Files
transformers/docs/source/en/model_doc/modernvbert.md
陈赣 06f1fd69a6
Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
first commit
2026-06-05 16:53:03 +08:00

3.0 KiB
Executable File

This model was published in HF papers on 2025-10-01 and contributed to Hugging Face Transformers on 2026-02-23.

ModernVBert

FlashAttention SDPA

Overview

ModernVBert is a Vision-Language encoder that combines ModernBert with a SigLIP vision encoder. It is optimized for visual document understanding and retrieval tasks.

The model was introduced in ModernVBERT: Towards Smaller Visual Document Retrievers.

import torch
from huggingface_hub import hf_hub_download
from PIL import Image

from transformers import AutoModelForMaskedLM, AutoProcessor


processor = AutoProcessor.from_pretrained("./mvb")
model = AutoModelForMaskedLM.from_pretrained("./mvb", device_map="auto")

image = Image.open(hf_hub_download("HuggingFaceTB/SmolVLM", "example_images/rococo.jpg", repo_type="space"))
text = "This [MASK] is on the wall."

# Create input messages
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": text}
        ]
    },
]

# Prepare inputs
prompt = processor.apply_chat_template(messages)
inputs = processor(text=prompt, images=[image], return_tensors="pt").to(model.device)

# Inference
with torch.no_grad():
  outputs = model(**inputs)

# To get predictions for the mask:
masked_index = inputs["input_ids"][0].tolist().index(processor.tokenizer.mask_token_id)
predicted_token_id = outputs.logits[0, masked_index].argmax(axis=-1)
predicted_token = processor.tokenizer.decode(predicted_token_id)
print("Predicted token:", predicted_token)  # Predicted token: painting

ModernVBertConfig

autodoc ModernVBertConfig

ModernVBertModel

autodoc ModernVBertModel - forward

ModernVBertForMaskedLM

autodoc ModernVBertForMaskedLM - forward

ModernVBertForSequenceClassification

autodoc ModernVBertForSequenceClassification - forward

ModernVBertForTokenClassification

autodoc ModernVBertForTokenClassification - forward