moshi_lm_kwargs.json

{
    "dim": 4096,
    "text_card": 32000,
    "existing_text_padding_id": 3,
    "n_q": 16,
    "dep_q": 8,
    "card": 2048,
    "num_heads": 32,
    "num_layers": 32,
    "hidden_scale": 4.125,
    "causal": true,
    "layer_scale": null,
    "context": 3000,
    "max_period": 10000,
    "gating": "silu",
    "norm": "rms_norm_f32",
    "positional_embedding": "rope",
    "depformer_dim": 1024,
    "depformer_dim_feedforward": 4224,
    "depformer_num_heads": 16,
    "depformer_num_layers": 6,
    "depformer_layer_scale": null,
    "depformer_multi_linear": true,
    "depformer_context": 8,
    "depformer_max_period": 10000,
    "depformer_gating": "silu",
    "depformer_pos_emb": "none",
    "depformer_weights_per_step": true,
    "delays": [
        0,
        0,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ]
}