{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 33, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 8, "num_hidden_layers": 4, "num_key_value_heads": 2, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 32.0, "high_freq_factor": 0.0078125, "low_freq_factor": 0.001953125, "original_max_position_embeddings": 16, "rope_type": "llama3" }, "rope_theta": 500000, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 2051 }