Instructions to use ai-mind-lab/CineMR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai-mind-lab/CineMR with Transformers:

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

pipe = pipeline("image-text-to-text", model="ai-mind-lab/CineMR")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ai-mind-lab/CineMR")
model = AutoModelForMultimodalLM.from_pretrained("ai-mind-lab/CineMR", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ai-mind-lab/CineMR with vLLM:

Install from pip and serve model

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

SGLang

How to use ai-mind-lab/CineMR 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 "ai-mind-lab/CineMR" \
    --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": "ai-mind-lab/CineMR",
		"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 "ai-mind-lab/CineMR" \
        --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": "ai-mind-lab/CineMR",
		"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 ai-mind-lab/CineMR with Docker Model Runner:
```
docker model run hf.co/ai-mind-lab/CineMR
```

viennh2012 commited on Aug 19

Commit

93deb31

verified ·

1 Parent(s): 09d3184

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -139,10 +139,8 @@ Evaluated on the **CineMR held-out test split** (n=3,320; distinct from the 1,19
 | Mean rollout accuracy | 39.24% ± 0.09pp |
 | pass@4 (any correct) | 55.98% |
 | Ground-truth satisfied (pass@1) | 38.83% |
-| ROUGE-L$^\dagger$ | 0.620 |
-| BERTScore F1$^\dagger$ | 0.974 |
-$^\dagger$ROUGE-L and BERTScore F1 have not been re-measured on this checkpoint; these two figures carry over from the original submission's checkpoint.
 **Accuracy by reasoning layer (mean rollout acc):** L1 10.87%, L2 73.22%, L3 66.90%, L4 55.84%, L5 11.46%, L6 37.25%. By clinical stage: L3–4 (clinical-criteria) 65.30% ± 0.66pp, L5–6 (full-diagnosis) 17.02% ± 1.41pp.

 | Mean rollout accuracy | 39.24% ± 0.09pp |
 | pass@4 (any correct) | 55.98% |
 | Ground-truth satisfied (pass@1) | 38.83% |
+| ROUGE-L | 0.620 |
+| BERTScore F1 | 0.974 |
 **Accuracy by reasoning layer (mean rollout acc):** L1 10.87%, L2 73.22%, L3 66.90%, L4 55.84%, L5 11.46%, L6 37.25%. By clinical stage: L3–4 (clinical-criteria) 65.30% ± 0.66pp, L5–6 (full-diagnosis) 17.02% ± 1.41pp.