Instructions to use InternScience/Sage-A1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InternScience/Sage-A1.5 with Transformers:

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

pipe = pipeline("text-generation", model="InternScience/Sage-A1.5")
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("InternScience/Sage-A1.5")
model = AutoModelForMultimodalLM.from_pretrained("InternScience/Sage-A1.5", 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 InternScience/Sage-A1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InternScience/Sage-A1.5"
# 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/Sage-A1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/InternScience/Sage-A1.5

SGLang

How to use InternScience/Sage-A1.5 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/Sage-A1.5" \
    --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/Sage-A1.5",
		"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/Sage-A1.5" \
        --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/Sage-A1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use InternScience/Sage-A1.5 with Docker Model Runner:
```
docker model run hf.co/InternScience/Sage-A1.5
```

If you don't include Qwen3.6-35B and Qwen3.8-27B benchmarks, people are going to auto skip this model

by pathosethoslogos - opened 7 days ago

Discussion

pathosethoslogos

7 days ago

First sentence says it's based on Qwen3.6, so compare it to that. And compare it to smaller yet more powerful (though slower) model, 3.8 27B where people can fit the model in similar size memory.

Everybody knows comparing it to Kimi K3, GLM 5.3, GPT 5.6 is just too much.

sY713

Intern Science org 7 days ago

First sentence says it's based on Qwen3.6, so compare it to that. And compare it to smaller yet more powerful (though slower) model, 3.8 27B where people can fit the model in similar size memory.

Everybody knows comparing it to Kimi K3, GLM 5.3, GPT 5.6 is just too much.

Thanks for the feedback! The Qwen-3.6-35B results have now been updated in the leaderboard table on the readme. Please refer to it.

mayankiit04

2 days ago

What is GPQA Diamond results?

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