config.json

{
    "architectures": [
        "MiniCPMForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_minicpm.MiniCPMConfig",
        "AutoModel": "modeling_minicpm.MiniCPMModel",
        "AutoModelForCausalLM": "modeling_minicpm.MiniCPMForCausalLM",
        "AutoModelForSeq2SeqLM": "modeling_minicpm.MiniCPMForCausalLM",
        "AutoModelForSequenceClassification": "modeling_minicpm.MiniCPMForSequenceClassification"
    },
    "bos_token_id": 1,
    "dim_model_base": 256,
    "eos_token_id": 73440,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.1,
    "intermediate_size": 16384,
    "max_position_embeddings": 65536,
    "mlp_bias": false,
    "model_type": "minicpm",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 2,
    "pad_token_id": 73440,
    "pretraining_tp": 1,
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
        "factor": 1.0,
        "long_factor": [
            0.9982316082870437,
            1.033048153422584,
            1.0749920956484724,
            1.1255096879436193,
            1.1863348602111476,
            1.259543828902579,
            1.3476188888731149,
            1.4535223827776373,
            1.5807816745852985,
            1.7335856049489526,
            1.9168922912975785,
            2.1365471404135326,
            2.3994084200118646,
            2.713475511863602,
            3.0880118452194134,
            3.533650295140154,
            4.062463396503134,
            4.687974098908333,
            5.425075306704039,
            6.289818967956352,
            7.29902962722721,
            8.469695779093664,
            9.81809877306655,
            11.358657902065282,
            13.102505860712087,
            15.055862949967128,
            17.218348131364184,
            19.581439255386453,
            22.127353314656723,
            24.828633849376587,
            27.6486820771775,
            30.54334096108829,
            33.46345345363812,
            36.358112337548896,
            39.17816056534983,
            41.879441100069684,
            44.425355159339965,
            46.78844628336223,
            48.95093146475928,
            50.90428855401433,
            52.648136512661125,
            54.18869564165987,
            55.537098635632745,
            56.7077647874992,
            57.71697544677006,
            58.58171910802236,
            59.31882031581807,
            59.94433101822328,
            60.47314411958625,
            60.918782569507,
            61.29331890286281,
            61.60738599471455,
            61.87024727431288,
            62.089902123428836,
            62.27320880977746,
            62.42601274014111,
            62.55327203194878,
            62.65917552585329,
            62.74725058582382,
            62.82045955451526,
            62.88128472678279,
            62.931802319077946,
            62.97374626130382,
            63.008562806439365
        ],
        "original_max_position_embeddings": 65536,
        "rope_type": "longrope",
        "short_factor": [
            0.9982316082870437,
            1.033048153422584,
            1.0749920956484724,
            1.1255096879436193,
            1.1863348602111476,
            1.259543828902579,
            1.3476188888731149,
            1.4535223827776373,
            1.5807816745852985,
            1.7335856049489526,
            1.9168922912975785,
            2.1365471404135326,
            2.3994084200118646,
            2.713475511863602,
            3.0880118452194134,
            3.533650295140154,
            4.062463396503134,
            4.687974098908333,
            5.425075306704039,
            6.289818967956352,
            7.29902962722721,
            8.469695779093664,
            9.81809877306655,
            11.358657902065282,
            13.102505860712087,
            15.055862949967128,
            17.218348131364184,
            19.581439255386453,
            22.127353314656723,
            24.828633849376587,
            27.6486820771775,
            30.54334096108829,
            33.46345345363812,
            36.358112337548896,
            39.17816056534983,
            41.879441100069684,
            44.425355159339965,
            46.78844628336223,
            48.95093146475928,
            50.90428855401433,
            52.648136512661125,
            54.18869564165987,
            55.537098635632745,
            56.7077647874992,
            57.71697544677006,
            58.58171910802236,
            59.31882031581807,
            59.94433101822328,
            60.47314411958625,
            60.918782569507,
            61.29331890286281,
            61.60738599471455,
            61.87024727431288,
            62.089902123428836,
            62.27320880977746,
            62.42601274014111,
            62.55327203194878,
            62.65917552585329,
            62.74725058582382,
            62.82045955451526,
            62.88128472678279,
            62.931802319077946,
            62.97374626130382,
            63.008562806439365
        ],
        "type": "longrope"
    },
    "rope_theta": 10000.0,
    "scale_depth": 1.4,
    "scale_emb": 12,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.53.3",
    "use_cache": true,
    "vocab_size": 73448
}