config.json

{
    "max_new_tokens": 8192,
    "llm_model": "llm.mnn",
    "llm_weight": "llm.mnn.weight",
    "backend_type": "cpu",
    "thread_num": 4,
    "precision": "low",
    "memory": "low",
    "sampler_type": "mixed",
    "mixed_samplers": [
        "penalty",
        "topK",
        "topP",
        "min_p",
        "temperature"
    ],
    "penalty": 1.1,
    "temperature": 1.0,
    "topP": 0.95,
    "topK": 20,
    "min_p": 0,
    "mllm": {
        "backend_type": "cpu",
        "thread_num": 4,
        "precision": "normal",
        "memory": "low"
    },
    "jinja": {
        "context": {
            "enable_thinking": true
        }
    }
}