Instructions to use yongxianwei/InternVL2_5-1B_Geometry with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yongxianwei/InternVL2_5-1B_Geometry with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="yongxianwei/InternVL2_5-1B_Geometry", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yongxianwei/InternVL2_5-1B_Geometry", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yongxianwei/InternVL2_5-1B_Geometry with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yongxianwei/InternVL2_5-1B_Geometry"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yongxianwei/InternVL2_5-1B_Geometry",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/yongxianwei/InternVL2_5-1B_Geometry

SGLang

How to use yongxianwei/InternVL2_5-1B_Geometry with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yongxianwei/InternVL2_5-1B_Geometry" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yongxianwei/InternVL2_5-1B_Geometry",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yongxianwei/InternVL2_5-1B_Geometry" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yongxianwei/InternVL2_5-1B_Geometry",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use yongxianwei/InternVL2_5-1B_Geometry with Docker Model Runner:
```
docker model run hf.co/yongxianwei/InternVL2_5-1B_Geometry
```

InternVL2_5-1B_Geometry

The Geometry expert of the OptMerge MLLM merging benchmark (ICLR 2026). It is one of five capability experts (VQA, Geometry, Chart, OCR, Grounding) fine-tuned from the same base model, so that they can be merged into one model without training data.

Paper: OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging (OpenReview)
Extended version (SWUDI): Closed-Form Spectral Regularization for Multi-Task Model Merging, which also uses these experts in its multimodal merging benchmark
Code: WalkerWorldPeace/MLLMerging
All experts: MLLMerging collection

Training

Base model: OpenGVLab/InternVL2_5-1B
Method: Full fine-tuning (learning rate 4e-5, warmup ratio 0.03, cosine schedule, 1 epoch).
Data: GeoQA+ (zh), G-LLaVA (190K samples, Table 1 of the paper).

Results

From Table 2 of the paper. The last row merges this expert with the other four experts using OptMerge.

Model	VizWiz	GQA	MathVista	MATH-Vision	ChartQA	TextVQA	OCRVQA	RefCOCO	RefCOCO+	RefCOCOg	Avg.
InternVL2.5-1B-Instruct (base model)	29.15	54.62	46.80	18.42	69.48	72.51	41.08	71.69	65.41	67.40	53.66
InternVL2_5-1B_Geometry	13.45	32.80	55.20	25.00	51.76	56.91	35.35	24.73	19.61	23.84	33.86
OptMerge (5 experts merged)	30.97	57.13	54.48	21.05	68.72	76.01	46.35	75.97	69.72	73.94	57.44

Usage

# pip install timm einops   (required by the InternVL remote code)
import torch
from transformers import AutoModel, AutoTokenizer

model_id = "yongxianwei/InternVL2_5-1B_Geometry"
model = AutoModel.from_pretrained(model_id, torch_dtype=torch.bfloat16, trust_remote_code=True).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
# Image preprocessing and model.chat(...) follow the official InternVL2.5-1B model card.

To merge the five experts yourself, see Reproducing OptMerge.

Citation

If you use these checkpoints or the MLLMerging code, please cite both OptMerge and its extended version:

@inproceedings{wei2025optmerge,
  title={OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging},
  author={Wei, Yongxian and Cheng, Runxi and Jin, Weike and Yang, Enneng and Shen, Li and Hou, Lu and Du, Sinan and Yuan, Chun and Cao, Xiaochun and Tao, Dacheng},
  booktitle={The Fourteenth International Conference on Learning Representations},
  year={2026},
  url={https://openreview.net/forum?id=Me0n0iESJY}
}

@article{wei2026swudi,
  title={Closed-Form Spectral Regularization for Multi-Task Model Merging},
  author={Wei, Yongxian and Cheng, Runxi and Zhang, Xingxuan and Shen, Li and Yuan, Chun and Cui, Peng and Tao, Dacheng},
  journal={arXiv preprint arXiv:2606.07289},
  year={2026}
}