mkurman/Llama-3.2-MedIT-SUN-2.5B-BT-GRPO

Full fine-tune vs meditsolutions/Llama-3.2-SUN-2.5B-chat. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 41/65, MLP 96/96, Attention 109/128

1 derivatives checked

• mradermacher/Llama-3.2-MedIT-SUN-2.5B-BT-GRPO-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse