bunnycore/CyberCore-Qwen-2.1-7B
Adapter vs bunnycore/Qwen-2.1-7b-Persona-lora_model. bunnycore/Qwen-2.1-7b-Persona-lora_model is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies bunnycore/CyberCore-Qwen-2.1-7B at load time.
2 derivatives checked
- mradermacher/CyberCore-Qwen-2.1-7B-i1-GGUF: Quantization
- mradermacher/CyberCore-Qwen-2.1-7B-GGUF: Same weights, converted