{ "_name_or_path": "hf-internal-testing/tiny-random-AlbertModel", "architectures": [ "AlbertModel" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 2, "classifier_dropout_prob": 0.1, "embedding_size": 128, "eos_token_id": 3, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 36, "initializer_range": 0.02, "inner_group_num": 1, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "albert", "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": "albert", "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "output_names": [ "logits" ], "static_batch_size": 1, "static_sequence_length": 32 }, "num_attention_heads": 6, "num_hidden_groups": 6, "num_hidden_layers": 6, "pad_token_id": 0, "position_embedding_type": "absolute", "task": "token-classification", "torchscript": true, "transformers_version": "4.41.1", "type_vocab_size": 16, "vocab_size": 30000 }