Instructions to use kasohrab/gemma-spatial-bbox-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kasohrab/gemma-spatial-bbox-fixed with Transformers:

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

pipe = pipeline("image-text-to-text", model="kasohrab/gemma-spatial-bbox-fixed")

# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("kasohrab/gemma-spatial-bbox-fixed", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kasohrab/gemma-spatial-bbox-fixed with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kasohrab/gemma-spatial-bbox-fixed

SGLang

How to use kasohrab/gemma-spatial-bbox-fixed 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 "kasohrab/gemma-spatial-bbox-fixed" \
    --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": "kasohrab/gemma-spatial-bbox-fixed",
		"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 "kasohrab/gemma-spatial-bbox-fixed" \
        --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": "kasohrab/gemma-spatial-bbox-fixed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kasohrab/gemma-spatial-bbox-fixed with Docker Model Runner:
```
docker model run hf.co/kasohrab/gemma-spatial-bbox-fixed
```

kasohrab commited on Nov 11, 2025

Commit

40ff6aa

verified ·

1 Parent(s): b28e772

Training in progress, step 99000

Browse files

Files changed (2) hide show

logs/events.out.tfevents.1762816700.atl1-1-03-012-18-0.pace.gatech.edu.1101255.0 +2 -2
model.safetensors +1 -1

logs/events.out.tfevents.1762816700.atl1-1-03-012-18-0.pace.gatech.edu.1101255.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce07c58f943bae868587d1bad1c07502bb04e2cdc0e09d40bb8513f0b381341
-size 105999

 version https://git-lfs.github.com/spec/v1
+oid sha256:a3f61e67a92152759ab9115dd12f2fd04c59b5c65b00c0f0899e031e9e593955
+size 110299

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6d191f233b3ea9c96a80acba61f0405cc7c20f423edba1401365232e874134
 size 8600280616

 version https://git-lfs.github.com/spec/v1
+oid sha256:51e150da0496973713ef230c811e1e2b7203ff7f3ff09aafdf83aa797791fe60
 size 8600280616