Instructions to use cfcamo/cfcamo-sft-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cfcamo/cfcamo-sft-4b with Transformers:

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

pipe = pipeline("image-text-to-text", model="cfcamo/cfcamo-sft-4b")
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("cfcamo/cfcamo-sft-4b")
model = AutoModelForMultimodalLM.from_pretrained("cfcamo/cfcamo-sft-4b")
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 cfcamo/cfcamo-sft-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cfcamo/cfcamo-sft-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cfcamo/cfcamo-sft-4b",
		"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/cfcamo/cfcamo-sft-4b

SGLang

How to use cfcamo/cfcamo-sft-4b 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 "cfcamo/cfcamo-sft-4b" \
    --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": "cfcamo/cfcamo-sft-4b",
		"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 "cfcamo/cfcamo-sft-4b" \
        --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": "cfcamo/cfcamo-sft-4b",
		"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 cfcamo/cfcamo-sft-4b with Docker Model Runner:
```
docker model run hf.co/cfcamo/cfcamo-sft-4b
```

CFCamo-SFT-4B

Cold-start checkpoint for CFCamo: Qwen3-VL-4B-Instruct fine-tuned on 1000 paired SFT rows (500 detect + 500 abstain, r=1:1) to teach the detect-or-abstain output schema. This is the init from which the RL stages (LoRA / Full FT) are trained; on its own it already abstains on target-absent counterfactuals but the paper-main numbers come from the RL checkpoints.

📄 Paper: https://arxiv.org/abs/2606.11231
Code & training recipe: https://github.com/suhang2000/CFCamo
Benchmark (CF-COD) + training data: https://huggingface.co/datasets/cfcamo/CF-COD

Use it

from transformers import AutoModelForImageTextToText, AutoProcessor
from PIL import Image

ckpt = "cfcamo/cfcamo-sft-4b"
processor = AutoProcessor.from_pretrained(ckpt)
model = AutoModelForImageTextToText.from_pretrained(
    ckpt, torch_dtype="auto", device_map="auto",
).eval()
# (use the same detect-or-abstain prompt as cfcamo-rl-full — see that model card)

Continue training: RL on top

git clone https://github.com/suhang2000/CFCamo && cd CFCamo
pip install -e .
huggingface-cli download cfcamo/cfcamo-sft-4b --local-dir checkpoints/cfcamo-sft-4b
huggingface-cli download --repo-type dataset cfcamo/CF-COD --local-dir data/cfcod
# LoRA (single GPU) — paper-main LoRA checkpoint at step 252 (epsilon=0.5)
python -m verl.trainer.main config=configs/rl_lora.yaml
# Full fine-tuning (multi-GPU) — checkpoint at step 126 (epsilon=0.5)
python -m verl.trainer.main config=configs/rl_full.yaml

The two RL checkpoints are also released at cfcamo/cfcamo-rl-lora (LoRA adapter on top of this SFT base) and cfcamo/cfcamo-rl-full.

Training summary

Base: Qwen/Qwen3-VL-4B-Instruct (Apache-2.0)
Data: 1000 SFT rows (paired r=1:1) with paired CoT reasoning
1 epoch, lr 2e-5, batch=2 × grad_accum=8

Citation

@article{li2026cfcamo,
  title   = {{CFCamo}: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection},
  author  = {Li, Suhang and Yoshie, Osamu and Ieiri, Yuya},
  journal = {arXiv preprint arXiv:2606.11231},
  year    = {2026}
}