logan7000/cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-granite2b-math345-groupC-granite2b-end

Full fine-tune vs ibm-granite/granite-3.3-2b-instruct. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 63/81, MLP 120/120, Attention 160/160

On the Hub · Downloads on Model Pulse