| { | |
| "name": "tiny-30m-byte", | |
| "vocab_size": 256, | |
| "d_model": 512, | |
| "embed_dim": 512, | |
| "n_layers": 10, | |
| "n_loops": 1, | |
| "n_heads": 8, | |
| "n_kv_heads": 2, | |
| "ffn_hidden": 1408, | |
| "max_seq_len": 1024, | |
| "rope_theta": 10000.0, | |
| "norm_eps": 1e-05, | |
| "tie_embeddings": true, | |
| "dropout": 0.0, | |
| "qk_norm": false, | |
| "conv_kernel": 3, | |
| "layer_types": null | |
| } |