| { | |
| "adapter_config": { | |
| "r": 16, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj" | |
| ], | |
| "description": "Balanced performance and efficiency" | |
| }, | |
| "training_config": { | |
| "dataset_format": "conversations", | |
| "max_seq_length": 2048, | |
| "num_epochs": 3, | |
| "batch_size": 4, | |
| "learning_rate": 0.0002 | |
| }, | |
| "base_model": "Qwen/Qwen2.5-3B-Instruct", | |
| "created_by": "MLResearcher" | |
| } |