Instructions to use hiko1999/Qwen2-Wildfire-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hiko1999/Qwen2-Wildfire-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="hiko1999/Qwen2-Wildfire-2B") 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("hiko1999/Qwen2-Wildfire-2B") model = AutoModelForMultimodalLM.from_pretrained("hiko1999/Qwen2-Wildfire-2B", 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 hiko1999/Qwen2-Wildfire-2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hiko1999/Qwen2-Wildfire-2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hiko1999/Qwen2-Wildfire-2B", "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/hiko1999/Qwen2-Wildfire-2B
- SGLang
How to use hiko1999/Qwen2-Wildfire-2B 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 "hiko1999/Qwen2-Wildfire-2B" \ --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": "hiko1999/Qwen2-Wildfire-2B", "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 "hiko1999/Qwen2-Wildfire-2B" \ --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": "hiko1999/Qwen2-Wildfire-2B", "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 hiko1999/Qwen2-Wildfire-2B with Docker Model Runner:
docker model run hf.co/hiko1999/Qwen2-Wildfire-2B
Qwen2-Wildfire-2B
ไธญๆ
Qwen2-Wildfire-2B ๆไพไบๅฏน้็ซ็ซ็พๅบๆฏ็ๆทฑๅบฆ่ฏๅซ๏ผๅฏไปฅๆไพๆฏๅ ถไปๆจกๅๆดๆทฑๅ ฅ็ๅบๆฏ็ป่ไฟกๆฏใ็ธ่พไบๅ ถไปๆทฑๅบฆๅญฆไน ๆจกๅ๏ผๅฎ่ฝๅคไธบๆถ้ฒๅทฅไฝๆไพๆดๅคๆๆ็ไฟกๆฏ๏ผไธ็ฑไบๆจกๅไฝ้ไธบ2B๏ผๅฐๆฅไนๅฏไปฅๆนไพฟๅฐๆญ่ฝฝๅฐ็งปๅจ่ฎพๅคไธใๆไปฌ็ๆจกๅ่ฝๅค่ฏๅซไปฅไธๅ ซๅคงๅ ณ้ฎ่ฆ็ด ๏ผ
- ็ซ็พ็ฑปๅไธ็ฏๅขๆ่ฟฐ
- ็ซ็ฐ็นๆง๏ผ้ข่ฒใ้ซๅบฆใๅผบๅบฆ๏ผ
- ็้พ็นๆง๏ผ้ข่ฒใๅฏๅบฆใๆฉๆฃๆนๅ๏ผ
- ็ซ่กไธบ๏ผไผ ๆญ้ๅบฆใ่ฟๅจๆจกๅผ๏ผ
- ๅๅฝฑๅๅบๅๆ่ฟฐ๏ผ็ซ็พ่ฆ็่ๅดใๆถๅ็ๆค่ขซๆ็ปๆ๏ผ
- ็ฐๅบๅบๅฏนๆชๆฝ๏ผๆถ้ฒๅใ่ฝฆ่พใ่ฎพๅค็ๅฏ่งๆง๏ผ
- ็ฏๅขๅ ็ด ๏ผๅจๅดๅฐๅฝขใ้ฃ้ใๆธฉๅบฆ๏ผ
- ๅพๅ่ดจ้๏ผๆๆๆถ้ดใ่งๅบฆใๅ่พจ็๏ผ
่ฎญ็ป็ๆฐๆฎ้็ฑ4135ๅผ ้ซ่ดจ้ๅพ็ๆๆ๏ผ็ป่ฟไบบๅทฅๆฃๆฅๅ่ฟ่กๆ ๆณจ๏ผๅนถ็จไบๅพฎ่ฐ Qwen ็ Qwen2-VL-2B-Instruct ๆจกๅ๏ผๅๅพไบๅพๅฅฝ็ๆๆใ
่ด่ฐขไธ่ฎธๅฏ่ฏดๆ
ๆ่ฐขๅคงๅฎถๅฏนๆฌๅพฎ่ฐๆจกๅ็ๆฏๆใไฝไธบๅผๆบๆจกๅ๏ผๆฌข่ฟๅคงๅฎถ่ช็ฑไฝฟ็จ๏ผไฝ่ฏทๅกๅฟ ๆณจๆๅบๅคใ็ธๅ ณ็ ็ฉถ่ฎบๆๅทฒๅจๅญฆๆฏไผ่ฎฎๅ่กจ๏ผๅนถๅ ฌๅผไบๅฎๆด็็ ็ฉถๆต็จๅๅฎ็ฐๆญฅ้ชคใ
English
Qwen2-Wildfire-2B provides deep recognition of wildfire scenarios, offering more detailed scene information than other models. Compared to other deep learning models, it can provide more effective information for firefighting work, and with its 2B size, it can be conveniently deployed on mobile devices in the future. Our model can recognize the following eight key elements:
- Fire type and environmental description
- Flame characteristics (color, height, intensity)
- Smoke characteristics (color, density, spread direction)
- Fire behavior (spread speed, movement pattern)
- Affected area description (fire coverage, vegetation or structures involved)
- On-site response measures (visibility of firefighters, vehicles, equipment)
- Environmental factors (surrounding terrain, wind speed, temperature)
- Image quality (capture time, angle, resolution)
The training dataset consists of 4,135 high-quality images, which were manually checked and labeled, and used to fine-tune Qwen's Qwen2-VL-2B-Instruct model, achieving excellent results.
Acknowledgments and License Notice
We appreciate everyone's support for this fine-tuned model. As an open-source model, you are welcome to use it freely, but please be sure to cite the source. The related research paper has been presented at academic conferences, and the complete research process and implementation steps have been made public.
ๆฅๆฌ่ช
Qwen2-Wildfire-2Bใฏใ้็ซ็ฝๅฎณใทใผใณใฎๆทฑใ่ช่ญใๆไพใใไปใฎใขใใซใใใ่ฉณ็ดฐใชใทใผใณๆ ๅ ฑใๆไพใใพใใไปใฎๆทฑๅฑคๅญฆ็ฟใขใใซใจๆฏ่ผใใฆใๆถ้ฒๆดปๅใซใใๅนๆ็ใชๆ ๅ ฑใๆไพใงใใ2Bใฎใตใคใบใซใใใๅฐๆฅ็ใซใขใใคใซใใใคในใธใฎๅฑ้ใๅฎนๆใงใใ็งใใกใฎใขใใซใฏไปฅไธใฎ8ใคใฎ้่ฆใช่ฆ็ด ใ่ช่ญใงใใพใ๏ผ
- ็ซ็ฝใฎ็จฎ้กใจ็ฐๅขใฎ่ชฌๆ
- ็ใฎ็นๆง๏ผ่ฒใ้ซใใๅผทๅบฆ๏ผ
- ็ ใฎ็นๆง๏ผ่ฒใๅฏๅบฆใๆกๆฃๆนๅ๏ผ
- ็ซใฎๆๅ๏ผไผๆญ้ๅบฆใ็งปๅใใฟใผใณ๏ผ
- ่ขซ็ฝๅฐๅใฎ่ชฌๆ๏ผ็ซ็ฝใฎ็ฏๅฒใๅฝฑ้ฟใๅใใๆค็ใๆง้ ็ฉ๏ผ
- ็พๅ ดๅฏพๅฟๆช็ฝฎ๏ผๆถ้ฒๅฃซใ่ปไธกใๆฉๅจใฎ่ฆ่ชๆง๏ผ
- ็ฐๅข่ฆๅ ๏ผๅจ่พบๅฐๅฝขใ้ขจ้ใๆฐๆธฉ๏ผ
- ็ปๅๅ่ณช๏ผๆฎๅฝฑๆ้ใ่งๅบฆใ่งฃๅๅบฆ๏ผ
ใใฌใผใใณใฐใใผใฟใปใใใฏ4,135ๆใฎ้ซๅ่ณช็ปๅใงๆงๆใใใๆๅใง็ขบ่ชใปใฉใใชใณใฐใใใQwenใฎQwen2-VL-2B-Instructใขใใซใฎๅพฎ่ชฟๆดใซไฝฟ็จใใใๅชใใ็ตๆใ้ๆใใพใใใ
่ฌ่พใจใฉใคใปใณใน่กจ็คบ
ใใฎๅพฎ่ชฟๆดใขใใซใธใฎใๆฏๆดใซๆ่ฌใใใใพใใใชใผใใณใฝใผในใขใใซใจใใฆใ่ช็ฑใซใๅฉ็จใใใ ใใพใใใๅฟ ใๅบๅ ธใๆ่จใใฆใใ ใใใ้ข้ฃ็ ็ฉถ่ซๆใฏๅญฆ่กไผ่ญฐใง็บ่กจใใใๅฎๅ จใช็ ็ฉถใใญใปในใจๅฎ่ฃ ๆ้ ใๅ ฌ้ใใใฆใใพใใ
- Downloads last month
- 29