mambiux/Luminium-Gixel-Cube-v1
Full fine-tune vs LiquidAI/LFM2-350M. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 2/2, other 21/21, MLP 48/48, Norms 38/38, Attention 12/12
2 derivatives checked
- mradermacher/Luminium-Gixel-Cube-v1-i1-GGUF: Quantization
- mradermacher/Luminium-Gixel-Cube-v1-GGUF: Same weights, converted