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
```

Add evaluation results

by SaylorTwift HF Staff - opened about 12 hours ago

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

-0

SaylorTwift

about 12 hours ago

Hugging Face CLI

No description provided.

Add evaluation resultsf8e2dae0

SaylorTwift

about 12 hours ago

Hugging Face CLI

Add Evaluation Results for InternScience/Agents-A1

Summary

This PR adds evaluation results extracted from the Agents-A1 model card benchmark table to the .eval_results/ directory, following the Hugging Face Hub evaluation-results specification.

Benchmarks Added

Benchmark	Score	Hub Dataset	Task ID
HLE w/ tools	47.6	`cais/hle`	`hle`

Benchmarks Skipped (Not Registered on Hub)

Benchmark	Score
BrowseComp	75.51
XBench-DS-2510	86.0
Seal0	56.36
GAIA	96.04
SciCode	44.33
MLE-Lite	43.94
HiPhO	46.4
FrontierScience-Olympiad	79.0
FrontierScience-Research	40.0
IFBench	80.61
LongBench-v2	60.2
IFEval	94.82
τ²-Bench	79.81
VitaBench	38.75
MatTools	47.1
MolBench-bind	56.8

These can be added once the benchmark authors register their eval.yaml on the Hub.

Source

Model card: https://huggingface.co/InternScience/Agents-A1
Technical Report: https://arxiv.org/abs/2606.30616

Files Added

.eval_results/Agents-A1.yaml

Verification

These results were extracted from the official benchmark table published in the Agents-A1 model card. No verified token is provided as these were not run via HF Jobs with inspect-ai.

BoZhang changed pull request status to merged about 1 hour ago

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