configs/gla_7B.json

{
    "attn": null,
    "attn_mode": "chunk",
    "bos_token_id": 1,
    "eos_token_id": 2,
    "expand_k": 0.5,
    "expand_v": 1,
    "fuse_cross_entropy": true,
    "fuse_norm": true,
    "hidden_act": "swish",
    "hidden_ratio": 4,
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "model_type": "gla",
    "norm_eps": 1e-06,
    "num_heads": 16,
    "num_hidden_layers": 32,
    "tie_word_embeddings": false,
    "use_cache": true,
    "use_gk": true,
    "use_gv": false,
    "use_output_gate": true,
    "use_short_conv": false
}