{ "architectures": [ "RMSN" ], "model_type": "rmsn", "vocab_size": 49152, "dim": 1152, "depth": 16, "slots": 64, "seq_len": 512, "num_parameters": 293031984, "tokenizer_class": "PreTrainedTokenizerFast", "tokenizer_name": "HuggingFaceTB/cosmo2-tokenizer", "val_ppl": 68.1, "val_lyap": -0.9714 }