sam-paech/Quill-v1
Full fine-tune vs google/gemma-2-9b-it. Fine-tune: 90% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 0/1, Norms 70/169, MLP 126/126, Attention 168/168
4 derivatives checked
- mradermacher/Quill-v1-i1-GGUF: Quantization
- mradermacher/Quill-v1-GGUF: Same weights, converted
- Naphula/Quill-v1-abliterated: Abliterated
- zelk12/MT1-Gen5-MU-gemma-2-S2Qv1-9B: Full fine-tune