Synchronizing local compiler cache.

neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev2/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/9dd87edc852713b393bd.json

@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 4, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}

neuronxcc-2.15.143.0+e39249ad/MODULE_13b72878753f07dee959+39f12043/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c1674712e02f7f71b2149d48d58a1cb1e81ffbfbbecfdc37dc285444111ce6
+oid sha256:64ba888e437b73920b2d50425446363d6130841997d61b01efd1986369933c55
 size 7158784

neuronxcc-2.15.143.0+e39249ad/MODULE_7e583a05cc455ec1b4a2+39f12043/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864bdf8a1c65da29e4ab598cd3aaa2d7d276cea7f7fd3b1862dfcf5773d6bc8a
+oid sha256:6a5e5d57d4bc89a87a5537304eeee857ef072e57d1808169fad715f8785cb287
 size 2806784