{ "alora_invocation_tokens": null, "alpha_pattern": { "model.layers.15.mlp.down_proj": 128, "model.layers.15.mlp.gate_proj": 128, "model.layers.15.mlp.up_proj": 128, "model.layers.15.self_attn.k_proj": 128, "model.layers.15.self_attn.o_proj": 128, "model.layers.15.self_attn.q_proj": 128, "model.layers.15.self_attn.v_proj": 128, "model.layers.16.mlp.down_proj": 32, "model.layers.16.mlp.gate_proj": 32, "model.layers.16.mlp.up_proj": 32, "model.layers.16.self_attn.k_proj": 32, "model.layers.16.self_attn.o_proj": 32, "model.layers.16.self_attn.q_proj": 32, "model.layers.16.self_attn.v_proj": 32, "model.layers.18.mlp.down_proj": 32, "model.layers.18.mlp.gate_proj": 32, "model.layers.18.mlp.up_proj": 32, "model.layers.18.self_attn.k_proj": 32, "model.layers.18.self_attn.o_proj": 32, "model.layers.18.self_attn.q_proj": 32, "model.layers.18.self_attn.v_proj": 32, "model.layers.20.mlp.down_proj": 64, "model.layers.20.mlp.gate_proj": 64, "model.layers.20.mlp.up_proj": 64, "model.layers.20.self_attn.k_proj": 64, "model.layers.20.self_attn.o_proj": 64, "model.layers.20.self_attn.q_proj": 64, "model.layers.20.self_attn.v_proj": 64, "model.layers.23.mlp.down_proj": 32, "model.layers.23.mlp.gate_proj": 32, "model.layers.23.mlp.up_proj": 32, "model.layers.23.self_attn.k_proj": 32, "model.layers.23.self_attn.o_proj": 32, "model.layers.23.self_attn.q_proj": 32, "model.layers.23.self_attn.v_proj": 32, "model.layers.24.mlp.down_proj": 64, "model.layers.24.mlp.gate_proj": 64, "model.layers.24.mlp.up_proj": 64, "model.layers.24.self_attn.k_proj": 64, "model.layers.24.self_attn.o_proj": 64, "model.layers.24.self_attn.q_proj": 64, "model.layers.24.self_attn.v_proj": 64, "model.layers.25.mlp.down_proj": 32, "model.layers.25.mlp.gate_proj": 32, "model.layers.25.mlp.up_proj": 32, "model.layers.25.self_attn.k_proj": 32, "model.layers.25.self_attn.o_proj": 32, "model.layers.25.self_attn.q_proj": 32, "model.layers.25.self_attn.v_proj": 32, "model.layers.26.mlp.down_proj": 128, "model.layers.26.mlp.gate_proj": 128, "model.layers.26.mlp.up_proj": 128, "model.layers.26.self_attn.k_proj": 128, "model.layers.26.self_attn.o_proj": 128, "model.layers.26.self_attn.q_proj": 128, "model.layers.26.self_attn.v_proj": 128, "model.layers.29.mlp.down_proj": 64, "model.layers.29.mlp.gate_proj": 64, "model.layers.29.mlp.up_proj": 64, "model.layers.29.self_attn.k_proj": 64, "model.layers.29.self_attn.o_proj": 64, "model.layers.29.self_attn.q_proj": 64, "model.layers.29.self_attn.v_proj": 64, "model.layers.32.mlp.down_proj": 64, "model.layers.32.mlp.gate_proj": 64, "model.layers.32.mlp.up_proj": 64, "model.layers.32.self_attn.k_proj": 64, "model.layers.32.self_attn.o_proj": 64, "model.layers.32.self_attn.q_proj": 64, "model.layers.32.self_attn.v_proj": 64, "model.layers.33.mlp.down_proj": 128, "model.layers.33.mlp.gate_proj": 128, "model.layers.33.mlp.up_proj": 128, "model.layers.33.self_attn.k_proj": 128, "model.layers.33.self_attn.o_proj": 128, "model.layers.33.self_attn.q_proj": 128, "model.layers.33.self_attn.v_proj": 128, "model.layers.7.mlp.down_proj": 128, "model.layers.7.mlp.gate_proj": 128, "model.layers.7.mlp.up_proj": 128, "model.layers.7.self_attn.k_proj": 128, "model.layers.7.self_attn.o_proj": 128, "model.layers.7.self_attn.q_proj": 128, "model.layers.7.self_attn.v_proj": 128, "model.layers.8.mlp.down_proj": 32, "model.layers.8.mlp.gate_proj": 32, "model.layers.8.mlp.up_proj": 32, "model.layers.8.self_attn.k_proj": 32, "model.layers.8.self_attn.o_proj": 32, "model.layers.8.self_attn.q_proj": 32, "model.layers.8.self_attn.v_proj": 32 }, "arrow_config": null, "auto_mapping": { "base_model_class": "Qwen3ForCausalLM", "parent_library": "transformers.models.qwen3.modeling_qwen3", "unsloth_fixed": true }, "base_model_name_or_path": "unsloth/Qwen3-4B-Base", "bias": "none", "corda_config": null, "ensure_weight_tying": false, "eva_config": null, "exclude_modules": null, "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layer_replication": null, "layers_pattern": null, "layers_to_transform": null, "loftq_config": {}, "lora_alpha": 64, "lora_bias": false, "lora_dropout": 0.0, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "peft_version": "0.18.1", "qalora_group_size": 16, "r": 32, "rank_pattern": { "model.layers.15.mlp.down_proj": 64, "model.layers.15.mlp.gate_proj": 64, "model.layers.15.mlp.up_proj": 64, "model.layers.15.self_attn.k_proj": 64, "model.layers.15.self_attn.o_proj": 64, "model.layers.15.self_attn.q_proj": 64, "model.layers.15.self_attn.v_proj": 64, "model.layers.16.mlp.down_proj": 16, "model.layers.16.mlp.gate_proj": 16, "model.layers.16.mlp.up_proj": 16, "model.layers.16.self_attn.k_proj": 16, "model.layers.16.self_attn.o_proj": 16, "model.layers.16.self_attn.q_proj": 16, "model.layers.16.self_attn.v_proj": 16, "model.layers.18.mlp.down_proj": 16, "model.layers.18.mlp.gate_proj": 16, "model.layers.18.mlp.up_proj": 16, "model.layers.18.self_attn.k_proj": 16, "model.layers.18.self_attn.o_proj": 16, "model.layers.18.self_attn.q_proj": 16, "model.layers.18.self_attn.v_proj": 16, "model.layers.20.mlp.down_proj": 32, "model.layers.20.mlp.gate_proj": 32, "model.layers.20.mlp.up_proj": 32, "model.layers.20.self_attn.k_proj": 32, "model.layers.20.self_attn.o_proj": 32, "model.layers.20.self_attn.q_proj": 32, "model.layers.20.self_attn.v_proj": 32, "model.layers.23.mlp.down_proj": 16, "model.layers.23.mlp.gate_proj": 16, "model.layers.23.mlp.up_proj": 16, "model.layers.23.self_attn.k_proj": 16, "model.layers.23.self_attn.o_proj": 16, "model.layers.23.self_attn.q_proj": 16, "model.layers.23.self_attn.v_proj": 16, "model.layers.24.mlp.down_proj": 32, "model.layers.24.mlp.gate_proj": 32, "model.layers.24.mlp.up_proj": 32, "model.layers.24.self_attn.k_proj": 32, "model.layers.24.self_attn.o_proj": 32, "model.layers.24.self_attn.q_proj": 32, "model.layers.24.self_attn.v_proj": 32, "model.layers.25.mlp.down_proj": 16, "model.layers.25.mlp.gate_proj": 16, "model.layers.25.mlp.up_proj": 16, "model.layers.25.self_attn.k_proj": 16, "model.layers.25.self_attn.o_proj": 16, "model.layers.25.self_attn.q_proj": 16, "model.layers.25.self_attn.v_proj": 16, "model.layers.26.mlp.down_proj": 64, "model.layers.26.mlp.gate_proj": 64, "model.layers.26.mlp.up_proj": 64, "model.layers.26.self_attn.k_proj": 64, "model.layers.26.self_attn.o_proj": 64, "model.layers.26.self_attn.q_proj": 64, "model.layers.26.self_attn.v_proj": 64, "model.layers.29.mlp.down_proj": 32, "model.layers.29.mlp.gate_proj": 32, "model.layers.29.mlp.up_proj": 32, "model.layers.29.self_attn.k_proj": 32, "model.layers.29.self_attn.o_proj": 32, "model.layers.29.self_attn.q_proj": 32, "model.layers.29.self_attn.v_proj": 32, "model.layers.32.mlp.down_proj": 32, "model.layers.32.mlp.gate_proj": 32, "model.layers.32.mlp.up_proj": 32, "model.layers.32.self_attn.k_proj": 32, "model.layers.32.self_attn.o_proj": 32, "model.layers.32.self_attn.q_proj": 32, "model.layers.32.self_attn.v_proj": 32, "model.layers.33.mlp.down_proj": 64, "model.layers.33.mlp.gate_proj": 64, "model.layers.33.mlp.up_proj": 64, "model.layers.33.self_attn.k_proj": 64, "model.layers.33.self_attn.o_proj": 64, "model.layers.33.self_attn.q_proj": 64, "model.layers.33.self_attn.v_proj": 64, "model.layers.7.mlp.down_proj": 64, "model.layers.7.mlp.gate_proj": 64, "model.layers.7.mlp.up_proj": 64, "model.layers.7.self_attn.k_proj": 64, "model.layers.7.self_attn.o_proj": 64, "model.layers.7.self_attn.q_proj": 64, "model.layers.7.self_attn.v_proj": 64, "model.layers.8.mlp.down_proj": 16, "model.layers.8.mlp.gate_proj": 16, "model.layers.8.mlp.up_proj": 16, "model.layers.8.self_attn.k_proj": 16, "model.layers.8.self_attn.o_proj": 16, "model.layers.8.self_attn.q_proj": 16, "model.layers.8.self_attn.v_proj": 16 }, "revision": null, "target_modules": [ "model.layers.33.self_attn.v_proj", "model.layers.20.mlp.gate_proj", "model.layers.29.mlp.down_proj", "model.layers.16.mlp.gate_proj", "model.layers.8.self_attn.q_proj", "model.layers.24.self_attn.q_proj", "model.layers.15.self_attn.k_proj", "model.layers.26.mlp.gate_proj", "model.layers.7.mlp.up_proj", "model.layers.18.self_attn.o_proj", "model.layers.24.self_attn.k_proj", "model.layers.16.self_attn.v_proj", "model.layers.20.mlp.down_proj", "model.layers.24.mlp.up_proj", "model.layers.15.mlp.gate_proj", "model.layers.16.mlp.down_proj", "model.layers.32.mlp.up_proj", "model.layers.20.self_attn.o_proj", "model.layers.8.self_attn.k_proj", "model.layers.18.self_attn.q_proj", "model.layers.15.self_attn.o_proj", "model.layers.24.self_attn.v_proj", "model.layers.29.mlp.gate_proj", "model.layers.26.self_attn.o_proj", "model.layers.8.mlp.up_proj", "model.layers.20.self_attn.k_proj", "model.layers.33.self_attn.k_proj", "model.layers.18.mlp.gate_proj", "model.layers.7.self_attn.k_proj", "model.layers.26.self_attn.k_proj", "model.layers.33.mlp.down_proj", "model.layers.29.self_attn.k_proj", "model.layers.16.self_attn.k_proj", "model.layers.23.self_attn.k_proj", "model.layers.7.mlp.down_proj", "model.layers.16.self_attn.q_proj", "model.layers.25.self_attn.k_proj", "model.layers.29.mlp.up_proj", "model.layers.18.self_attn.k_proj", "model.layers.29.self_attn.v_proj", "model.layers.7.mlp.gate_proj", "model.layers.23.mlp.down_proj", "model.layers.24.self_attn.o_proj", "model.layers.26.mlp.down_proj", "model.layers.25.self_attn.q_proj", "model.layers.16.self_attn.o_proj", "model.layers.24.mlp.down_proj", "model.layers.15.mlp.down_proj", "model.layers.7.self_attn.q_proj", "model.layers.32.self_attn.q_proj", "model.layers.23.self_attn.v_proj", "model.layers.26.mlp.up_proj", "model.layers.8.mlp.gate_proj", "model.layers.15.self_attn.q_proj", "model.layers.20.self_attn.v_proj", "model.layers.33.self_attn.o_proj", "model.layers.32.self_attn.v_proj", "model.layers.33.mlp.up_proj", "model.layers.32.mlp.down_proj", "model.layers.26.self_attn.v_proj", "model.layers.23.self_attn.q_proj", "model.layers.25.self_attn.v_proj", "model.layers.32.self_attn.k_proj", "model.layers.16.mlp.up_proj", "model.layers.33.self_attn.q_proj", "model.layers.8.self_attn.v_proj", "model.layers.23.mlp.gate_proj", "model.layers.8.mlp.down_proj", "model.layers.8.self_attn.o_proj", "model.layers.25.self_attn.o_proj", "model.layers.32.mlp.gate_proj", "model.layers.20.self_attn.q_proj", "model.layers.26.self_attn.q_proj", "model.layers.18.self_attn.v_proj", "model.layers.7.self_attn.v_proj", "model.layers.23.self_attn.o_proj", "model.layers.25.mlp.down_proj", "model.layers.25.mlp.up_proj", "model.layers.24.mlp.gate_proj", "model.layers.33.mlp.gate_proj", "model.layers.32.self_attn.o_proj", "model.layers.7.self_attn.o_proj", "model.layers.20.mlp.up_proj", "model.layers.29.self_attn.q_proj", "model.layers.15.mlp.up_proj", "model.layers.23.mlp.up_proj", "model.layers.15.self_attn.v_proj", "model.layers.25.mlp.gate_proj", "model.layers.29.self_attn.o_proj", "model.layers.18.mlp.down_proj", "model.layers.18.mlp.up_proj" ], "target_parameters": null, "task_type": "CAUSAL_LM", "trainable_token_indices": null, "use_dora": false, "use_qalora": false, "use_rslora": false }