Instructions to use cfli/AREX-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cfli/AREX-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="cfli/AREX-2")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("cfli/AREX-2")
model = AutoModelForMultimodalLM.from_pretrained("cfli/AREX-2", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cfli/AREX-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cfli/AREX-2"
# 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/AREX-2",
		"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/cfli/AREX-2

SGLang

How to use cfli/AREX-2 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/AREX-2" \
    --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/AREX-2",
		"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 "cfli/AREX-2" \
        --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/AREX-2",
		"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 cfli/AREX-2 with Docker Model Runner:
```
docker model run hf.co/cfli/AREX-2
```

cfli commited on 21 days ago

Commit

40dd1d6

verified ·

1 Parent(s): bd2b553

Add files using upload-large-folder tool

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -57,8 +57,8 @@ reported in the AREX-2 paper.
 ### Coding and machine-learning engineering
-<div style="overflow-x:auto">
-<table cellpadding="7" style="width:100%;border-collapse:collapse;font-size:13px;white-space:nowrap">
 <thead>
 <tr style="color:#0F766E;border-bottom:2px solid #0F766E">
 <th style="padding:8px;text-align:left">Model</th>
@@ -95,8 +95,8 @@ AREX team. MLE-Lite reports Any Medal averaged over three seeds.
 ### General agentic reasoning and deep research
-<div style="overflow-x:auto">
-<table cellpadding="7" style="width:100%;border-collapse:collapse;font-size:13px;white-space:nowrap">
 <thead>
 <tr style="color:#0F766E;border-bottom:2px solid #0F766E">
 <th style="padding:8px;text-align:left">Model</th>
@@ -126,7 +126,7 @@ AREX team. MLE-Lite reports Any Medal averaged over three seeds.
 <tr><td>MiroThinker-1.7</td><td style="text-align:center">235B</td><td style="text-align:center">74.0</td><td style="text-align:center">42.9</td><td style="text-align:center">82.7</td><td style="text-align:center">72.1</td></tr>
 <tr><td>XYZ-Aquila-pro</td><td style="text-align:center">397B</td><td style="text-align:center">84.8</td><td style="text-align:center">53.3</td><td style="text-align:center">-</td><td style="text-align:center">92.5</td></tr>
 <tr><td>Iris-pro</td><td style="text-align:center">397B</td><td style="text-align:center">88.6</td><td style="text-align:center">56.4</td><td style="text-align:center">-</td><td style="text-align:center">92.9</td></tr>
-<tr style="background:rgba(15,118,110,.05);font-weight:600;color:#0F766E"><td>AREX-Base</td><td style="text-align:center">122B</td><td style="text-align:center">82.5</td><td style="text-align:center">52.4</td><td style="text-align:center">85.4</td><td style="text-align:center">89.9</td></tr>
 <tr><td colspan="6" style="padding:8px 10px;font-weight:600;color:#0F766E;background:rgba(15,118,110,.1)">Small models (&le;40B)</td></tr>
 <tr><td>Tongyi-DeepResearch-30B</td><td style="text-align:center">30B</td><td style="text-align:center">43.4</td><td style="text-align:center">32.9</td><td style="text-align:center">70.9</td><td style="text-align:center">-</td></tr>
 <tr><td>Qwen3.5-35B</td><td style="text-align:center">35B</td><td style="text-align:center">61.0</td><td style="text-align:center">47.4</td><td style="text-align:center">80.0</td><td style="text-align:center">68.5</td></tr>
@@ -137,7 +137,7 @@ AREX team. MLE-Lite reports Any Medal averaged over three seeds.
 <tr><td>Agents-A1</td><td style="text-align:center">35B</td><td style="text-align:center">75.5</td><td style="text-align:center">47.6</td><td style="text-align:center">96.0</td><td style="text-align:center">-</td></tr>
 <tr><td>MiroThinker-1.7-mini</td><td style="text-align:center">30B</td><td style="text-align:center">67.9</td><td style="text-align:center">36.4</td><td style="text-align:center">80.3</td><td style="text-align:center">67.9</td></tr>
 <tr><td>Iris-mini</td><td style="text-align:center">35B</td><td style="text-align:center">82.2</td><td style="text-align:center">52.3</td><td style="text-align:center">-</td><td style="text-align:center">86.9</td></tr>
-<tr style="background:rgba(15,118,110,.05);font-weight:600;color:#0F766E"><td>AREX-Turbo</td><td style="text-align:center">4B</td><td style="text-align:center">70.7</td><td style="text-align:center">40.6</td><td style="text-align:center">81.6</td><td style="text-align:center">78.5</td></tr>
 <tr style="background:rgba(15,118,110,.12);font-weight:700;color:#0F766E"><td>AREX-2</td><td style="text-align:center">27B</td><td style="text-align:center">84.0</td><td style="text-align:center">52.6</td><td style="text-align:center">92.2</td><td style="text-align:center">93.8</td></tr>
 </tbody>
 </table>

 ### Coding and machine-learning engineering
+<div style="overflow-x:auto;max-width:100%">
+<table cellpadding="7" style="width:100%;border-collapse:collapse;font-size:13px;table-layout:auto">
 <thead>
 <tr style="color:#0F766E;border-bottom:2px solid #0F766E">
 <th style="padding:8px;text-align:left">Model</th>
 ### General agentic reasoning and deep research
+<div style="overflow-x:auto;max-width:100%">
+<table cellpadding="7" style="width:100%;border-collapse:collapse;font-size:13px;table-layout:auto">
 <thead>
 <tr style="color:#0F766E;border-bottom:2px solid #0F766E">
 <th style="padding:8px;text-align:left">Model</th>
 <tr><td>MiroThinker-1.7</td><td style="text-align:center">235B</td><td style="text-align:center">74.0</td><td style="text-align:center">42.9</td><td style="text-align:center">82.7</td><td style="text-align:center">72.1</td></tr>
 <tr><td>XYZ-Aquila-pro</td><td style="text-align:center">397B</td><td style="text-align:center">84.8</td><td style="text-align:center">53.3</td><td style="text-align:center">-</td><td style="text-align:center">92.5</td></tr>
 <tr><td>Iris-pro</td><td style="text-align:center">397B</td><td style="text-align:center">88.6</td><td style="text-align:center">56.4</td><td style="text-align:center">-</td><td style="text-align:center">92.9</td></tr>
+<tr><td>AREX-Base</td><td style="text-align:center">122B</td><td style="text-align:center">82.5</td><td style="text-align:center">52.4</td><td style="text-align:center">85.4</td><td style="text-align:center">89.9</td></tr>
 <tr><td colspan="6" style="padding:8px 10px;font-weight:600;color:#0F766E;background:rgba(15,118,110,.1)">Small models (&le;40B)</td></tr>
 <tr><td>Tongyi-DeepResearch-30B</td><td style="text-align:center">30B</td><td style="text-align:center">43.4</td><td style="text-align:center">32.9</td><td style="text-align:center">70.9</td><td style="text-align:center">-</td></tr>
 <tr><td>Qwen3.5-35B</td><td style="text-align:center">35B</td><td style="text-align:center">61.0</td><td style="text-align:center">47.4</td><td style="text-align:center">80.0</td><td style="text-align:center">68.5</td></tr>
 <tr><td>Agents-A1</td><td style="text-align:center">35B</td><td style="text-align:center">75.5</td><td style="text-align:center">47.6</td><td style="text-align:center">96.0</td><td style="text-align:center">-</td></tr>
 <tr><td>MiroThinker-1.7-mini</td><td style="text-align:center">30B</td><td style="text-align:center">67.9</td><td style="text-align:center">36.4</td><td style="text-align:center">80.3</td><td style="text-align:center">67.9</td></tr>
 <tr><td>Iris-mini</td><td style="text-align:center">35B</td><td style="text-align:center">82.2</td><td style="text-align:center">52.3</td><td style="text-align:center">-</td><td style="text-align:center">86.9</td></tr>
+<tr><td>AREX-Turbo</td><td style="text-align:center">4B</td><td style="text-align:center">70.7</td><td style="text-align:center">40.6</td><td style="text-align:center">81.6</td><td style="text-align:center">78.5</td></tr>
 <tr style="background:rgba(15,118,110,.12);font-weight:700;color:#0F766E"><td>AREX-2</td><td style="text-align:center">27B</td><td style="text-align:center">84.0</td><td style="text-align:center">52.6</td><td style="text-align:center">92.2</td><td style="text-align:center">93.8</td></tr>
 </tbody>
 </table>