Image-Text-to-Text
Transformers
English
vision-language-model
vlm
surveillance
iot
gemma
vl-jepa
multimodal
object-detection
video-analytics
Instructions to use hardiksa/arcisvlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hardiksa/arcisvlm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="hardiksa/arcisvlm")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hardiksa/arcisvlm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hardiksa/arcisvlm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hardiksa/arcisvlm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hardiksa/arcisvlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hardiksa/arcisvlm
- SGLang
How to use hardiksa/arcisvlm 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 "hardiksa/arcisvlm" \ --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": "hardiksa/arcisvlm", "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 "hardiksa/arcisvlm" \ --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": "hardiksa/arcisvlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hardiksa/arcisvlm with Docker Model Runner:
docker model run hf.co/hardiksa/arcisvlm
| # Deploy ArcisVLM to GCP — creates VM with L4 GPU, installs Docker, builds stack | |
| set -euo pipefail | |
| PROJECT="arcisai-iot-platform" | |
| ZONE="us-central1-a" | |
| INSTANCE="arcisvlm-beta" | |
| MACHINE="g2-standard-8" | |
| GPU="nvidia-l4" | |
| DISK_SIZE="100GB" | |
| echo "=== Creating GCE instance: $INSTANCE ===" | |
| gcloud compute instances create "$INSTANCE" \ | |
| --project="$PROJECT" \ | |
| --zone="$ZONE" \ | |
| --machine-type="$MACHINE" \ | |
| --accelerator="type=$GPU,count=1" \ | |
| --maintenance-policy=TERMINATE \ | |
| --boot-disk-size="$DISK_SIZE" \ | |
| --boot-disk-type=pd-ssd \ | |
| --image-family=ubuntu-2204-lts \ | |
| --image-project=ubuntu-os-cloud \ | |
| --metadata=install-nvidia-driver=True \ | |
| --tags=http-server,https-server | |
| echo "=== Configuring firewall ===" | |
| gcloud compute firewall-rules create allow-arcisvlm-http \ | |
| --project="$PROJECT" \ | |
| --allow=tcp:80,tcp:443 \ | |
| --target-tags=http-server \ | |
| --description="Allow HTTP/HTTPS for ArcisVLM" 2>/dev/null || true | |
| echo "=== Waiting for instance to boot (60s) ===" | |
| sleep 60 | |
| echo "=== Copying code to instance ===" | |
| SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" | |
| PROJECT_DIR="$(dirname "$SCRIPT_DIR")" | |
| cd "$PROJECT_DIR" | |
| tar czf /tmp/arcisvlm-deploy.tar.gz \ | |
| --exclude='.git' --exclude='__pycache__' --exclude='node_modules' \ | |
| --exclude='.next' --exclude='exports' --exclude='profiling' \ | |
| --exclude='checkpoints/*.pt' --exclude='*.onnx*' --exclude='.claude' \ | |
| . | |
| gcloud compute scp /tmp/arcisvlm-deploy.tar.gz "$INSTANCE":~ --zone="$ZONE" --project="$PROJECT" | |
| gcloud compute scp deploy/setup-instance.sh "$INSTANCE":~ --zone="$ZONE" --project="$PROJECT" | |
| echo "=== Running setup on instance ===" | |
| gcloud compute ssh "$INSTANCE" --zone="$ZONE" --project="$PROJECT" \ | |
| --command="chmod +x ~/setup-instance.sh && ~/setup-instance.sh" | |
| IP=$(gcloud compute instances describe "$INSTANCE" --zone="$ZONE" --project="$PROJECT" \ | |
| --format='get(networkInterfaces[0].accessConfigs[0].natIP)') | |
| echo "" | |
| echo "=============================================" | |
| echo " ArcisVLM deployed at: http://$IP" | |
| echo " Instance: $INSTANCE ($ZONE)" | |
| echo "" | |
| echo " REMEMBER: Destroy when testing complete!" | |
| echo " Run: ./deploy/destroy-gcp.sh" | |
| echo "=============================================" | |