How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PerRing/InternVL-MoonViT-V2-MiniCPM5-2B-HF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PerRing/InternVL-MoonViT-V2-MiniCPM5-2B-HF",
		"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/PerRing/InternVL-MoonViT-V2-MiniCPM5-2B-HF
Quick Links

InternVL-MoonViT-V2-MiniCPM5-2B-HF

This model combines the MoonViT V2 vision encoder from Kimi K3 with the MiniCPM5-2B language model.

The multimodal projector (MLP) was not trained. Please keep this in mind when evaluating or using the model.

Model architecture

  • Vision encoder: MoonViT V2 from Kimi K3
  • Language model: MiniCPM5-2B
  • Multimodal projector (MLP): not trained

Loading the model

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "PerRing/InternVL-MoonViT-V2-MiniCPM5-2B-HF"

processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,
)

model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
).eval()

Note: This repository uses custom modeling and processing code, so trust_remote_code=True is required.

Downloads last month
21
Safetensors
Model size
3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support