Instructions to use TerraSense-CASM/TerraSense with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TerraSense-CASM/TerraSense with Transformers:

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

pipe = pipeline("image-text-to-text", model="TerraSense-CASM/TerraSense")
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("TerraSense-CASM/TerraSense")
model = AutoModelForMultimodalLM.from_pretrained("TerraSense-CASM/TerraSense")
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 TerraSense-CASM/TerraSense with vLLM:

Install from pip and serve model

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

SGLang

How to use TerraSense-CASM/TerraSense 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 "TerraSense-CASM/TerraSense" \
    --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": "TerraSense-CASM/TerraSense",
		"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 "TerraSense-CASM/TerraSense" \
        --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": "TerraSense-CASM/TerraSense",
		"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 TerraSense-CASM/TerraSense with Docker Model Runner:
```
docker model run hf.co/TerraSense-CASM/TerraSense
```

TerraSense / README.md

MaQAQ

Upload folder using huggingface_hub

3d7a782 verified 7 months ago

preview code

Raw

History Blame Contribute Delete

1.5 kB

	---
	library_name: transformers
	license: apache-2.0
	language:
	- en
	- zh
	tags:
	- remote-sensing
	- mllm
	- multimodal
	- earth-observation
	- satellite-imagery
	pipeline_tag: image-text-to-text
	---

	# 🌍 TerraSense-Base

	A Multimodal Large Language Model for Remote Sensing.

	## 📖 Documentation

	For usage instructions, examples, and detailed documentation, please visit:

	👉 [GitHub Repository](https://github.com/TerraSense-CASM/terrasense)

	## 🚀 Quick Start

	```python
	from transformers import AutoModelForVision2Seq, AutoProcessor
	from qwen_vl_utils import process_vision_info
	import torch

	model = AutoModelForVision2Seq.from_pretrained(
	"TerraSense-CASM/TerraSense-Base",
	torch_dtype=torch.bfloat16,
	device_map="auto",
	trust_remote_code=True
	)
	processor = AutoProcessor.from_pretrained("TerraSense-CASM/TerraSense-Base", trust_remote_code=True)

	messages = [{"role": "user", "content": [
	{"type": "image", "image": "path/to/image.jpg"},
	{"type": "text", "text": "Describe this remote sensing image."},
	]}]

	text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	image_inputs, _ = process_vision_info(messages)
	inputs = processor(text=[text], images=image_inputs, padding=True, return_tensors="pt").to("cuda")
	output = model.generate(**inputs, max_new_tokens=512)
	print(processor.batch_decode(output, skip_special_tokens=True)[0])
	```

	## 📜 License

	[Apache 2.0](https://github.com/TerraSense-CASM/terrasense/blob/main/LICENSE)