Instruction Finetuning - Math (MetaMathQA) - a LoRA-TMLR-2024 Collection

LoRA-TMLR-2024 's Collections

Instruction Finetuning - Code (Magicoder-Evol-Instruct-110K)

Continued Pretraining - Code (StarCoder-Python)

Instruction Finetuning - Math (MetaMathQA)

Continued Pretraining - Math (OpenWebMath)

Instruction Finetuning - Math (MetaMathQA)

updated Sep 25, 2024

Model and LoRA adapter checkpoints for Llama-2-7B finetuned on MetaMathQA