Instructions to use InternScience/Agents-A1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InternScience/Agents-A1 with Transformers:

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

pipe = pipeline("text-generation", model="InternScience/Agents-A1")
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("InternScience/Agents-A1")
model = AutoModelForMultimodalLM.from_pretrained("InternScience/Agents-A1")
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 InternScience/Agents-A1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InternScience/Agents-A1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InternScience/Agents-A1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/InternScience/Agents-A1

SGLang

How to use InternScience/Agents-A1 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 "InternScience/Agents-A1" \
    --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": "InternScience/Agents-A1",
		"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 "InternScience/Agents-A1" \
        --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": "InternScience/Agents-A1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use InternScience/Agents-A1 with Docker Model Runner:
```
docker model run hf.co/InternScience/Agents-A1
```

Can't wait for Agents-A2!

#21

by sulaiymanfauzi - opened 10 days ago

Discussion

sulaiymanfauzi

10 days ago

Imagine continuing horizon scaling until it surpasses claude opus. Hopefully this is possible.

Basher17

9 days ago

yeah good luck with that. But I would love to see A2 based on Qwen 3.6 with MTP heads preserved, that would be a game changer for local agentic work.

BoZhang

Intern Science org 3 days ago

@Basher17 @sulaiymanfauzi Thank you for your attention and recognition. We have already released the 4B version of the model, and will soon release a series of agent models in different model sizes to meet the diverse needs of the community. Meanwhile, we will continue to iterate on multiple atomic abilities of our agent models. Please stay tuned for our upcoming work.

sulaiymanfauzi

3 days ago

•

edited 3 days ago

Can' t wait! This paradigm shift is a game changer for consumer-grade inference. The sweet spot for me is the Q4 variant at 130-150 tokens per second with RTX 5090.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment