{ "architectures": [ "LlamaBidirectionalModel" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "llama_bidirectional_model.LlamaBidirectionalConfig", "AutoModel": "llama_bidirectional_model.LlamaBidirectionalModel" }, "bos_token_id": 128000, "dtype": "bfloat16", "eos_token_id": 128001, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama_bidirec", "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": null, "pooling": "avg", "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_parameters": { "factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_theta": 500000.0, "rope_type": "llama3" }, "temperature": 1.0, "tie_word_embeddings": true, "transformers_version": "5.5.0", "use_bidirectional_attention": true, "use_cache": true, "vocab_size": 128256 }