gradients-io-tournaments/tournament-tourn_5abc2fe9f0667979_20260914-d7ab189e-947e-401d-9f66-92aea124efdf-5ELGMNNW
Adapter vs unsloth/Meta-Llama-3.1-8B-Instruct. gradients-io-tournaments/tournament-tourn_5abc2fe9f0667979_20260914-d7ab189e-947e-401d-9f66-92aea124efdf-5ELGMNNW is a LoRA adapter, not full weights: rank 128, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 32 layers (224 adapted matrices). It modifies unsloth/Meta-Llama-3.1-8B-Instruct at load time.