AKMESSI/lfm2.5-230m-fable-5
LoRA-style vs LiquidAI/LFM2.5-230M. AKMESSI/lfm2.5-230m-fable-5 is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, q_proj, v_proj changed, in 6 of 14 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, other 0/16, MLP 0/42, Norms 0/40, Attention 18/24