| { | |
| "_name_or_path": "aurora_base", | |
| "architectures": [ | |
| "AuroraForPrediction" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_aurora.AuroraConfig", | |
| "AutoModelForCausalLM": "modeling_aurora.AuroraForPrediction" | |
| }, | |
| "dropout_rate": 0.2, | |
| "hidden_act": "silu", | |
| "hidden_size": 256, | |
| "token_len": 48, | |
| "intermediate_size": 512, | |
| "max_position_embeddings": 10000, | |
| "model_type": "aurora", | |
| "num_attention_heads": 8, | |
| "num_enc_layers": 1, | |
| "num_dec_layers": 9, | |
| "rope_theta": 10000, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.1", | |
| "num_sampling_steps": 50, | |
| "flow_loss_depth": 3, | |
| "diffusion_batch_mul": 4, | |
| "threshold_ratio": [0.2, 0.3, 0.4, 0.5], | |
| "mask_ratio": 0.5, | |
| "norm_mode": "batch", | |
| "num_prototypes": 1000, | |
| "num_retriever_enc_layers": 1, | |
| "num_retriever_dec_layers": 1, | |
| "num_text_cross_layers": 1, | |
| "num_vision_cross_layers": 1, | |
| "num_text_connect_layers": 1, | |
| "num_vision_connect_layers": 1, | |
| "num_distill": 10 | |
| } |