insraq/LFM2.5-2.6B-heretic-GGUF
Full fine-tune vs LiquidAI/LFM2.5-2.6B-Base. insraq/LFM2.5-2.6B-heretic-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 2/2, other 44/44, MLP 90/90, Norms 69/76, Attention 32/32