Instructions to use cfli/A-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cfli/A-base with Transformers:

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

pipe = pipeline("text-generation", model="cfli/A-base")
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("cfli/A-base")
model = AutoModelForMultimodalLM.from_pretrained("cfli/A-base", device_map="auto")
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 cfli/A-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cfli/A-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cfli/A-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cfli/A-base

SGLang

How to use cfli/A-base 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 "cfli/A-base" \
    --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": "cfli/A-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "cfli/A-base" \
        --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": "cfli/A-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cfli/A-base with Docker Model Runner:
```
docker model run hf.co/cfli/A-base
```

cfli commited on about 12 hours ago

Commit

600ff57

verified ·

1 Parent(s): e7becd6

Add files using upload-large-folder tool

Browse files

Files changed (1) hide show

README.md +16 -2

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ tags:
 <div align="center">
   <img src="assets/arex-logo.png" width="40%" alt="AREX" style="display: block; margin: 0 auto -2px;">
   <div style="margin-bottom: 7px;"><strong>Towards a Recursively Self-Improving Agent for Deep Research</strong></div>
-  <a href="#"><img src="https://img.shields.io/badge/-Paper-B31B1B?style=for-the-badge&amp;logo=arxiv&amp;logoColor=white" alt="Paper"></a>
   <a href="https://vectorspacelab.github.io/arex-model/"><img src="https://img.shields.io/badge/-Homepage-24292F?style=for-the-badge&amp;logo=github&amp;logoColor=white" alt="Homepage"></a>
   <a href="https://arex-research.com/"><img src="https://img.shields.io/badge/-Live_Demo-0F766E?style=for-the-badge&amp;logo=googlechrome&amp;logoColor=white" alt="Live Demo"></a>
 </div>
@@ -151,7 +151,7 @@ AREX is evaluated through a unified long-horizon search-agent interface with `se
 </tr>
 </tbody>
 </table>
-<div style="font-size:12px;color:#6b7280;margin-top:8px;line-height:1.5">* Results reported on the full HLE. Unmarked HLE results use the text-only subset.</div>
 </div>
 ## Inference
@@ -165,3 +165,17 @@ AREX-Base is intended for research-agent applications that require long-horizon
 ## License
 AREX-Base is released under the [Apache License 2.0](LICENSE).

 <div align="center">
   <img src="assets/arex-logo.png" width="40%" alt="AREX" style="display: block; margin: 0 auto -2px;">
   <div style="margin-bottom: 7px;"><strong>Towards a Recursively Self-Improving Agent for Deep Research</strong></div>
+  <a href="https://arxiv.org/abs/2607.21461"><img src="https://img.shields.io/badge/-Paper-B31B1B?style=for-the-badge&amp;logo=arxiv&amp;logoColor=white" alt="Paper"></a>
   <a href="https://vectorspacelab.github.io/arex-model/"><img src="https://img.shields.io/badge/-Homepage-24292F?style=for-the-badge&amp;logo=github&amp;logoColor=white" alt="Homepage"></a>
   <a href="https://arex-research.com/"><img src="https://img.shields.io/badge/-Live_Demo-0F766E?style=for-the-badge&amp;logo=googlechrome&amp;logoColor=white" alt="Live Demo"></a>
 </div>
 </tr>
 </tbody>
 </table>
+<div style="font-size:12px;color:#6b7280;margin-top:6px;margin-bottom:-8px;line-height:1.5">* Results reported on the full HLE. Unmarked HLE results use the text-only subset.</div>
 </div>
 ## Inference
 ## License
 AREX-Base is released under the [Apache License 2.0](LICENSE).
+## Citation
+```bibtex
+@misc{lu2026arexrecursivelyselfimprovingagent,
+      title={AREX: Towards a Recursively Self-Improving Agent for Deep Research},
+      author={Shuqi Lu and Chaofan Li and Kun Luo and Zhang Zhang and Hui Wang and Hongwang Xiao and Zheng Liu and Lei Xiong and Jiahao Wang and Sen Wang and Xiyan Jiang and Wanli Li and Yuyang Hu and Hongjin Qian and Bingyu Yan and Ziyi Xia and Yingxia Shao and Kang Liu and Zhicheng Dou and Di He and Chaozhuo Li and Qiwei Ye and Zhongyuan Wang and Zheng Liu},
+      year={2026},
+      eprint={2607.21461},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2607.21461},
+}
+```