{ "_name_or_path": "CodeLlama-7b-hf/config.json", "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "model_type": "llama", "neuron": { "auto_cast_type": "fp16", "batch_size": 1, "compiler_type": "neuronx-cc", "compiler_version": "2.11.0.34+c5231f848", "num_cores": 12, "sequence_length": 2048, "task": "text-generation" }, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.33.2", "use_cache": true, "vocab_size": 32016 }