Image-Text-to-Text
Transformers
Safetensors
English
Korean
qwen3_5_moe
vision-language-model
medical-imaging
brain-ct
stroke
region-classification
lora
conversational
Instructions to use JLKGroup/JOOMED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JLKGroup/JOOMED with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="JLKGroup/JOOMED") 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("JLKGroup/JOOMED") model = AutoModelForMultimodalLM.from_pretrained("JLKGroup/JOOMED") 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 JLKGroup/JOOMED with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JLKGroup/JOOMED" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JLKGroup/JOOMED", "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/JLKGroup/JOOMED
- SGLang
How to use JLKGroup/JOOMED 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 "JLKGroup/JOOMED" \ --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": "JLKGroup/JOOMED", "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 "JLKGroup/JOOMED" \ --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": "JLKGroup/JOOMED", "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 JLKGroup/JOOMED with Docker Model Runner:
docker model run hf.co/JLKGroup/JOOMED
| license: apache-2.0 | |
| base_model: Qwen/Qwen3.6-35B-A3B | |
| pipeline_tag: image-text-to-text | |
| library_name: transformers | |
| tags: | |
| - vision-language-model | |
| - medical-imaging | |
| - brain-ct | |
| - stroke | |
| - region-classification | |
| - lora | |
| language: | |
| - en | |
| - ko | |
| <div align="center"> | |
| # JOOMED ยท Brain-CT Lesion Region Classifier | |
| **Qwen3.6-35B-A3B**(MoE Vision-Language Model)์ LoRA๋ก ํ์ธํ๋ํ ๋์กธ์ค ํนํ ์์ญ ๋ถ๋ฅ ๋ชจ๋ธ | |
| [](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) | |
| [](./LICENSE) | |
| [](#) | |
| </div> | |
| --- | |
| CT summary ์์์์ ๋ณ๋ณ์ด ์์นํ **ํด๋ถํ์ ์์ญ(anatomical)** ๊ณผ **ํ๊ด ์ง๋ฐฐ ์์ญ(vascular)** ์ | |
| ์ข์ฐ(L/R) ๊ตฌ๋ถ๊ณผ ํจ๊ป ๋ถ๋ฅํ์ฌ **๊ตฌ์กฐํ JSON** ์ผ๋ก ์ถ๋ ฅํฉ๋๋ค. | |
| ```json | |
| {"anatomical_regions": ["basal_ganglia_thalamus_right"], | |
| "vascular_territories": ["MCA_right", "PCA_right"]} | |
| ``` | |
| ## ๋ชจ๋ธ ๊ฐ์ | |
| | | | | |
| |---|---| | |
| | **Base model** | `Qwen/Qwen3.6-35B-A3B` โ MoE VLM, 35B total / ~3B active (`qwen3_5_moe`) | | |
| | **Adaptation** | LoRA (r=8, ฮฑ=16, attention `q/k/v/o_proj`) โ ๋ฒ ์ด์ค์ **๋ณํฉ๋ ํ๋ชจ๋ธ** | | |
| | **Input โ Output** | PNG (CT summary) โ ์์ญ๋ถ๋ฅ JSON | | |
| | **Label space** | anatomical 23๊ทธ๋ฃน ยท vascular 14๊ทธ๋ฃน (coarse, ์ข์ฐ ์ ์ง) | | |
| | **Project** | RQT-25-090047 โ ๋ค์ค ๋ชจ๋ฌ AI ๋์กธ์ค ์์์ง์ LLM (ใ์ ์ด์์ผ์ด) | | |
| ## ์ฑ๋ฅ | |
| ์์ญ ์ถ์ถ ์ ํ๋ (set ๊ธฐ๋ฐ per-sample F1, macro ํ๊ท ): | |
| | ํ๊ฐ์ | n | Anatomical F1 | Vascular F1 | ํ๊ท | | |
| |---|---:|---:|---:|---:| | |
| | ์ ์ฒด test | 12,140 | **0.741** | **0.802** | **0.771** | | |
| ๋ฌดํ์ธํ๋ Base(0.29 / 0.30) ๋๋น **2.5๋ฐฐ ์ด์** ํฅ์. ๊ฐ์ ์ ํต์ฌ์ recall ์์น | |
| (anatomical +0.17, vascular +0.13)์ผ๋ก, ๋๋ฝ ๋ณ๋ณ์ด ํฌ๊ฒ ๊ฐ์ํ์ต๋๋ค. | |
| <details> | |
| <summary>๋ณด์กฐ ํ ์คํธ ์งํ (์์ญ ๋ผ๋ฒจ์ ํ ์คํธ๋ก ์ง๋ ฌํํด ์ธก์ ยท ํ๋ ๋ฌธ ํ์ง ์๋)</summary> | |
| | BLEU-1 | METEOR | BERTScore F1 | G-Eval | | |
| |---:|---:|---:|---:| | |
| | 0.798 | 0.794 | 0.952 | 3.68 | | |
| > ์ถ๋ ฅ์ด ์งง์ ๋ผ๋ฒจ ๋ฌธ์ฅ์ด๋ผ ์์ ํ ์คํธ ํ๋ ๋ฌธ ์งํ์ ์ธก์ ๋์์ด ๋ค๋ฆ ๋๋ค. ๋น๊ต ์ ์ฃผ์. | |
| </details> | |
| ## ์ฌ์ฉ๋ฒ | |
| ```python | |
| from transformers import AutoModelForImageTextToText, AutoProcessor | |
| from PIL import Image | |
| model_id = "JLKGroup/JOOMED" | |
| model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") | |
| processor = AutoProcessor.from_pretrained(model_id) | |
| img = Image.open("ct_summary.png").convert("RGB") | |
| prompt = "์ฃผ์ด์ง CT summary ์ด๋ฏธ์ง์์ ๋ณ๋ณ์ด ์ํ๋ anatomical region๊ณผ vascular territory๋ฅผ JSON์ผ๋ก ๋ตํ๋ผ." | |
| messages = [{"role": "user", "content": [{"type": "image", "image": img}, {"type": "text", "text": prompt}]}] | |
| text = processor.apply_chat_template( | |
| messages, tokenize=False, add_generation_prompt=True, enable_thinking=False # ํ์ต ํ ํ๋ฆฟ๊ณผ ์ผ์น | |
| ) | |
| inputs = processor(text=[text], images=[img], return_tensors="pt").to(model.device) | |
| out = model.generate(**inputs, max_new_tokens=256, do_sample=False) | |
| print(processor.tokenizer.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)) | |
| ``` | |
| > **Tip** โ ์ถ๋ก ์ ๋ฐ๋์ `enable_thinking=False` ๋ก ๋์ด์ผ ํ์ต ์ ํ ํ๋ฆฟ๊ณผ ์ผ์นํฉ๋๋ค. | |
| ## ๋ผ๋ฒจ ์ฒด๊ณ | |
| | ์ถ | ๊ทธ๋ฃน | | |
| |---|---| | |
| | Anatomical (รL/R) | frontal ยท parietal ยท temporal ยท occipital ยท insula ยท limbic ยท basal_ganglia_thalamus ยท cerebellum ยท brainstem ยท ventricle ยท white_matter_other | | |
| | Vascular (รL/R) | ACA ยท MCA ยท PCA ยท basilar ยท cerebellar ยท anterior_choroidal ยท lateral_ventricle | | |
| ## ํ๊ณ ๋ฐ ์ฃผ์ | |
| - **์๋ฃ ์ฐ๊ตฌ์ฉ ๋ชจ๋ธ**์ ๋๋ค. ์์ ์์ฌ๊ฒฐ์ ์ ๋จ๋ ๊ทผ๊ฑฐ๋ก ์ฌ์ฉํ์ง ๋ง์ญ์์ค. | |
| ## ๋ผ์ด์ ์ค | |
| ๋ฒ ์ด์ค ๋ชจ๋ธ `Qwen3.6-35B-A3B`์ Apache-2.0๋ฅผ ๋ฐ๋ฆ ๋๋ค. | |