{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "dtype": "float32", "eos_token_id": 1, "head_dim": 32, "hidden_act": "silu", "hidden_size": 192, "initializer_range": 0.02, "intermediate_size": 512, "max_position_embeddings": 256, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 6, "num_hidden_layers": 8, "num_key_value_heads": 3, "pad_token_id": 3, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_parameters": { "factor": 2.0, "rope_theta": 1000.0, "rope_type": "dynamic" }, "tie_word_embeddings": true, "transformers_version": "5.8.0", "use_cache": true, "vocab_size": 4096 }