| { | |
| "architectures": [ | |
| "Transformer" | |
| ], | |
| "attention2": true, | |
| "bias": true, | |
| "bilinear": true, | |
| "d_hidden": 2048, | |
| "d_model": 512, | |
| "dtype": "float32", | |
| "gate": null, | |
| "n_ctx": 256, | |
| "n_head": 8, | |
| "n_layer": 6, | |
| "norm_bias": true, | |
| "normalization": true, | |
| "pad_token_id": 2, | |
| "repo": null, | |
| "tokenizer": "ts-4096", | |
| "transformers_version": "4.57.3" | |
| } | |