configs/delta_net_340M.json

{
    "attn_mode": "chunk",
    "bos_token_id": 1,
    "conv_size": 4,
    "eos_token_id": 2,
    "expand_k": 1,
    "expand_v": 1,
    "fuse_cross_entropy": true,
    "hidden_act": "swish",
    "hidden_ratio": 4,
    "hidden_size": 1024,
    "initializer_range": 0.006,
    "intermediate_size": null,
    "model_type": "delta_net",
    "norm_eps": 1e-06,
    "norm_first": false,
    "num_heads": 8,
    "num_hidden_layers": 24,
    "qk_activation": "silu",
    "qk_norm": "l2",
    "tie_word_embeddings": false,
    "use_beta": true,
    "use_cache": true,
    "use_gate": false,
    "use_output_norm": true,
    "use_short_conv": true
}