allura-org/Lune-Mamba-3B-v1
Full fine-tune vs ibm-granite/granite-4.0-h-micro. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 88/117, other 200/252, MLP 80/80, Attention 16/16
2 derivatives checked
- mradermacher/Lune-Mamba-3B-v1-i1-GGUF: Quantization
- allura-org/Lune-Mamba-3B-v1-GRPO_IF: LoRA-style