| { | |
| "llm_model": "llm.mnn", | |
| "llm_weight": "llm.mnn.weight", | |
| "backend_type": "cpu", | |
| "thread_num": 4, | |
| "precision": "low", | |
| "memory": "low", | |
| "sampler_type": "penalty", | |
| "penalty": 1.1, | |
| "mllm": { | |
| "backend_type": "cpu", | |
| "thread_num": 4, | |
| "precision": "normal", | |
| "memory": "low" | |
| }, | |
| "speculative_type": "eagle", | |
| "hidden_states": true | |
| } |