dcvlm-4b-model

DCVLM-4B

DCVLM-4B is the large-scale reference 4B-parameter VLM from our DataComp-VLM paper, pretrained from scratch on DCVLM-Baseline.

⚠️ This is a pretrained (base) model, not an instruction-tuned assistant. It is released as a reproducible reference point for data-centric research: to compare pretraining datasets, and as an initialization for your own SFT. It has not been chat- or preference-tuned and should not be expected to follow instructions reliably.

Model details

Results

Core evaluation suite (33 tasks), compared against FineVision, the previous best open pretraining dataset, trained at the same scale with the same architecture and token budget.

Categories: Gen general understanding · Know knowledge · OCR OCR & charts · Vision vision-centric · MTL multilingual · Text text-only.

Usage

The model uses custom modeling code, so trust_remote_code=True is required.

import torch
from transformers import AutoModel, AutoTokenizer

path = "mlfoundations/dcvlm-4b-model"
model = AutoModel.from_pretrained(
    path, torch_dtype=torch.bfloat16, trust_remote_code=True, low_cpu_mem_usage=True
).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

Image preprocessing follows the standard InternVL-2.5 dynamic-tiling recipe (448px tiles, max_dynamic_patch=12).

Related releases

Citation

@article{farina2026datacomp,
  title={DataComp-VLM: Improved Open Datasets for Vision-Language Models},
  author={Farina, Matteo and Udandarao, Vishaal and Nguyen, Thao and Kuzucu, Selim and B{\"o}ther, Maximilian and Hochlehnert, Andreas and Ghosh, Adhiraj and Nezhurina, Marianna and Roth, Karsten and Struber, Joschka and others},
  journal={arXiv preprint arXiv:2606.28551},
  year={2026}
}