{ "architectures": [ "SqueezeBertForSequenceClassification" ], "attention_dropout": 0.1, "attention_probs_dropout_prob": 0.1, "embedding_size": 32, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_groups": 4, "intermediate_size": 64, "k_groups": 2, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "squeezebert", "num_attention_heads": 4, "num_hidden_layers": 5, "output_groups": 1, "pad_token_id": 0, "post_attention_groups": 2, "q_groups": 2, "torch_dtype": "float32", "transformers_version": "4.28.0.dev0", "type_vocab_size": 2, "v_groups": 2, "vocab_size": 1124 }