mradermacher/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca-GGUF
Adapter vs MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca. MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca is a LoRA adapter, not full weights: rank 32, on gate, k_proj, o_proj, q_proj, v_proj, w1, w2, w3 in 32 layers (928 adapted matrices). It modifies mradermacher/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca-GGUF at load time.