Synchronizing local compiler cache.

neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.25.dev0/inference/llama/m-a-p/OpenCodeInterpreter-DS-6.7B/2d9951810006a2012453.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 32013, "eos_token_id": 32021, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "m-a-p/OpenCodeInterpreter-DS-6.7B", "checkpoint_revision": "60b89884df814590abd76757a6db4a527cbdfc91", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": {"factor": 4.0, "rope_type": "linear", "type": "linear"}, "rope_theta": 100000, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": false, "vocab_size": 32256}