ViTP InternVL 1B RS

Usage

The model repo includes the modeling code. Load with transformers (no ViTP repo needed):

from transformers import AutoModel, AutoImageProcessor
import torch

device = "cuda"
model = AutoModel.from_pretrained(
    "BiliSakura/ViTP-InternVL-1B-RS",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map=device,
).eval()

processor = AutoImageProcessor.from_pretrained("BiliSakura/ViTP-InternVL-1B-RS")
pixel_values = processor(images="image.jpg", return_tensors="pt").pixel_values.to(device, model.dtype)

with torch.no_grad():
    outputs = model(pixel_values=pixel_values)

# Pooled CLS token: (1, 1024)
features = outputs.pooler_output
# Or full sequence: outputs.last_hidden_state

Citation

@article{Li_2025_ViTP,
  title={Visual Instruction Pretraining for Domain-Specific Foundation Models},
  author={Li, Yuxuan and Zhang, Yicheng and Tang, Wenhao and Dai, Yimian and Cheng, Ming-Ming and Li, Xiang and Yang, Jian},
  journal={arXiv},
  year={2025}
}

--- license: cc-by-nc-4.0 tags: - vision - image-classification - vit - ViTP - InternVL - domain-adaptation - remote-sensing language: - en library_name: transformers pipeline_tag: image-feature-extraction base_model: - GreatBird/ViTP --- # ViTP-InternVL-1B-RS ViTP (Visual Instruction Pretraining) vision backbone — **InternVL 1B** variant pretrained on **remote sensing** domain visual instruction data. Compatible with `InternVisionModel` from [InternVL](https://github.com/OpenGVLab/InternVL). ## Model Details - **Architecture**: InternVisionModel (24 layers, 1024 hidden, 16 heads) - **Image size**: 448×448 - **Patch size**: 14 - **Domain**: Remote sensing ## Usage The model repo includes the modeling code. Load with `transformers` (no ViTP repo needed): ```python from transformers import AutoModel, AutoImageProcessor import torch device = "cuda" model = AutoModel.from_pretrained( "BiliSakura/ViTP-InternVL-1B-RS", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map=device, ).eval() processor = AutoImageProcessor.from_pretrained("BiliSakura/ViTP-InternVL-1B-RS") pixel_values = processor(images="image.jpg", return_tensors="pt").pixel_values.to(device, model.dtype) with torch.no_grad(): outputs = model(pixel_values=pixel_values) # Pooled CLS token: (1, 1024) features = outputs.pooler_output # Or full sequence: outputs.last_hidden_state ``` ## Citation ```bibtex @article{Li_2025_ViTP, title={Visual Instruction Pretraining for Domain-Specific Foundation Models}, author={Li, Yuxuan and Zhang, Yicheng and Tang, Wenhao and Dai, Yimian and Cheng, Ming-Ming and Li, Xiang and Yang, Jian}, journal={arXiv}, year={2025} } ```