config.json

{
    "llm_model": "llm.mnn",
    "llm_weight": "llm.mnn.weight",
    "backend_type": "cpu",
    "thread_num": 4,
    "precision": "low",
    "memory": "low",
    "sampler_type": "mixed",
    "temperature": 0.8,
    "top_k": 40,
    "top_p": 0.9,
    "min_p": 0.05,
    "tfs_z": 1.0,
    "typical": 0.95,
    "repetition_penalty": 1.0,
    "presence_penalty": 0.0,
    "frequency_penalty": 0.0,
    "penalty_window": 0,
    "n_gram": 8,
    "ngram_factor": 1.0,
    "tokenizer_file": "tokenizer.mtok",
    "mllm": {
        "backend_type": "cpu",
        "thread_num": 4,
        "precision": "normal",
        "memory": "low"
    },
    "per_layer_embedding_file": "ple_embeddings_int4.bin"
}