AnshChoudhary/finetuning-Llama2-7b
Fine-tuning the LLaMA 2-7B model (7 billion parameters) using QLoRA technique on a T4 GPU with 16 GB of VRAM.
Jupyter Notebook
Fine-tuning the LLaMA 2-7B model (7 billion parameters) using QLoRA technique on a T4 GPU with 16 GB of VRAM.
Jupyter Notebook