Synchronizing local compiler cache.

.gitattributes

@@ -1040,3 +1040,4 @@ neuronxcc-2.12.68.0+4480452af/MODULE_c735c8c0ea77473fff76+2c2d707e/model.neff fi
 neuronxcc-2.12.68.0+4480452af/MODULE_f3608c91e33c37024bb3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_07f04326f582ccad6a0f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-7b-chat-hf/3671f4f6e9fb55e4d4fd.json

@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8"}}

neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/mistral/mistralai/Mistral-7B-Instruct-v0.1/2b4950cda53848217daa.json

@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 8, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.1", "checkpoint_revision": "9ab9e76e2b09f9f29ea2d56aa5bd139e4445c59e"}}

neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/mistral/mistralai/Mistral-7B-Instruct-v0.1/f4eeffddc98bbf289ce6.json

@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.1", "checkpoint_revision": "9ab9e76e2b09f9f29ea2d56aa5bd139e4445c59e"}}

neuronxcc-2.12.68.0+4480452af/MODULE_07f04326f582ccad6a0f+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.12.68.0+4480452af/MODULE_07f04326f582ccad6a0f+2c2d707e/model.hlo.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce792bd904a07cbe8a2f99a4fc8339d26b3ceb27269304a815bdd521b352a905
+size 410840

neuronxcc-2.12.68.0+4480452af/MODULE_07f04326f582ccad6a0f+2c2d707e/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15dc276e09757bd8b664ab16edcb9d50979e0fcdabe3f2b8634a8118825ad19
+size 10722304

neuronxcc-2.12.68.0+4480452af/MODULE_bcba395a7a65790b3f7b+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.12.68.0+4480452af/MODULE_bcba395a7a65790b3f7b+2c2d707e/model.hlo.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce266eb850667d2625ba8be39cd84bf887ef519587b8861fee1e6db1dbb0fa6d
+size 537246832