config.json

{
    "architectures": [
        "Mamba2ForCausalLM"
    ],
    "bos_token_id": 0,
    "chunk_size": 256,
    "conv_kernel": 4,
    "eos_token_id": 0,
    "expand": 2,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.1,
    "intermediate_size": 8192,
    "layer_norm_epsilon": 1e-05,
    "model_type": "mamba2",
    "n_groups": 8,
    "norm_before_gate": true,
    "num_heads": 128,
    "num_hidden_layers": 64,
    "pad_token_id": 0,
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8
    },
    "rescale_prenorm_residual": false,
    "residual_in_fp32": true,
    "rms_norm": true,
    "state_size": 128,
    "tie_word_embeddings": false,
    "time_step_floor": 0.0001,
    "time_step_init_scheme": "random",
    "time_step_limit": [
        0.0,
        Infinity
    ],
    "time_step_max": 0.1,
    "time_step_min": 0.001,
    "time_step_rank": 256,
    "time_step_scale": 1.0,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.44.0.dev0",
    "use_bias": false,
    "use_cache": true,
    "use_conv_bias": true,
    "vocab_size": 32768
}