zelk12/MT5-IF-gemma-2-RIv0.1RAv0.1-9B
Full fine-tune vs zelk12/recoilme-gemma-2-Ataraxy-9B-v0.1. Fine-tune: 98% of the weights changed, across 42 of 42 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 91/169, MLP 123/126, Attention 164/168
1 derivatives checked
- mradermacher/MT5-IF-gemma-2-RIv0.1RAv0.1-9B-GGUF: Same weights, converted
3 other repos hold byte-for-byte identical weight files.