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 5 days ago

Commit

8651f5a

verified ·

1 Parent(s): f407c3f

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -38,11 +38,11 @@ The progress estimate is intended to serve as a dense reward signal for robotic
 ## Quick Start
-The recommended interface for inference is [RoboReason](https://github.com/Philip-MIT/roboreason):
-    # pip install -U roboreason
-    import roboreason as rr
     video_paths = [
         "test_videos/robosuite/lift/unsuccessful/robosuite_lift_episode_12_unsuccessful_max_reward_38.mp4"
@@ -50,7 +50,7 @@ The recommended interface for inference is [RoboReason](https://github.com/Phili
     task_description = "Pick up the cube from the table."
-    rewards, reasoning_traces = rr.generate(
         model="SOLE-R1",
         task_description=task_description,
         video_paths=video_paths,
@@ -62,7 +62,7 @@ The recommended interface for inference is [RoboReason](https://github.com/Phili
     # 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],
@@ -76,7 +76,7 @@ The recommended interface for inference is [RoboReason](https://github.com/Phili
 Optional pre-download:
-    from roboreason.utils.model_utils import get_model_dir
     get_model_dir("sole-r1")

 ## Quick Start
+The recommended interface for inference is [RewardGen](https://github.com/Philip-MIT/rewardgen):
+    # pip install -U rewardgen
+    from rewardgen import generate, video_plot
     video_paths = [
         "test_videos/robosuite/lift/unsuccessful/robosuite_lift_episode_12_unsuccessful_max_reward_38.mp4"
     task_description = "Pick up the cube from the table."
+    rewards, reasoning_traces = generate(
         model="SOLE-R1",
         task_description=task_description,
         video_paths=video_paths,
     # Plotting with show_reasoning_traces=True
     output_sole = {"model": "SOLE-R1", "rewards": rewards[0], "reasoning_traces": reasoning_traces[0]}
+    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],
 Optional pre-download:
+    from rewardgen.utils.model_utils import get_model_dir
     get_model_dir("sole-r1")