Tivaphraen/LFM2-8B-A1B-smoltalk-GGUF
Adapter vs LiquidAI/LFM2-8B-A1B-smoltalk-LoRA. LiquidAI/LFM2-8B-A1B-smoltalk-LoRA is a LoRA adapter, not full weights: rank 8, on gate, in_proj, k_proj, out_proj, q_proj, v_proj, w1, w2… in 24 layers (2200 adapted matrices). It modifies Tivaphraen/LFM2-8B-A1B-smoltalk-GGUF at load time.