mlc-chat-config.json

{
    "model_lib": "Qra-7b-q4f32_0",
    "local_id": "Qra-7b-q4f32_0",
    "conv_template": "llama-2",
    "temperature": 0.7,
    "repetition_penalty": 1.0,
    "top_p": 0.95,
    "mean_gen_len": 128,
    "max_gen_len": 4096,
    "num_shards": 1,
    "use_presharded_weights": false,
    "shift_fill_factor": 0.3,
    "tokenizer_files": [
        "tokenizer.model",
        "tokenizer.json"
    ],
    "model_category": "llama",
    "model_name": "Qra-7b",
    "vocab_size": 32000,
    "prefill_chunk_size": -1,
    "max_window_size": 4096
}