logan7000/cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-phi4mini-math345-groupB-llama32-end
Full fine-tune vs meta-llama/Llama-3.2-3B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 15/57, MLP 84/84, Attention 112/112
1 derivatives checked
- tinyopsec/cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-phi4mini-math345-groupB-llama32-end-GGUF: Same weights, converted