ZuzeTt/LFM2.5-1.2B-Instruct-imatrix-GGUF
Full fine-tune vs LiquidAI/LFM2.5-1.2B-Base. ZuzeTt/LFM2.5-1.2B-Instruct-imatrix-GGUF is a GGUF (BF16) of different weights. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 2/2, other 20/20, MLP 48/48, Norms 44/44, Attention 24/24