{ "architectures": [ "CyclicFormerForCausalLM" ], "cyclic_size": 200, "drop_prob": 0.1, "hidden_size": 200, "initializer_range": 0.1, "model_type": "cyclicformer", "n_loop": 3, "num_attention_heads": 4, "num_hidden_layers": 4, "rms_norm_eps": 1e-06, "torch_dtype": "float32", "transformers_version": "4.41.2", "use_cache": false, "vocab_size": 50257 }