Lambent/Mira-v1.26.1-27B
Full fine-tune vs unsloth/gemma-3-27b-pt. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Norms 484/484, MLP 294/294, Attention 464/464, other 1/1, Embeddings 3/3
2 derivatives checked
- mradermacher/Mira-v1.26.1-27B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Mira-v1.26.1-27B-GGUF: Quantization (fewer layers)