Synchronizing local compiler cache.

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/f54906e314fbdb1f9711.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "checkpoint_revision": "74fbf131a939963dd1e244389bb61ad0d0440a4d", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ebf416056af21adc3bc3d71057c68e6353e2f8d7e384b6741366543b8ec0de
+oid sha256:55254fa7cc84ed2c53d21177d4593a3d67aee29ac21b8ea690b080b327d622d6
 size 7803904

neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7c98cc9bf2a57760705a932a6f1c62de9f0d31c125e997d8b03d2ae2ad602a
+oid sha256:5ee9cc60f35b7a6d07a396cdb7952d261dfb276e4bf4bab8c5ad41e7ad16b995
 size 5970944