Instructions to use prithivMLmods/SpatialBlock-3B-reason-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/SpatialBlock-3B-reason-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/SpatialBlock-3B-reason-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/SpatialBlock-3B-reason-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/SpatialBlock-3B-reason-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/SpatialBlock-3B-reason-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/SpatialBlock-3B-reason-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/SpatialBlock-3B-reason-GGUF",
		"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/prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/SpatialBlock-3B-reason-GGUF 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 "prithivMLmods/SpatialBlock-3B-reason-GGUF" \
    --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": "prithivMLmods/SpatialBlock-3B-reason-GGUF",
		"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 "prithivMLmods/SpatialBlock-3B-reason-GGUF" \
        --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": "prithivMLmods/SpatialBlock-3B-reason-GGUF",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/SpatialBlock-3B-reason-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use prithivMLmods/SpatialBlock-3B-reason-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/SpatialBlock-3B-reason-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/SpatialBlock-3B-reason-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SpatialBlock-3B-reason-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

prithivMLmods commited on Sep 11

Commit

03b6fe3

verified ·

1 Parent(s): 687080c

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -1

README.md CHANGED Viewed

@@ -2,4 +2,15 @@
 license: apache-2.0
 base_model:
 - rsoohyun/SpatialBlock-3B-reason
----

 license: apache-2.0
 base_model:
 - rsoohyun/SpatialBlock-3B-reason
+language:
+- en
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- text-generation-inference
+- llama-cpp
+---
+# **SpatialBlock-3B-reason-GGUF**
+> **SpatialBlock-3B-reason** is an open-source multimodal model released on Hugging Face by [rsoohyun](https://huggingface.co/rsoohyun) under the Apache-2.0 license, developed to enhance spatial intelligence in Large Vision-Language Models (LVLMs). Based on the `Qwen/Qwen2.5-VL-3B-Instruct` base architecture and supported by the Hugging Face `transformers` library via the `image-text-to-text` pipeline, this checkpoint is fine-tuned on the synthetic `SpatialBlock-15k` dataset as presented in the paper *SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem*. It specializes in reasoning through and directly predicting solutions to intricate spatial challenges—including 3D-to-2D projection, viewpoint transformation, and structural combination—with complete training methodology, evaluation metrics, and companion models accessible via its [GitHub repository](https://github.com/rsoohyun/SpatialBlock).