Modelpublic

wangshiting/linear_llama_math_coding

sourceHugging Faceupdated 8mo agoView on Hugging Face

0likes12downloads

mergekit_config.yml10 linesDownload Raw Back to root

1models:2  - model: MergeBench/Llama-3.2-3B-Instruct_math3    parameters:4      weight: 1.05  - model: MergeBench/Llama-3.2-3B-Instruct_coding6    parameters:7      weight: 1.08merge_method: linear9dtype: float1610