Synchronizing local compiler cache.

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev2/inference/llama/unsloth/Llama-3.2-1B-Instruct/fd812d26a7e8213812ef.json

@@ -0,0 +1 @@
+{"_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": {"all_reduce_dtype": null, "allow_flash_attention": true, "attention_layout": "BSH", "attn_output_transposed": false, "auto_cast_type": "fp16", "backend": "hlo", "batch_size": 4, "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", "checkpoint_revision": "9b58d4a36161a1e49ecf0a69d20b2736fef8e438", "collectives_layout": "HSB", "continuous_batching": true, "fuse_qkv": true, "group_query_attention": "shard-over-heads", "log_softmax_scores": false, "neuronxcc_version": "2.16.372.0+4a9b2326", "optimum_neuron_version": "0.2.0.dev2", "output_all_logits": false, "sequence_length": 4096, "tp_degree": 2}, "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}