Instructions to use kp-forks/SpatialLM-Llama-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kp-forks/SpatialLM-Llama-1B with Transformers:

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

pipe = pipeline("text-generation", model="kp-forks/SpatialLM-Llama-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("kp-forks/SpatialLM-Llama-1B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kp-forks/SpatialLM-Llama-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kp-forks/SpatialLM-Llama-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kp-forks/SpatialLM-Llama-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kp-forks/SpatialLM-Llama-1B

SGLang

How to use kp-forks/SpatialLM-Llama-1B 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 "kp-forks/SpatialLM-Llama-1B" \
    --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": "kp-forks/SpatialLM-Llama-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "kp-forks/SpatialLM-Llama-1B" \
        --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": "kp-forks/SpatialLM-Llama-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kp-forks/SpatialLM-Llama-1B with Docker Model Runner:
```
docker model run hf.co/kp-forks/SpatialLM-Llama-1B
```

ysmao commited on Mar 21, 2025

Commit

0a4c5f3

verified ·

1 Parent(s): 5ee85c0

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -37,6 +37,7 @@ SpatialLM is a 3D large language model designed to process 3D point cloud data a
 <div align="center">
   <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63efbb1efc92a63ac81126d0/3bz_jNRCLD2L9uj11HPnP.mp4" poster="https://cdn-uploads.huggingface.co/production/uploads/63efbb1efc92a63ac81126d0/euo94dNx28qBNe51_oiB1.png"></video>
 </div>
 ## SpatialLM Models

 <div align="center">
   <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63efbb1efc92a63ac81126d0/3bz_jNRCLD2L9uj11HPnP.mp4" poster="https://cdn-uploads.huggingface.co/production/uploads/63efbb1efc92a63ac81126d0/euo94dNx28qBNe51_oiB1.png"></video>
+  <p><i>SpatialLM reconstructs 3D layout from a monocular RGB video with MASt3R-SLAM. Results aligned to video with GT cameras for visualization.</i></p>
 </div>
 ## SpatialLM Models