LoRA-TMLR-2024/metamath-lora-rank-16-alpha-32
Updated • 40
Instruction Finetuning - Math (MetaMathQA)
Model and LoRA adapter checkpoints for Llama-2-7B finetuned on MetaMathQA
Model and LoRA adapter checkpoints for Llama-2-7B finetuned on MetaMathQA