Downloads · 30 days
1
2% of all-time downloads
Arjun9350/Ai24x7-vision-v10
Ai24x7-vision-v10 is a machine learning model from Arjun9350. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Base Model: Qwen3VL-8B (Fine-tuned on CCTV domain) - Format: GGUF Q5KM (quantized, 5.5GB) - Fine-tuning: 28 CCTV images, 3 epochs, LoRA QLoRA fine-tuning - Loss improvement: 3.65 → 1.97 (45% reduction) - Hardware: C…
Downloads · 30 days
1
2% of all-time downloads
All-time downloads
45
Public
Repo size
5.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf5.9 GB · 100%
From the Hugging Face model README
Customer CCTV Camera → AI24x7 Agent (₹42K machine) → Cloud GPU API (Arjun's server) → Telegram Alerts
curl -sL https://huggingface.co/Arjun9350/Ai24x7-vision-v10/resolve/main/install.sh | bash
# Download model
mkdir -p /opt/ai24x7/models
wget https://huggingface.co/Arjun9350/Ai24x7-vision-v10/resolve/main/model-q5_k_m.gguf -O /opt/ai24x7/models/model-q5_k_m.gguf
# Setup agent
pip3 install flask requests pillow python-telegram-bot opencv-python-headless
# Run
python3 ai24x7_agent.py
| Endpoint | Method | Description |
|---|---|---|
/health | GET | Health check |
/analyze | POST | Analyze image file |
/camera/<id>/snapshot | GET | Capture from RTSP and analyze |
curl -X POST http://localhost:5051/analyze -F "[email protected]"
model-q5_k_m.gguf - AI model (5.5GB)install.sh - One-command installer