Synchronizing local compiler cache.

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/unsloth/Llama-3.2-1B-Instruct/29929e0fe636f4e5af91.json

@@ -0,0 +1,36 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": null,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.17.194.0+d312836f/MODULE_7a4e910c3dbc7ccf8eb3+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e56596001e148a997be5c08e33d42ead54de9bb71a322ecb9fb918a31e1e6ca
+oid sha256:98bf65cdce6d9e04670d52b876bcbf1ef63801f425a23366708e18485a789902
 size 29072384

neuronxcc-2.17.194.0+d312836f/MODULE_f91cd98a64f373af274d+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be60c6c56fc5e842770cf2425fe5f78961a96bf5225d482509659dcedde23207
+oid sha256:f8ffe7e9a80e9bb621d91d69c3ce56f8841902928b64fab653f11cc9762806af
 size 2448384