A 3B parameter language model fine-tuned for instruction following and reasoning tasks using Unsloth. The model was trained on problem-solving data containing questions, reasoning traces, and final answers.
1curl -fsSL https://ollama.com/install.sh | sh
2
3ollama serve
4
5ollama create my_model -f ./Modelfile
6
7ollama run my_model
This model is intended for research, learning, and experimentation. Outputs may contain mistakes and should be verified before use in important applications.
