{ "activation": "gelu", "architectures": [ "DistilBertForQuestionAnswering" ], "attention_dropout": 0.1, "dim": 768, "dropout": 0.1, "hidden_dim": 3072, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 6, "output_past": true, "pad_token_id": 0, "qa_dropout": 0.1, "rknn": { "model.rknn": { "batch_size": 1, "custom_string": null, "dynamic_input": null, "float_dtype": "float16", "inputs_yuv_fmt": null, "max_seq_length": 512, "mean_values": null, "model_input_names": [ "input_ids", "attention_mask" ], "opset": 19, "optimization": { "compress_weight": false, "enable_flash_attention": true, "model_pruning": false, "optimization_level": 0, "remove_reshape": false, "remove_weight": false, "sparse_infer": false }, "quantization": { "auto_hybrid_cos_thresh": 0.98, "auto_hybrid_euc_thresh": null, "dataset_columns": null, "dataset_name": null, "dataset_size": 128, "dataset_split": null, "dataset_subset": null, "do_quantization": false, "quant_img_RGB2BGR": false, "quantized_algorithm": "normal", "quantized_dtype": "w8a8", "quantized_hybrid_level": 0, "quantized_method": "channel" }, "rktransformers_version": "0.3.0", "single_core_mode": false, "std_values": null, "target_platform": "rk3588", "task": "question-answering", "task_kwargs": null } }, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": true, "tie_weights_": true, "torch_dtype": "float32", "transformers_version": "4.55.4", "vocab_size": 28996 }