Instructions to use AllSpark-Research/Iris-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AllSpark-Research/Iris-mini with Transformers:

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

pipe = pipeline("text-generation", model="AllSpark-Research/Iris-mini")
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("AllSpark-Research/Iris-mini")
model = AutoModelForMultimodalLM.from_pretrained("AllSpark-Research/Iris-mini", 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 AllSpark-Research/Iris-mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AllSpark-Research/Iris-mini

SGLang

How to use AllSpark-Research/Iris-mini 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 "AllSpark-Research/Iris-mini" \
    --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": "AllSpark-Research/Iris-mini",
		"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 "AllSpark-Research/Iris-mini" \
        --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": "AllSpark-Research/Iris-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AllSpark-Research/Iris-mini with Docker Model Runner:
```
docker model run hf.co/AllSpark-Research/Iris-mini
```

nielsr HF Staff commited on 2 days ago

Commit

92f1a08

verified ·

1 Parent(s): 1ec3716

Add paper link to model card

Browse files

Adds a link to the Hugging Face paper page for *Iris: Climbing to the Search Frontier* in the model card banner so readers can directly access the paper. Existing metadata is already appropriate; no other changes are made.

Files changed (1) hide show

README.md +9 -8

README.md CHANGED Viewed

@@ -1,14 +1,14 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen3.6-35B-A3B
-pipeline_tag: text-generation
 library_name: transformers
 tags:
-  - search-agent
-  - deep-research
-  - agentic
-  - qwen3.6
-  - moe
 ---
 <h1 align="center">Iris-mini</h1>
@@ -17,6 +17,7 @@ tags:
 <p align="center">
   🤗 <a href="https://huggingface.co/collections/AllSpark-Research/iris"><b>Collection</b></a> &nbsp;|&nbsp;
   💻 <a href="https://github.com/AllSpark-Research/Iris"><b>GitHub</b></a> &nbsp;|&nbsp;
   🔬 <a href="https://github.com/AllSpark-Research/Iris/tree/main/Iris-Harness"><b>Evaluation Harness</b></a>
 </p>
@@ -107,4 +108,4 @@ harness's `iris-mini` config sets this up for you.
 ## License
-Apache 2.0.

 ---
 base_model: Qwen/Qwen3.6-35B-A3B
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
+- search-agent
+- deep-research
+- agentic
+- qwen3.6
+- moe
 ---
 <h1 align="center">Iris-mini</h1>
 <p align="center">
   🤗 <a href="https://huggingface.co/collections/AllSpark-Research/iris"><b>Collection</b></a> &nbsp;|&nbsp;
+  📄 <a href="https://huggingface.co/papers/2609.04304"><b>Paper</b></a> &nbsp;|&nbsp;
   💻 <a href="https://github.com/AllSpark-Research/Iris"><b>GitHub</b></a> &nbsp;|&nbsp;
   🔬 <a href="https://github.com/AllSpark-Research/Iris/tree/main/Iris-Harness"><b>Evaluation Harness</b></a>
 </p>
 ## License
+Apache 2.0.