Synchronizing local compiler cache.

neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/abacusai/Smaug-72B-v0.1/0d8e57049c33c5b5c6d9.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": true, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 24576, "max_position_embeddings": 32768, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "abacusai/Smaug-72B-v0.1", "checkpoint_revision": "a1d657156f82c24b670158406378648233487011", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 64, "pad_token_id": 151643, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "seq_length": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 152064}