Synchronizing local compiler cache.

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/michaelbenayoun/llama-2-tiny-4kv-heads-4layers-random/5095e05b335533413a68.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 128, "is_decoder": true, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"compiler_version": "2.15.128.0+56dc5a86", "input_specs": {"attention_mask": [1, 128], "input_ids": [1, 128], "labels": [1, 128]}, "model_class": "LlamaForCausalLM", "num_neuron_cores_per_node": 2, "pipeline_parallel_size": 1, "precision": "float32", "tensor_parallel_size": 2, "training": true}, "num_attention_heads": 32, "num_hidden_layers": 4, "num_key_value_heads": 4, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.15.128.0+56dc5a86/MODULE_2523944151895168973+cc298dfa/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_2523944151895168973+cc298dfa/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b1d3adde6610c13734530fb833dfccdad0a494f68f2e014c79f6ddbc7474d8
+size 153501

neuronxcc-2.15.128.0+56dc5a86/MODULE_5498874236757814731+cc298dfa/compile_flags.json

@@ -0,0 +1 @@
+["--model-type=transformer"]

neuronxcc-2.15.128.0+56dc5a86/MODULE_5498874236757814731+cc298dfa/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3abc922ca4fbd1bf20d24a5cdfb583ab4a945a8bcf531e96a7f8844c1f63379
+size 153127