farwew/gemma2-9b-cpt-sahabatai-v1-instruct-Med_QA_LoRA
Full fine-tune vs GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct. farwew/gemma2-9b-cpt-sahabatai-v1-instruct-Med_QA_LoRA is a GGUF (F16) of different weights. Fine-tune: 90% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 0/1, Norms 84/169, MLP 126/126, Attention 168/168