SicariusSicariiStuff/2B_or_not_2B
Full fine-tune vs google/gemma-1.1-2b-it. Fine-tune: 100% of the weights changed, across 18 of 18 layers.
Tensors changed: Embeddings 1/1, Norms 37/37, MLP 54/54, Attention 72/72
4 derivatives checked
- mradermacher/2B_or_not_2B-i1-GGUF: Quantization
- bartowski/2B_or_not_2B-GGUF: Quantization
- mradermacher/2B_or_not_2B-GGUF: Same weights, converted
- SicariusSicariiStuff/2B_or_not_2B_GGUFs: Quantization