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", dtype="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
| "use client"; | |
| import { useState } from "react"; | |
| import { startStream } from "../lib/api"; | |
| interface AddCameraModalProps { | |
| open: boolean; | |
| onClose: () => void; | |
| onAdded: () => void; | |
| } | |
| export default function AddCameraModal({ open, onClose, onAdded }: AddCameraModalProps) { | |
| const [cameraId, setCameraId] = useState(""); | |
| const [rtspUrl, setRtspUrl] = useState(""); | |
| const [fps, setFps] = useState("2.0"); | |
| const [loading, setLoading] = useState(false); | |
| const [error, setError] = useState<string | null>(null); | |
| if (!open) return null; | |
| async function handleSubmit() { | |
| if (!cameraId.trim() || !rtspUrl.trim()) { | |
| setError("Camera ID and RTSP URL are required"); | |
| return; | |
| } | |
| setLoading(true); | |
| setError(null); | |
| try { | |
| await startStream(cameraId.trim(), rtspUrl.trim(), parseFloat(fps)); | |
| setCameraId(""); | |
| setRtspUrl(""); | |
| onAdded(); | |
| onClose(); | |
| } catch (e) { | |
| setError(e instanceof Error ? e.message : "Failed to start stream"); | |
| } finally { | |
| setLoading(false); | |
| } | |
| } | |
| return ( | |
| <div className="fixed inset-0 z-50 flex items-center justify-center"> | |
| <div className="absolute inset-0 bg-black/60" onClick={onClose} /> | |
| <div className="relative bg-[var(--surface)] border border-[var(--border)] rounded-2xl p-6 w-full max-w-md shadow-2xl"> | |
| <h2 className="text-lg font-semibold mb-4">Add Camera</h2> | |
| <div className="space-y-3"> | |
| <div> | |
| <label className="text-xs text-[var(--muted)] mb-1 block">Camera ID</label> | |
| <input | |
| value={cameraId} | |
| onChange={(e) => setCameraId(e.target.value)} | |
| placeholder="e.g. lobby-cam-01" | |
| className="w-full bg-[var(--background)] border border-[var(--border)] rounded-lg px-3 py-2 text-sm focus:outline-none focus:border-[var(--accent)]/50" | |
| /> | |
| </div> | |
| <div> | |
| <label className="text-xs text-[var(--muted)] mb-1 block">RTSP URL</label> | |
| <input | |
| value={rtspUrl} | |
| onChange={(e) => setRtspUrl(e.target.value)} | |
| placeholder="rtsp://user:pass@192.168.1.100:554/stream" | |
| className="w-full bg-[var(--background)] border border-[var(--border)] rounded-lg px-3 py-2 text-sm focus:outline-none focus:border-[var(--accent)]/50" | |
| /> | |
| </div> | |
| <div> | |
| <label className="text-xs text-[var(--muted)] mb-1 block">Target FPS</label> | |
| <input | |
| type="number" | |
| value={fps} | |
| onChange={(e) => setFps(e.target.value)} | |
| min="0.1" | |
| max="30" | |
| step="0.5" | |
| className="w-full bg-[var(--background)] border border-[var(--border)] rounded-lg px-3 py-2 text-sm focus:outline-none focus:border-[var(--accent)]/50" | |
| /> | |
| </div> | |
| </div> | |
| {error && <p className="text-xs text-[var(--danger)] mt-3">{error}</p>} | |
| <div className="flex gap-2 mt-5 justify-end"> | |
| <button onClick={onClose} className="px-4 py-2 text-sm text-[var(--muted)] hover:text-[var(--foreground)]">Cancel</button> | |
| <button | |
| onClick={handleSubmit} | |
| disabled={loading} | |
| className="px-4 py-2 bg-[var(--accent)] hover:bg-[var(--accent-hover)] text-white rounded-lg text-sm font-medium disabled:opacity-40" | |
| > | |
| {loading ? "Connecting..." : "Add Camera"} | |
| </button> | |
| </div> | |
| </div> | |
| </div> | |
| ); | |
| } | |