Modelpublic

ksjpswaroop/zindango-slm-gguf

sourceHugging Faceapache-2.0updated 11mo agoView on Hugging Face

0likes45downloads

Model Card

Zindango-SLM GGUF

Fine-tuned version of zindango-slm-7B-Instruct with custom identity.

Model Details

—Base Model:
—Parameters: 7.62 billion
—Test Accuracy: 100%
—Developer: Zindango

Identity

Q: "Who are you?"
A: "I am SIlo one of zindango slm models"

Available Quantizations

File	Size	Description
`zindango-slm-q4_k_m.gguf`	4.4 GB	⭐ Recommended - Best balance
`zindango-slm-q5_k_m.gguf`	5.1 GB	Higher quality
`zindango-slm-q6_k.gguf`	5.9 GB	Very high quality
`zindango-slm-q8_0.gguf`	7.6 GB	Near lossless
`zindango-slm-f16.gguf`	15 GB	Full precision

Usage

Ollama

bash

# Download model
wget https://huggingface.co/$HF_USERNAME/zindango-slm-gguf/resolve/main/zindango-slm-q4_k_m.gguf

# Create Modelfile
cat > Modelfile << 'MODELFILE'
FROM ./zindango-slm-q4_k_m.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER top_k 40
MODELFILE

# Import to Ollama
ollama create zindango-slm:q4km -f Modelfile

# Run
ollama run zindango-slm:q4km "Who are you?"

llama.cpp

bash

# Download
wget https://huggingface.co/$HF_USERNAME/zindango-slm-gguf/resolve/main/zindango-slm-q4_k_m.gguf

# Run
./llama-cli -m zindango-slm-q4_k_m.gguf -p "Who are you?" -n 50

License

Apache 2.0 (inherited from Qwen2.5)

Citation

bibtex

@misc{zindango-slm,
  author = {Zindango},
  title = {Zindango-SLM},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/$HF_USERNAME/zindango-slm-gguf}}
}