configs/transformer_16M_8192.json

{
    "model_type": "transformer",
    "attention_bias": false,
    "bos_token_id": 1,
    "clamp_min": null,
    "eos_token_id": 2,
    "fuse_cross_entropy": true,
    "fuse_norm": true,
    "hidden_act": "swish",
    "hidden_ratio": 4,
    "hidden_size": 256,
    "state_size": 16,
    "initializer_range": 0.02,
    "intermediate_size": null,
    "max_position_embeddings": 8192,
    "num_heads": 4,
    "num_kv_heads": 4,
    "num_hidden_layers": 10,
    "norm_eps": 1e-06,
    "tie_word_embeddings": true,
    "transformers_version": "4.38.2",
    "use_cache": true,
    "use_gk": true,
    "use_gv": false,
    "vocab_size": 32000
}