This collection includes base phi3-mini A) DPO aligned B) SFT on ARC train split (3 epochs) C) Quantised version of B) using GPTQ.
MLP
classroom
AI & ML interests
Building ChatGPT for EPFL Course Contents
This collection includes base phi3-mini A) DPO aligned B) SFT on ARC train split (3 epochs) C) Quantised version of B) using GPTQ.
Collection of the quantised version of the best performing model finetuned for MCQA
Collection of Phi3 models aligned for MCQA for respective datasets for 3 epochs. MCQ dataset is combination of all datasets.
Collection of the QLoRA Phi-3 DPO aligned models, each having different hyper-parameters.