{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"compiler_version": "2.13.68.0+6dfecc895", "input_specs": {"attention_mask": [2, 512], "input_ids": [2, 512], "labels": [2, 512]}, "model_class": "MistralForCausalLM", "num_neuron_cores_per_node": 64, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 8, "training": false}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}