Instructions to use Jaew00Lee/HiViG-critic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jaew00Lee/HiViG-critic with Transformers:

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

pipe = pipeline("image-text-to-text", model="Jaew00Lee/HiViG-critic")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Jaew00Lee/HiViG-critic")
model = AutoModelForMultimodalLM.from_pretrained("Jaew00Lee/HiViG-critic")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jaew00Lee/HiViG-critic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jaew00Lee/HiViG-critic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jaew00Lee/HiViG-critic",
		"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/Jaew00Lee/HiViG-critic

SGLang

How to use Jaew00Lee/HiViG-critic 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 "Jaew00Lee/HiViG-critic" \
    --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": "Jaew00Lee/HiViG-critic",
		"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 "Jaew00Lee/HiViG-critic" \
        --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": "Jaew00Lee/HiViG-critic",
		"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 Jaew00Lee/HiViG-critic with Docker Model Runner:
```
docker model run hf.co/Jaew00Lee/HiViG-critic
```

HiViG-critic / README.md

Jaew00Lee

Update README.md

013a789 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.89 kB

	---
	library_name: transformers
	license: other
	base_model: Qwen/Qwen3-VL-8B-Thinking
	tags:
	- llama-factory
	- full
	- generated_from_trainer
	model-index:
	- name: HiViG-critic
	results: []
	datasets:
	- OpenGVLab/ScaleCUA-Data
	language:
	- en
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# Model Card for HiViG-critic for HiViG (History-aware Visually Grounded) test-time intervention framework


	## Model Description

	HiViG (History-aware Visually Grounded), a test-time intervention framework designed to equip CUAs with history state tracking and visually grounded error analysis. Inside our framework, we propose HiVis-critic, a multimodal model to serve as an intervention engine with these dual critique generation capabilities.

	Key Highlights:

	* 📝 HiViG-critic for history state tracking: maintains a macro-action history, a compact record of past interactions to date, recursively compressing past interactions into multi-step achieved goals, enabling better history-aware planning of policies over long horizons.
	* 🎯 HiViG-critic for visually grounded error analysis: verifies raw execution coordinates against actual visual states. If a proposed action is flawed, the model identifies the error dimension to provide the policy with corrective guidance before execution.
	- Developed by: Jaewoo Lee, Zaid Khan, Archiki Prasad, Justin Chih-Yao Chen, Supriyo Chakraborty, Kartik Balasubramaniam, Sambit Sahu, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal
	- Model type: `Qwen3ForCausalLM`, fine-tuned Large Language Model
	- Language(s) (NLP): English
	- License: MIT
	- Finetuned from model: Qwen3-VL-8B-Thinking


	### Model Sources
	- Repository: https://github.com/G-JWLee/HiViG
	- Paper: [A History-Aware Visually Grounded Critic for Computer Use Agents](TBD)

	## Overview of HiViG

	![Overview of HiViG](https://raw.githubusercontent.com/G-JWLee/HiViG/main/assets/overview.png
	)

	## Uses

	### Test-time intervention
	The HiViG-critic model serves as an intervention engine with these dual critique generation capabilities to aid policies in long-horizon GUI tasks, enabling precise error analysis before execution and providing a history state tracking that allows better decisions.

	## Citation
	If you find this work useful, please consider citing us:
	```bibtex
	@article{lee2026hivig,
	title={A History-Aware Visually Grounded Critic for Computer Use Agents},
	author={Jaewoo Lee and Zaid Khan and Archiki Prasad and Justin Chih-Yao Chen and Supriyo Chakraborty and Kartik Balasubramaniam and Sambit Sahu and Elias Stengel-Eskin and Hyunji Lee and Mohit Bansal},
	year={2026},
	journal={arXiv preprint arXiv:2606.11078},
	url={https://arxiv.org/abs/2606.11078},
	}
	```