config.json

{
    "architectures": [
        "BaichuanM1ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_baichuan.BaichuanM1Config",
        "AutoModelForCausalLM": "modeling_baichuan.BaichuanM1ForCausalLM"
    },
    "bos_token_id": 1,
    "conv_window": 2,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 17408,
    "max_position_embeddings": 32768,
    "model_max_length": 32768,
    "model_type": "baichuan_m1",
    "num_attention_heads": 20,
    "num_hidden_layers": 40,
    "num_key_value_heads": 2,
    "num_swa_attention_heads": 40,
    "num_swa_key_value_heads": 8,
    "pad_token_id": 0,
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8
    },
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "sliding_window": 8192,
    "sliding_window_layers": [
        1,
        3,
        5,
        7,
        9,
        11,
        13,
        15,
        17,
        19,
        21,
        23,
        25,
        27,
        29,
        31,
        33,
        35,
        37,
        39
    ],
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.48.1",
    "use_cache": true,
    "vocab_size": 133120
}