Instructions to use Philip-MIT/SOLE-R1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Philip-MIT/SOLE-R1-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Philip-MIT/SOLE-R1-8B")
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("Philip-MIT/SOLE-R1-8B")
model = AutoModelForImageTextToText.from_pretrained("Philip-MIT/SOLE-R1-8B")
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 Philip-MIT/SOLE-R1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Philip-MIT/SOLE-R1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Philip-MIT/SOLE-R1-8B",
		"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/Philip-MIT/SOLE-R1-8B

SGLang

How to use Philip-MIT/SOLE-R1-8B 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 "Philip-MIT/SOLE-R1-8B" \
    --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": "Philip-MIT/SOLE-R1-8B",
		"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 "Philip-MIT/SOLE-R1-8B" \
        --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": "Philip-MIT/SOLE-R1-8B",
		"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 Philip-MIT/SOLE-R1-8B with Docker Model Runner:
```
docker model run hf.co/Philip-MIT/SOLE-R1-8B
```

Philip-MIT commited on 2 days ago

Commit

f407c3f

verified ·

1 Parent(s): 179a97a

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ This model accompanies the paper **“SOLE-R1: Video-Language Reasoning as the S
 ## Model Description
-SOLE-R1 predicts robot task progress from visual observations. Given an image or video-frame montage containing the first, previous, and current timestep views, plus a task description and prior progress value, the model outputs a reasoning trace and a scalar progress estimate.
 Expected output format:
@@ -35,17 +35,6 @@ Expected output format:
 The progress estimate is intended to serve as a dense reward signal for robotic reinforcement learning, especially when manually engineered rewards are unavailable.
-## Intended Use
-SOLE-R1-8B is intended for:
-- Robotics reward prediction
-- Online robot RL reward generation
-- Evaluating task progress from robot videos
-- Interpretable video-language reasoning for manipulation tasks
-- Research on learned reward models and robotic foundation models
-It is not intended as a general-purpose safety-critical robotics controller. The model should be validated in the target environment before use in closed-loop robotic systems.
 ## Quick Start
@@ -68,9 +57,20 @@ The recommended interface for inference is [RoboReason](https://github.com/Phili
         view_type_per_video=["external and wrist"],
         verbose=False,
     )
-print(rewards)
-print(reasoning_traces)

 ## Model Description
+SOLE-R1 predicts robot task progress from visual observations. Given a video and a task description, the model outputs a reasoning trace and a scalar progress estimate.
 Expected output format:
 The progress estimate is intended to serve as a dense reward signal for robotic reinforcement learning, especially when manually engineered rewards are unavailable.
 ## Quick Start
         view_type_per_video=["external and wrist"],
         verbose=False,
     )
+    print(rewards)
+    print(reasoning_traces)
+    # Plotting with show_reasoning_traces=True
+    output_sole = {"model": "SOLE-R1", "rewards": rewards[0], "reasoning_traces": reasoning_traces[0]}
+    rr.video_plot(
+        outputs=[output_sole],
+        plot_save_path='model_outputs/sole-r1/robosuite/lift/unsuccessful/robosuite_lift_episode_12_unsuccessful_max_reward_38.mp4',
+        video_path=video_paths[0],
+        show_reasoning_traces=True,
+        task_description=task_description,
+        verbose=False
+    )