{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "dtype": "bfloat16", "eos_token_id": 128261, "head_dim": 64, "hidden_act": "silu", "hidden_size": 576, "initializer_range": 0.02, "intermediate_size": 2304, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 9, "num_hidden_layers": 24, "num_key_value_heads": 3, "pad_token_id": 128001, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 32.0, "rope_type": "linear", "type": "linear" }, "rope_theta": 500000, "tie_word_embeddings": true, "transformers_version": "4.57.6", "use_cache": false, "vocab_size": 194256 }