zelk12/MT-Merge2-MU-gemma-2-MTg2MT1g2-9B
Full fine-tune vs zelk12/MT-Gen2-gemma-2-9B. Fine-tune: 91% of the weights changed, across 42 of 42 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 127/169, MLP 126/126, Attention 168/168
8 derivatives checked
- mradermacher/MT-Merge2-MU-gemma-2-MTg2MT1g2-9B-GGUF: Same weights, converted
- zelk12/MT1-Max-Merge_02012025163610-MU-gemma-2-MTM2MUMT1g2-9B: Full fine-tune
- djuna/G2-Nowing-9B-32K-YS: Partial fine-tune
- zelk12/MT1-Max-Merge_02012025163610-IF-gemma-2-MT1g2MTM2MU-9B: Full fine-tune
- zelk12/MT1-Max-Merge_02012025163610-MA-gemma-2-MTM5MTM2MU-9B: Full fine-tune
- zelk12/MT-Max-Merge_02012025163610-MU-gemma-2-MTM2MUMTM4-9B: Full fine-tune
- djuna/G2-Nowing-9B: Partial fine-tune
- zelk12/MT2-Max-Merge_02012025163610-MU-gemma-2-MTM2MUMTM4-9B: Full fine-tune