{ "alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "Locutusque/TinyMistral-248M", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "loftq_config": {}, "lora_alpha": 16, "lora_dropout": 0.05, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "r": 16, "rank_pattern": {}, "revision": null, "target_modules": [ "model.layers.2.self_attn.k_proj", "model.layers.8.mlp.down_proj", "model.layers.8.mlp.up_proj", "model.layers.7.self_attn.o_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.o_proj", "model.layers.4.mlp.gate_proj", "model.layers.4.self_attn.q_proj", "model.layers.6.mlp.up_proj", "model.layers.6.mlp.down_proj", "model.layers.2.mlp.gate_proj", "model.layers.5.self_attn.v_proj", "model.layers.7.mlp.down_proj", "model.layers.7.mlp.up_proj", "model.layers.1.self_attn.o_proj", "lm_head", "model.layers.5.mlp.up_proj", "model.layers.0.mlp.gate_proj", "model.layers.9.self_attn.k_proj", "model.layers.2.self_attn.o_proj", "model.layers.4.mlp.up_proj", "model.layers.1.self_attn.k_proj", "model.layers.3.self_attn.v_proj", "model.layers.10.mlp.down_proj", "model.layers.10.mlp.gate_proj", "model.layers.6.self_attn.q_proj", "model.layers.3.self_attn.k_proj", "model.layers.9.mlp.up_proj", "model.layers.7.self_attn.k_proj", "model.layers.3.self_attn.q_proj", "model.layers.8.self_attn.o_proj", "model.layers.10.mlp.up_proj", "model.layers.7.self_attn.q_proj", "model.layers.0.mlp.down_proj", "model.layers.7.mlp.gate_proj", "model.layers.3.mlp.down_proj", "model.layers.10.self_attn.o_proj", "model.layers.4.self_attn.o_proj", "model.layers.3.self_attn.o_proj", "model.layers.5.self_attn.k_proj", "model.layers.1.self_attn.q_proj", "model.layers.5.self_attn.o_proj", "model.layers.11.mlp.down_proj", "model.layers.9.self_attn.v_proj", "model.layers.1.self_attn.v_proj", "model.layers.2.self_attn.v_proj", "model.layers.4.mlp.down_proj", "model.layers.10.self_attn.q_proj", "model.layers.0.self_attn.q_proj", "model.layers.3.mlp.gate_proj", "model.layers.9.self_attn.o_proj", "model.layers.8.self_attn.q_proj", "model.layers.10.self_attn.v_proj", "model.layers.3.mlp.up_proj", "model.layers.8.self_attn.v_proj", "model.layers.8.self_attn.k_proj", "model.layers.9.mlp.down_proj", "model.layers.11.mlp.up_proj", "model.layers.4.self_attn.k_proj", "model.layers.11.self_attn.v_proj", "model.layers.10.self_attn.k_proj", "model.layers.0.mlp.up_proj", "model.layers.1.mlp.down_proj", "model.layers.11.self_attn.q_proj", "model.layers.1.mlp.gate_proj", "model.layers.5.self_attn.q_proj", "model.layers.7.self_attn.v_proj", "model.layers.5.mlp.down_proj", "model.layers.9.mlp.gate_proj", "model.layers.11.self_attn.k_proj", "model.layers.9.self_attn.q_proj", "model.layers.2.mlp.up_proj", "model.layers.4.self_attn.v_proj", "model.layers.11.self_attn.o_proj", "model.layers.1.mlp.up_proj", "model.layers.0.self_attn.k_proj", "model.layers.5.mlp.gate_proj", "model.layers.6.mlp.gate_proj", "model.layers.8.mlp.gate_proj", "model.layers.0.self_attn.v_proj", "model.layers.6.self_attn.v_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.mlp.down_proj", "model.layers.0.self_attn.o_proj", "model.layers.11.mlp.gate_proj" ], "task_type": "CAUSAL_LM", "use_rslora": false }