Text Generation
Safetensors
GGUF
English
Arabic
qwen2
conversational
small-language-model
edge-ai
raspberry-pi
arm
lora
Instructions to use srmortal/SilentVision-52M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use srmortal/SilentVision-52M with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf srmortal/SilentVision-52M:Q4_K_M # Run inference directly in the terminal: llama cli -hf srmortal/SilentVision-52M:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf srmortal/SilentVision-52M:Q4_K_M # Run inference directly in the terminal: llama cli -hf srmortal/SilentVision-52M:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf srmortal/SilentVision-52M:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf srmortal/SilentVision-52M:Q4_K_M
Use Docker
docker model run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use srmortal/SilentVision-52M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "srmortal/SilentVision-52M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "srmortal/SilentVision-52M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Ollama
How to use srmortal/SilentVision-52M with Ollama:
ollama run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use srmortal/SilentVision-52M with Docker Model Runner:
docker model run hf.co/srmortal/SilentVision-52M:Q4_K_M
- Lemonade
How to use srmortal/SilentVision-52M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull srmortal/SilentVision-52M:Q4_K_M
Run and chat with the model
lemonade run user.SilentVision-52M-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload models/catalog.json with huggingface_hub
Browse files- models/catalog.json +8 -5
models/catalog.json
CHANGED
|
@@ -200,9 +200,10 @@
|
|
| 200 |
"id": "tool-navigation",
|
| 201 |
"name": "Pedestrian Navigation & Spatial Tool",
|
| 202 |
"category": "tools",
|
| 203 |
-
"version": "1.0.
|
| 204 |
"size_mb": 0.1,
|
| 205 |
"description": "SQLite R*Tree spatial query engine for nearest transit, pharmacies, and street accessibility.",
|
|
|
|
| 206 |
"dependencies": ["map-egypt"],
|
| 207 |
"target_path": "src/tools/navigation/pedestrian_map.py",
|
| 208 |
"upstream_url": "https://huggingface.co/srmortal/SilentVision-52M/resolve/main/tools/tool-navigation.tar.gz",
|
|
@@ -248,9 +249,10 @@
|
|
| 248 |
"id": "tool-audio",
|
| 249 |
"name": "Accessible Audio & VAD Loop Engine",
|
| 250 |
"category": "tools",
|
| 251 |
-
"version": "1.0.
|
| 252 |
"size_mb": 0.1,
|
| 253 |
-
"description": "Audio earcons, WebRTC VAD chunking, tactile button hooks, and speech daemon for blind users.",
|
|
|
|
| 254 |
"dependencies": ["vad-webrtc", "stt-whisper", "tts-piper"],
|
| 255 |
"target_path": "src/tools/audio/vad.py",
|
| 256 |
"upstream_url": "https://huggingface.co/srmortal/SilentVision-52M/resolve/main/tools/tool-audio.tar.gz",
|
|
@@ -260,9 +262,10 @@
|
|
| 260 |
"id": "tool-system",
|
| 261 |
"name": "Edge Telemetry & Hardware Monitor",
|
| 262 |
"category": "tools",
|
| 263 |
-
"version": "1.0.
|
| 264 |
"size_mb": 0.1,
|
| 265 |
-
"description": "Real-time physical CPU temperature, RAM usage, swap rate, storage, and battery monitor.",
|
|
|
|
| 266 |
"dependencies": [],
|
| 267 |
"target_path": "src/tools/system/hardware.py",
|
| 268 |
"upstream_url": "https://huggingface.co/srmortal/SilentVision-52M/resolve/main/tools/tool-system.tar.gz",
|
|
|
|
| 200 |
"id": "tool-navigation",
|
| 201 |
"name": "Pedestrian Navigation & Spatial Tool",
|
| 202 |
"category": "tools",
|
| 203 |
+
"version": "1.0.1",
|
| 204 |
"size_mb": 0.1,
|
| 205 |
"description": "SQLite R*Tree spatial query engine for nearest transit, pharmacies, and street accessibility.",
|
| 206 |
+
"changelog": "1.0.1: Added live GPS and phone broadcast location support",
|
| 207 |
"dependencies": ["map-egypt"],
|
| 208 |
"target_path": "src/tools/navigation/pedestrian_map.py",
|
| 209 |
"upstream_url": "https://huggingface.co/srmortal/SilentVision-52M/resolve/main/tools/tool-navigation.tar.gz",
|
|
|
|
| 249 |
"id": "tool-audio",
|
| 250 |
"name": "Accessible Audio & VAD Loop Engine",
|
| 251 |
"category": "tools",
|
| 252 |
+
"version": "1.0.1",
|
| 253 |
"size_mb": 0.1,
|
| 254 |
+
"description": "Audio earcons, WebRTC VAD chunking, tactile button hooks, openWakeWord acoustic detection, and speech daemon for blind users.",
|
| 255 |
+
"changelog": "1.0.1: Added openWakeWord ONNX acoustic wake-word engine with graceful fallback",
|
| 256 |
"dependencies": ["vad-webrtc", "stt-whisper", "tts-piper"],
|
| 257 |
"target_path": "src/tools/audio/vad.py",
|
| 258 |
"upstream_url": "https://huggingface.co/srmortal/SilentVision-52M/resolve/main/tools/tool-audio.tar.gz",
|
|
|
|
| 262 |
"id": "tool-system",
|
| 263 |
"name": "Edge Telemetry & Hardware Monitor",
|
| 264 |
"category": "tools",
|
| 265 |
+
"version": "1.0.1",
|
| 266 |
"size_mb": 0.1,
|
| 267 |
+
"description": "Real-time physical CPU temperature, RAM usage, swap rate, storage, phone-shared GPS, and battery monitor.",
|
| 268 |
+
"changelog": "1.0.1: Added live GPS reader supporting phone-shared broadcast and gpsd socket",
|
| 269 |
"dependencies": [],
|
| 270 |
"target_path": "src/tools/system/hardware.py",
|
| 271 |
"upstream_url": "https://huggingface.co/srmortal/SilentVision-52M/resolve/main/tools/tool-system.tar.gz",
|