Instructions to use shanyangmie/physics-r1-seed23 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shanyangmie/physics-r1-seed23 with Transformers:

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

pipe = pipeline("image-text-to-text", model="shanyangmie/physics-r1-seed23")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("shanyangmie/physics-r1-seed23")
model = AutoModelForImageTextToText.from_pretrained("shanyangmie/physics-r1-seed23")
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

vLLM

How to use shanyangmie/physics-r1-seed23 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shanyangmie/physics-r1-seed23"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shanyangmie/physics-r1-seed23",
		"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/shanyangmie/physics-r1-seed23

SGLang

How to use shanyangmie/physics-r1-seed23 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 "shanyangmie/physics-r1-seed23" \
    --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": "shanyangmie/physics-r1-seed23",
		"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 "shanyangmie/physics-r1-seed23" \
        --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": "shanyangmie/physics-r1-seed23",
		"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 shanyangmie/physics-r1-seed23 with Docker Model Runner:
```
docker model run hf.co/shanyangmie/physics-r1-seed23
```

Physics-R1 — Seed 23 (HF safetensors)

Project Page | Paper | Code | Training corpus

The Physics-R1 paper checkpoint for the seed-23 row of Table 2 (canonical step 60). Fine-tune of Qwen3-VL-8B-Thinking on the audited PhysR1Corp (2,268 closed-form physics problems) via full-parameter FSDP1 GRPO with binary correctness reward.

This seed has the highest individual PhysOlym-A score (28.2) among the paper's three seeds.

This is the easy-to-use HF safetensors release. For the original verl FSDP-sharded archive, see physics-r1-seed23-canonical-step60-fsdp.

Quickstart

from transformers import AutoModelForImageTextToText, AutoProcessor
import torch

model = AutoModelForImageTextToText.from_pretrained(
    "shanyangmie/physics-r1-seed23",
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(
    "shanyangmie/physics-r1-seed23",
    trust_remote_code=True,
)

For evaluation against the paper's benchmark, see PhysOlym-A and the code release.

Performance (paper Table 2, seed-23 row)

Eval	Physics-R1 (this checkpoint)	Base Qwen3-VL-8B-Thinking	Δ
PhyX-mini	77.9	73.7	+4.2
PhyX-3k	76.6	74.4	+2.2
PhysReason	43.4	23.9	+19.5
PUB-OE	30.9	35.3	-4.4
OlympiadBench-Physics	48.0	39.3	+8.7
PhysOlym-A	28.2	8.0	+20.2

Scoring: problem-level liberal Sonnet-as-judge (every subpart of a multi-part problem must be correct). The 3-seed mean across {42, 17, 23} is the paper's headline (+18.9 pp on PhysOlym-A).

Other seeds (HF safetensors mirrors)

Seed	HF safetensors mirror	FSDP archive
42	`shanyangmie/physics-r1-seed42-v4-step60`	`...-seed42-v4-step60-fsdp`
17	`shanyangmie/physics-r1-seed17`	`...-seed17-canonical-step63-fsdp`
23	this card	`...-seed23-canonical-step60-fsdp`

Training recipe

Base model: Qwen/Qwen3-VL-8B-Thinking
Algorithm: GRPO (verl 0.6.1, full-parameter FSDP1 — actor.strategy=fsdp, not fsdp2)
Reward: binary correctness, per-subpart Sonnet judge with problem-level AND aggregation (see paper §3.2)
Data: shanyangmie/physr1corp — 2,268 audited closed-form problems
Seed / step: 23 / 60
Hardware: 4×H200 (FSDP1 4-way sharded)

Full hyperparameters in paper Appendix.

License

Apache 2.0, inheriting from the base model Qwen3-VL-8B-Thinking. Training data (physr1corp) is CC BY-NC 4.0, so this derivative checkpoint is intended for non-commercial research use.

Citation

@misc{yang2026physicsr1,
  title  = {Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning},
  author = {Yang, Shan},
  year   = {2026},
  url    = {https://huggingface.co/papers/2605.14040}
}

Downloads last month: 29

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for shanyangmie/physics-r1-seed23

Base model

Qwen/Qwen3-VL-8B-Thinking

Finetuned

(60)

this model

Paper for shanyangmie/physics-r1-seed23

Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning

Paper • 2605.14040 • Published 8 days ago • 2