Image-Text-to-Text
Transformers
Safetensors
remote-sensing
earth-observation
geospatial
qwen2_5_vl
grpo
Instructions to use ibm-research/GeoVLM-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-research/GeoVLM-R1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="ibm-research/GeoVLM-R1")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ibm-research/GeoVLM-R1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ibm-research/GeoVLM-R1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ibm-research/GeoVLM-R1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ibm-research/GeoVLM-R1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ibm-research/GeoVLM-R1
- SGLang
How to use ibm-research/GeoVLM-R1 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 "ibm-research/GeoVLM-R1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ibm-research/GeoVLM-R1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "ibm-research/GeoVLM-R1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ibm-research/GeoVLM-R1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ibm-research/GeoVLM-R1 with Docker Model Runner:
docker model run hf.co/ibm-research/GeoVLM-R1
Download GeoVLM_R1_Region_Captioning/tokenizer.json from ibm-research/GeoVLM-R1: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/ibm-research/GeoVLM-R1/resolve/main/GeoVLM_R1_Region_Captioning/tokenizer.json
- Command line
-
hf download hf://ibm-research/GeoVLM-R1/GeoVLM_R1_Region_Captioning/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/ibm-research/GeoVLM-R1/resolve/main/GeoVLM_R1_Region_Captioning/tokenizer.json
11.4 MB
- Xet hash:
- ff206f79d3c0e627de7956b4ef37c2b8eeab5e83490ff04516bc674e4c1d6e77
- Size of remote file:
- 11.4 MB
- SHA256:
- 5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.