config.json

{
    "architectures": [
        "Gemma2ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": 50.0,
    "bos_token_id": 2,
    "cache_implementation": "hybrid",
    "eos_token_id": 1,
    "final_logit_softcapping": 30.0,
    "head_dim": 128,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 4608,
    "initializer_range": 0.02,
    "intermediate_size": 36864,
    "max_position_embeddings": 8192,
    "model_type": "gemma2",
    "num_attention_heads": 32,
    "num_hidden_layers": 46,
    "num_key_value_heads": 16,
    "pad_token_id": 0,
    "query_pre_attn_scalar": 144,
    "rms_norm_eps": 1e-06,
    "rope_theta": 10000.0,
    "sliding_window": 4096,
    "sliding_window_size": 4096,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.42.0.dev0",
    "use_cache": true,
    "vocab_size": 256000,
    "_attn_implementation": "eager",
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.1.6",
        "bits": 4.5,
        "head_bits": 6,
        "calibration": {
            "rows": 115,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}