tiny-qwen-5m-simplewiki / mixed_config.json
av-codes's picture
Upload folder using huggingface_hub
f82e713 verified
Raw
History Blame Contribute Delete
213 Bytes
{
"vocab_size": 512,
"dim": 256,
"n_layers": 7,
"n_heads": 4,
"intermediate_size": 704,
"max_seq_len": 1024,
"rope_theta": 10000.0,
"rms_norm_eps": 1e-06,
"dropout": 0.05,
"tie_weights": true
}