{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 32768, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "quantization": { "group_size": 64, "bits": 4 }, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 6315088.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.41.2", "use_cache": true, "use_flash_attention_2": true, "vocab_size": 128256 }