| { | |
| "architectures": [ | |
| "CustomResearchModel" | |
| ], | |
| "architecture": "transformer", | |
| "model_type": "transformer", | |
| "hidden_size": 256, | |
| "num_hidden_layers": 6, | |
| "num_attention_heads": 2, | |
| "intermediate_size": 1024, | |
| "hidden_act": "gelu", | |
| "max_position_embeddings": 256, | |
| "layer_norm_eps": 1e-12, | |
| "checkpoint_status": "initialization-only", | |
| "notes": "Untrained checkpoint for smoke tests; no benchmark claim.", | |
| "use_cache": true, | |
| "torch_dtype": "float32", | |
| "vocab_size": 2048 | |
| } |