Instructions to use ChiPhan1110/ScaleReasoner-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChiPhan1110/ScaleReasoner-R1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ChiPhan1110/ScaleReasoner-R1")
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("ChiPhan1110/ScaleReasoner-R1")
model = AutoModelForMultimodalLM.from_pretrained("ChiPhan1110/ScaleReasoner-R1", 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 ChiPhan1110/ScaleReasoner-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChiPhan1110/ScaleReasoner-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChiPhan1110/ScaleReasoner-R1",
		"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/ChiPhan1110/ScaleReasoner-R1

SGLang

How to use ChiPhan1110/ScaleReasoner-R1 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 "ChiPhan1110/ScaleReasoner-R1" \
    --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": "ChiPhan1110/ScaleReasoner-R1",
		"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 "ChiPhan1110/ScaleReasoner-R1" \
        --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": "ChiPhan1110/ScaleReasoner-R1",
		"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 ChiPhan1110/ScaleReasoner-R1 with Docker Model Runner:
```
docker model run hf.co/ChiPhan1110/ScaleReasoner-R1
```

ChiPhan1110 commited on Jun 25

Commit

6464c39

verified ·

1 Parent(s): 9bc3c29

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -55,7 +55,7 @@ Naively constructed cross-scale VQA benchmarks suffer from **text-only shortcut
 | **Cross-scale MCQ Construction & Clinical Validation** | Final MCQs are reviewed by senior pathologists to confirm that correct answers are visually grounded and distractors are clinically plausible. |
 ### ScaleReasoner-R1: Cross-scale Reasoning via RL
-ScaleReasoner-R1 is initialized from **Patho-R1-7B** and fine-tuned with **GRPO** on Scale-VQA. Given a multi-scale image set $I = \{I^{10\times}, I^{40\times}, I^{200\times}\}$, a question, and options, the model generates a structured response with a reasoning trace (`<think>`) followed by a final answer (`<answer>`).
 **Training Dynamics:**

 | **Cross-scale MCQ Construction & Clinical Validation** | Final MCQs are reviewed by senior pathologists to confirm that correct answers are visually grounded and distractors are clinically plausible. |
 ### ScaleReasoner-R1: Cross-scale Reasoning via RL
+ScaleReasoner-R1 is initialized from **Patho-R1-7B** and fine-tuned with **GRPO** on Scale-VQA. Given a multi-scale image set I = {I_(10x), I_(40x), I_(200x)}, a question, and options, the model generates a structured response with a reasoning trace (`<think>`) followed by a final answer (`<answer>`).
 **Training Dynamics:**