{ "_name_or_path": "hf-internal-testing/tiny-random-ConvBertModel", "architectures": [ "ConvBertModel" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "conv_kernel_size": 9, "embedding_size": 768, "eos_token_id": 2, "head_ratio": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "convbert", "neuron": { "auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.14.182.0+a56cbff7", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": true, "inline_weights_to_neff": true, "input_names": [ "input_ids", "attention_mask", "token_type_ids" ], "model_type": "convbert", "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "output_names": [ "last_hidden_state" ], "static_batch_size": 1, "static_sequence_length": 32 }, "num_attention_heads": 4, "num_groups": 1, "num_hidden_layers": 5, "pad_token_id": 0, "task": "feature-extraction", "torchscript": true, "transformers_version": "4.41.1", "type_vocab_size": 16, "vocab_size": 1124 }