Instructions to use aimagelab/CounterVid-InternVL3-9B-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aimagelab/CounterVid-InternVL3-9B-LoRA with Transformers:

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

pipe = pipeline("image-text-to-text", model="aimagelab/CounterVid-InternVL3-9B-LoRA", 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)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("aimagelab/CounterVid-InternVL3-9B-LoRA", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aimagelab/CounterVid-InternVL3-9B-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aimagelab/CounterVid-InternVL3-9B-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aimagelab/CounterVid-InternVL3-9B-LoRA",
		"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/aimagelab/CounterVid-InternVL3-9B-LoRA

SGLang

How to use aimagelab/CounterVid-InternVL3-9B-LoRA 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 "aimagelab/CounterVid-InternVL3-9B-LoRA" \
    --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": "aimagelab/CounterVid-InternVL3-9B-LoRA",
		"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 "aimagelab/CounterVid-InternVL3-9B-LoRA" \
        --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": "aimagelab/CounterVid-InternVL3-9B-LoRA",
		"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 aimagelab/CounterVid-InternVL3-9B-LoRA with Docker Model Runner:
```
docker model run hf.co/aimagelab/CounterVid-InternVL3-9B-LoRA
```

CounterVid — InternVL3-9B

This repository contains the 9B CounterVid-aligned model from CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models (EMNLP 2026).

CounterVid improves grounding in video-language models by combining textual and visual preferences generated from controlled counterfactual videos. The released weights are a standalone merge of the language-model LoRA, the trained multimodal projector, and the original InternVL3 base model.

Loading

import torch
from transformers import AutoModel, AutoTokenizer

model_id = "aimagelab/CounterVid-InternVL3-9B-LoRA"
model = AutoModel.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto", trust_remote_code=True,
).eval()
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False)

For complete video inference and evaluation examples, see the CounterVid repository and project page.

Training summary

Base model: OpenGVLab/InternVL3-9B-Instruct
Training data: CounterVid (26,167 synthetic visual and textual preference pairs)
Objective: MixDPO / PaMi-VDPO with CounterVid anchors
LoRA was merged before release; PEFT is not required at inference time
Vision encoder frozen during preference optimization

Intended use and limitations

This is a research model for video-language understanding, with a focus on action recognition and temporal reasoning. It inherits the capabilities, limitations, biases, and license conditions of its base model. It may still produce incorrect or unsupported answers and should not be used as the sole basis for high-stakes decisions.

Citation

@inproceedings{poppi2026countervid,
  title     = {{CounterVid}: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models},
  author    = {Poppi, Tobia and Uzkent, Burak and Garg, Amanmeet and Porto, Lucas and Kessler, Garin and Yang, Yezhou and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita and Schiffers, Florian},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year      = {2026}
}

This work was conducted during Tobia Poppi's Applied Scientist internship with the Amazon Prime Video team in Seattle.