| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "embedding_size": 768, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 512, | |
| "model_type": "squeezebert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "type_vocab_size": 2, | |
| "vocab_size": 30528, | |
| "q_groups": 4, | |
| "k_groups": 4, | |
| "v_groups": 4, | |
| "post_attention_groups": 1, | |
| "intermediate_groups": 4, | |
| "output_groups": 4 | |
| } | |