Instructions to use lelloman/smollm-torrent-metadata 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 lelloman/smollm-torrent-metadata 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 lelloman/smollm-torrent-metadata:F32 # Run inference directly in the terminal: llama cli -hf lelloman/smollm-torrent-metadata:F32
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf lelloman/smollm-torrent-metadata:F32 # Run inference directly in the terminal: llama cli -hf lelloman/smollm-torrent-metadata:F32
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf lelloman/smollm-torrent-metadata:F32 # Run inference directly in the terminal: ./llama-cli -hf lelloman/smollm-torrent-metadata:F32
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf lelloman/smollm-torrent-metadata:F32 # Run inference directly in the terminal: ./build/bin/llama-cli -hf lelloman/smollm-torrent-metadata:F32
Use Docker
docker model run hf.co/lelloman/smollm-torrent-metadata:F32
- LM Studio
- Jan
- vLLM
How to use lelloman/smollm-torrent-metadata with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lelloman/smollm-torrent-metadata" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lelloman/smollm-torrent-metadata", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lelloman/smollm-torrent-metadata:F32
- Ollama
How to use lelloman/smollm-torrent-metadata with Ollama:
ollama run hf.co/lelloman/smollm-torrent-metadata:F32
- Unsloth Desktop
- Docker Model Runner
How to use lelloman/smollm-torrent-metadata with Docker Model Runner:
docker model run hf.co/lelloman/smollm-torrent-metadata:F32
- Lemonade
How to use lelloman/smollm-torrent-metadata with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull lelloman/smollm-torrent-metadata:F32
Run and chat with the model
lemonade run user.smollm-torrent-metadata-F32
List all available models
lemonade list
- Atomic Chat
SmolLM Torrent Metadata Extractor
Fine-tuned SmolLM-360M-Instruct for extracting structured metadata from torrent names.
Model Description
This model extracts title, artist, and year information from torrent filenames for audio and video content.
Input Format
<|im_start|>user
<|extract|>[content_type] torrent_name<|im_end|>
<|im_start|>assistant
Content Types
audio/albumโ outputs:album | artist | yearaudio/trackโ outputs:track | artist | yearvideo/movieโ outputs:title | yearvideo/episodeโ outputs:series_titlevideo/seasonโ outputs:series_titlevideo/seriesโ outputs:series_title
Examples
Input: <|extract|>[audio/album] Pink Floyd - The Dark Side of the Moon (1973) [FLAC]
Output: The Dark Side of the Moon | Pink Floyd | 1973
Input: <|extract|>[video/movie] The.Matrix.1999.1080p.BluRay.x264-GROUP
Output: The Matrix | 1999
Training
- Base model: SmolLM-360M-Instruct
- Method: LoRA fine-tuning (r=16, alpha=32)
- Training data: ~200k samples from Spotify catalog validation
- Checkpoint: 11500 steps
Files
| File | Size | Description |
|---|---|---|
smollm-f32.gguf |
1.4GB | Full precision GGUF |
smollm-q4_k_m.gguf |
259MB | Q4_K_M quantized (recommended for inference) |
Usage with llama.cpp
./llama-cli -m smollm-q4_k_m.gguf -p "<|im_start|>user
<|extract|>[audio/album] Radiohead - OK Computer (1997) [FLAC]<|im_end|}
<|im_start|>assistant
" -n 32
License
MIT
- Downloads last month
- 6
Hardware compatibility
Log In to add your hardware
4-bit
32-bit
Model tree for lelloman/smollm-torrent-metadata
Base model
HuggingFaceTB/SmolLM-360M Quantized
HuggingFaceTB/SmolLM-360M-Instruct