Instructions to use cipherxsnier/ocean-blue-blue3-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cipherxsnier/ocean-blue-blue3-vision with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="cipherxsnier/ocean-blue-blue3-vision") 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("cipherxsnier/ocean-blue-blue3-vision") model = AutoModelForMultimodalLM.from_pretrained("cipherxsnier/ocean-blue-blue3-vision", 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 cipherxsnier/ocean-blue-blue3-vision with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cipherxsnier/ocean-blue-blue3-vision" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cipherxsnier/ocean-blue-blue3-vision", "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/cipherxsnier/ocean-blue-blue3-vision
- SGLang
How to use cipherxsnier/ocean-blue-blue3-vision 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 "cipherxsnier/ocean-blue-blue3-vision" \ --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": "cipherxsnier/ocean-blue-blue3-vision", "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 "cipherxsnier/ocean-blue-blue3-vision" \ --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": "cipherxsnier/ocean-blue-blue3-vision", "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 cipherxsnier/ocean-blue-blue3-vision with Docker Model Runner:
docker model run hf.co/cipherxsnier/ocean-blue-blue3-vision
Ocean Blue: Blue-3 Vision
The vision sibling of Ocean Blue 3, named by Thomas. Qwen2.5-VL-7B-Instruct fine-tuned on real NOAA GOES-19 (East) and GOES-18 (West) full-disk GeoColor frames (1150 frames; 284 of them notarized by Omega TV and checked by SHA-256). Every label is computed, not guessed: the satellite and UTC time come from the frame, day or night at the disk centre from solar geometry. The held-out test is the newest 36 hours, never trained on.
| Task (held-out) | Before | After |
|---|---|---|
| Which satellite | 99.2% | 100.0% |
| UTC hour (within 1 h) | 36.8% | 98.5% |
| Day or night at disk centre | 56.7% | 100.0% |
| Overall | 64.7% | 99.4% |
Imagery: NOAA/NESDIS STAR, public domain. Weights: Apache-2.0 (from Qwen2.5-VL-7B-Instruct). Built with Qwen.
- Downloads last month
- 14
Model tree for cipherxsnier/ocean-blue-blue3-vision
Base model
Qwen/Qwen2.5-VL-7B-Instruct