Instructions to use nova819/sole-r1-v3-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nova819/sole-r1-v3-sft with Transformers:

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

pipe = pipeline("image-text-to-text", model="nova819/sole-r1-v3-sft")
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("nova819/sole-r1-v3-sft")
model = AutoModelForMultimodalLM.from_pretrained("nova819/sole-r1-v3-sft", 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 nova819/sole-r1-v3-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nova819/sole-r1-v3-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nova819/sole-r1-v3-sft",
		"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/nova819/sole-r1-v3-sft

SGLang

How to use nova819/sole-r1-v3-sft 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 "nova819/sole-r1-v3-sft" \
    --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": "nova819/sole-r1-v3-sft",
		"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 "nova819/sole-r1-v3-sft" \
        --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": "nova819/sole-r1-v3-sft",
		"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 nova819/sole-r1-v3-sft with Docker Model Runner:
```
docker model run hf.co/nova819/sole-r1-v3-sft
```

sole-r1-v3-sft

本项目的LIBERO Spatial任务进度推理模型，非官方SOLE-R1权重。预测百分比及CoT；不是动作策略。

完整模型权重、tokenizer和processor已保留。推理建议使用BF16；本次未转换源权重精度，v3存储为BF16，v7为FP32。可用 Transformers 4.57.3 的 Qwen3VLForConditionalGeneration 和 AutoProcessor 加载。准确的图像角色与输入prompt须遵循对应数据中的训练协议，不能只输入任意一张图片。

v3 SFT最终模型；基础模型为Qwen3-VL-8B-Instruct，没有使用官方SOLE-R1最终权重初始化。

数据与模型可能包含视觉识别、CoT或进度误差；工程跑通不等于RL收益已得到证明。上游基础模型：Qwen3-VL-8B-Instruct。

Downloads last month: 10

Safetensors

Model size

770k params

Tensor type

BF16

Model tree for nova819/sole-r1-v3-sft

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(710)

this model

nova819
/

sole-r1-v3-sft

sole-r1-v3-sft

Model tree for nova819/sole-r1-v3-sft

Dataset used to train nova819/sole-r1-v3-sft