djuna/G2-Nowing-9B-32K-YS
Partial fine-tune vs zelk12/MT-Merge2-MU-gemma-2-MTg2MT1g2-9B. Partial change: 89% of the weights changed (attention, embeddings, mlp, norms), in 41 of 42 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 136/169, MLP 123/126, Attention 164/168
2 derivatives checked
- mradermacher/G2-Nowing-9B-32K-YS-i1-GGUF: Quantization
- mradermacher/G2-Nowing-9B-32K-YS-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.