{ "architectures": [ "Transformer" ], "bias": false, "bilinear": true, "scale_attn": false, "d_hidden": 3072, "d_model": 768, "gate": null, "tokenizer": "ts-4096", "dataset": "tinystories", "n_ctx": 256, "n_head": 12, "n_layer": 8, "normalization": true, "torch_dtype": "float32", "transformers_version": "4.45.1" }