{ "architectures": [ "LlamaForCausalLM" ], "model_type": "llama", "hidden_size": 512, "intermediate_size": 1408, "num_hidden_layers": 20, "num_attention_heads": 8, "num_key_value_heads": 2, "head_dim": 64, "max_position_embeddings": 2048, "rope_theta": 100000.0, "rope_scaling": null, "rms_norm_eps": 1e-05, "vocab_size": 49152, "tie_word_embeddings": true, "hidden_act": "silu", "attention_bias": false, "mlp_bias": false, "bos_token_id": 1, "eos_token_id": 5, "pad_token_id": 0, "torch_dtype": "float16", "transformers_version": "4.57.0" }