from transformers import AutoModel, AutoTokenizer

repo_id = "zpointsun/DiBO-TFBind10"
tokenizer = AutoTokenizer.from_pretrained(
    repo_id,
    revision="v1.1.1",
    trust_remote_code=True,
)
model = AutoModel.from_pretrained(
    repo_id,
    revision="v1.1.1",
    trust_remote_code=True,
    use_safetensors=True,
    torch_dtype="auto",
)
model.eval()

The packaged tokenizer already includes the four DiBO delimiter tokens. Do not add them or resize embeddings again after loading this export.

B. Download and load the original checkpoint

The original artifact uses the released DiBO loader, which initializes the pinned LLaDA base, adds the four delimiter tokens, resizes the input embedding, and strictly loads checkpoint["model"] .

hf download zpointsun/DiBO-TFBind10 dibo_tfbind10_final.pt \
  --revision v1.1.1 --local-dir checkpoints/dibo-tfbind10

import torch
from huggingface_hub import hf_hub_download
from src.model.dllm import DEFAULT_MODEL_ID, LLADA_MODEL_REVISION, load_model_and_tokenizer

assert DEFAULT_MODEL_ID == "GSAI-ML/LLaDA-8B-Instruct"
assert LLADA_MODEL_REVISION == "08b83a6feb34df1a6011b80c3c00c7563e963b07"
checkpoint_path = hf_hub_download(
    "zpointsun/DiBO-TFBind10",
    filename="dibo_tfbind10_final.pt",
    revision="v1.1.1",
)
model, tokenizer = load_model_and_tokenizer(DEFAULT_MODEL_ID, device="cuda")
checkpoint = torch.load(checkpoint_path, map_location="cuda")
model.load_state_dict(checkpoint["model"], strict=True)
model.eval()

C. Evaluate either format

From a checkout of the released DiBO code and its oracle environment:

# Standard Transformers export
python eval.py --tasks TFBind10-Exact-v0 \
  --model_name_or_path zpointsun/DiBO-TFBind10 --model_revision v1.1.1 \
  --seeds <SEEDS> --max_attempts 1000

# Canonical local .pt checkpoint
python eval.py --tasks TFBind10-Exact-v0 \
  --checkpoint_path checkpoints/dibo-tfbind10/dibo_tfbind10_final.pt \
  --seeds <SEEDS> --max_attempts 1000

Both choices share the same downstream DiBO evaluation path. Direct oracle evaluation requires the Design-Bench data cache and task dependencies described in the DiBO repository . For the exact Design-Bench snapshot used in the DiBO experiments, see DiBO-DesignBench-Snapshot .

Limitations

Practical inference requires a CUDA-capable PyTorch environment. These task-specific models are designed for DiBO's masked-response generation and evaluation workflow; this release does not claim generic text-generation pipeline support. Loading a released final model is for evaluation or use and does not reproduce the DA/SFT/RL training process.

Other DiBO task models

• DiBO-TFBind8
• DiBO-AntMorphology
• DiBO-DKittyMorphology

Citation

If you find DiBO helpful, please cite:

@article{sun2026training,
  title={Training diffusion language models for black-box optimization},
  author={Sun, Zipeng and Chen, Can and Yuan, Ye and Wu, Haolun and Gu, Jiayao and Pal, Christopher and Liu, Xue},
  journal={arXiv preprint arXiv:2603.17919},
  year={2026}
}