Instructions to use mindlab-research/MJev-Spatial-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mindlab-research/MJev-Spatial-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="mindlab-research/MJev-Spatial-4B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mindlab-research/MJev-Spatial-4B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mindlab-research/MJev-Spatial-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mindlab-research/MJev-Spatial-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mindlab-research/MJev-Spatial-4B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mindlab-research/MJev-Spatial-4B

SGLang

How to use mindlab-research/MJev-Spatial-4B 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 "mindlab-research/MJev-Spatial-4B" \
    --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": "mindlab-research/MJev-Spatial-4B",
		"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 "mindlab-research/MJev-Spatial-4B" \
        --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": "mindlab-research/MJev-Spatial-4B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mindlab-research/MJev-Spatial-4B with Docker Model Runner:
```
docker model run hf.co/mindlab-research/MJev-Spatial-4B
```

MJev-Spatial-4B

File size: 403 Bytes

{
  "step": 100,
  "format": "kev-spatial/v1",
  "train_mode": "full_language",
  "readout_kind": "native_last_qk_mean",
  "point_variant": "crop_refill",
  "readout_layer_index": 31,
  "readout_layer_indices": null,
  "layer_fusion": null,
  "checkpoint_policy": "full",
  "upstream_revision": "f1535963cea021439370c23127bc970b6788e730",
  "base_revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a"
}