GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
cfcamo
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cfcamo
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForImageTextToText, AutoProcessorfrom PIL import Imageckpt = "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)
bash
git clone https://github.com/suhang2000/CFCamo && cd CFCamopip install -e .huggingface-cli download cfcamo/cfcamo-sft-4b --local-dir checkpoints/cfcamo-sft-4bhuggingface-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.
bibtex
@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}}