config.json

{
    "architectures": [
        "Glm4ForCausalLM"
    ],
    "attention_bias": true,
    "attention_dropout": 0.0,
    "eos_token_id": [
        151329,
        151336,
        151338
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 13696,
    "max_position_embeddings": 32768,
    "model_type": "glm4",
    "num_attention_heads": 32,
    "num_hidden_layers": 40,
    "num_key_value_heads": 2,
    "pad_token_id": 151329,
    "partial_rotary_factor": 0.5,
    "rms_norm_eps": 1e-05,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.52.0.dev0",
    "use_cache": true,
    "vocab_size": 151552,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.2.9",
        "bits": 4.0,
        "head_bits": 6,
        "calibration": {
            "rows": 115,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}