Obotu/POIEO-GGUF
Full fine-tune vs LiquidAI/LFM2.5-2.6B-Base. Obotu/POIEO-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/2, other 44/44, MLP 90/90, Norms 0/76, Attention 32/32