🦙 Llama 3.2 3B Instruct - Fine-tuned on FineTome
KTH ID2223 Scalable Machine Learning - Lab 2
This chatbot uses my fine-tuned Llama 3.2 3B model trained on the FineTome-100k dataset.
📦 Model: Marcus719/Llama-3.2-3B-Instruct-Lab2
64 1024
0.1 1.5
0.1 1
💡 Try these examples
📝 About This Project
Fine-tuning Details:
- Base Model:
meta-llama/Llama-3.2-3B-Instruct - Dataset: FineTome-100k
- Method: QLoRA (4-bit quantization + LoRA)
- Framework: Unsloth
Built with ❤️ for KTH ID2223 Lab 2