diff --git a/.gitattributes b/.gitattributes
index 515956a49057f5aa5785566d7ed02bd8bc5689dc..b273bf1b97d0f6a84ada387b86536c1fd7669285 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1119,3 +1119,19 @@ neuronxcc-2.12.54.0+f631c2365/MODULE_96c74602c6595c924750+2c2d707e/model.neff fi
 neuronxcc-2.12.54.0+f631c2365/MODULE_b731fc0c29ae932dea47+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/63eb7e01e61523a14109.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/63eb7e01e61523a14109.json
new file mode 100644
index 0000000000000000000000000000000000000000..5c074653768a698a2252f95cc44b4e3ef1a87ddd
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/63eb7e01e61523a14109.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "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, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 16, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/8772702e5f5223f7de94.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/8772702e5f5223f7de94.json
new file mode 100644
index 0000000000000000000000000000000000000000..bd9c47581979a45b5f3613290e4887f6bfb352c1
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/8772702e5f5223f7de94.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "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, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/d4dddb49c677c531dcd7.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/d4dddb49c677c531dcd7.json
new file mode 100644
index 0000000000000000000000000000000000000000..8fe29ecf22f9129dac5c07702a3ecb916ceff778
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/d4dddb49c677c531dcd7.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "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, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/f40b584c97bffabc60c2.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/f40b584c97bffabc60c2.json
new file mode 100644
index 0000000000000000000000000000000000000000..c422ee800d350ca6dc77e3e03969d414772a3f1b
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-13b-chat-hf/f40b584c97bffabc60c2.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "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, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/93dc703e497680b4df4d.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/93dc703e497680b4df4d.json
new file mode 100644
index 0000000000000000000000000000000000000000..da9a0fff3bcde018892e939d3e373797511d1189
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/93dc703e497680b4df4d.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, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/b8a63e77583d9b7004b6.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/b8a63e77583d9b7004b6.json
new file mode 100644
index 0000000000000000000000000000000000000000..6462310d2d616efb2b6df5437cf379d8b0fe6667
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/meta-llama/Llama-2-7b-chat-hf/b8a63e77583d9b7004b6.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, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/624ef8314775a5c7b63b.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/624ef8314775a5c7b63b.json
new file mode 100644
index 0000000000000000000000000000000000000000..2556f959472054e0d08abf346ece9d44b8a4f9ce
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/624ef8314775a5c7b63b.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 2048, "intermediate_size": 5504, "num_hidden_layers": 24, "num_attention_heads": 16, "num_key_value_heads": 16, "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": "float32", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/7700052f85791490f5aa.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/7700052f85791490f5aa.json
new file mode 100644
index 0000000000000000000000000000000000000000..7c1e7f1cfd444e84ffb4a17e88e48b0c7716759d
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/7700052f85791490f5aa.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 2048, "intermediate_size": 5504, "num_hidden_layers": 24, "num_attention_heads": 16, "num_key_value_heads": 16, "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": "float32", "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": "bf16", "sequence_length": 1024, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/a737859203da7a2e914f.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/a737859203da7a2e914f.json
new file mode 100644
index 0000000000000000000000000000000000000000..b9c5935fd25412542ff0ab9139f5ff50adc0752a
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/a737859203da7a2e914f.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 2048, "intermediate_size": 5504, "num_hidden_layers": 24, "num_attention_heads": 16, "num_key_value_heads": 16, "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": "float32", "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": 4, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 1024, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/f1c71b95ef4e98e06b6a.json b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/f1c71b95ef4e98e06b6a.json
new file mode 100644
index 0000000000000000000000000000000000000000..68decf11fb4a4828826ad2a41dc0c565bee605b7
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/f1c71b95ef4e98e06b6a.json
@@ -0,0 +1 @@
+{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 2048, "intermediate_size": 5504, "num_hidden_layers": 24, "num_attention_heads": 16, "num_key_value_heads": 16, "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": "float32", "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": 4, "num_cores": 2, "auto_cast_type": "fp32", "sequence_length": 1024, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4"}}
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..05536fdbe1d2b9a9477f3eed4cc11ef18e24c5b2
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a060fccd716fe8f5683c4f86250fbeb8b28943ac48b2e578534dcbf655785f2
+size 437888
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..27fa83255eed8223ffbeaf1658d672b8d836e055
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_1154b678e32b38df568d+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef145ab8e588dddd7332b13131940c9eb328571e94d023b69de380392c236a9f
+size 28232704
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..aade0af53ffca5bfdeef98d2f20d75608fb9bf7a
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e150a71819706f9ed33715d6826037f41a6721e23464e8d39484d0d3f89114
+size 261709
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f3a5c29f5a5f6497445cf6faa816e22ab85e4542
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_13c86804904d0329bc38+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7385093a9a2686451785e49e7fa14bf437f3fc81ed4173dc652e41d9a4e7b97
+size 4629504
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..0c047fe028761811949a90ef4f6988595b06f5af
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4f1189b9b16998156cc3358fb2cd5c3b562e75d0e957a923b819b7f063943d
+size 225998
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0f6180a2703850caf916a7b5888b40a77a641196
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_14fd59d8fbe618033e23+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac14cdf2344ed1500dd809ebba3a0a63c1d521ae596bbef8f57210013e555c8
+size 1823744
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..1867dfeb48fc7b5a43ed6ad54ce4288d63996098
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9545060a46d7deeda64f76eec5868a6e800eb05f08299260c1dfb8eb328f24
+size 256261
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..849fb0f5259da8ea4487f67ebfe5755f7d38e75a
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_1f4c8e3481cc0ab2ecfe+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7bfa2cef67985f8e93c0549ba0a45dc9da2d628cc0311d75374f3c6cd5e169
+size 7681024
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..97c1c4410c17c8d74959fd1052f8c2ec2307af35
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6326e41992e691fa8133fa973fc23ff5a6a1d0ccdc7fcca4b53ff80986da5b
+size 223497
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..077e4748df92120eb21366d9e4a2ad58aa436072
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_22850a3c370343c4e87c+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4123837c77ddb4716ad5674d772cf2f8887dd2bee22f4a3bb3b7caf4cdfe719d
+size 2571264
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..c719518f21cb678b1472dc9d111addcbc2a761ef
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5298d063e0b0217d531e500f2a003e597b37881244b029ca276dc30c632ab0ac
+size 256261
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1c096120169d8b5177cff43f40d6682c25e5b07d
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_23be14b918bd101e0307+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92fdc60f880041fb004c6337777bd150002245d1c7f7a49d50101c86731bba5
+size 7681024
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..306a31aaed04d384a40951c9aa4f339077873d37
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd2dc6439c7e93d0de24d09aeede49422a2702868b539af8aab3e719e9dc150
+size 295537
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..5e6c5092dada92fc0c4b7efece4c787fd6da5a00
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_439cb9059d1a4720adfb+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592ecc0f2e26c2b716fa32a3cef40b6ce7ce4e9211cea329d01e2b05ebbda324
+size 2622464
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..276c4f03cdf218664416836474e7742264bb326a
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8043d11cce1bc62c812cb9df49922f8d59fc1b247b0e3b7dd86262388faf81c6
+size 220730
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..1837dc50c265b47fa44f4739b960bc9ce6848221
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_441b50063b845da3c878+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86b555fa1eb898a9ec0d4244a4ddea536bbbaade14712509d56fc3705a736f1
+size 1793024
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..cdb7c4747b03856a600e3ddef727337fee596785
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bf29b9c97232e2e1bbdeb1bd25b9011cd0aee2a5fed300fea50a39c2228c54
+size 287274
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..48b21ca89b684af696ad3bfe5e4b97dbd53856ed
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_62ebf9bdd149ff8c97d9+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8b786fdb966254b9d9ecdfac8b4dab2d98eb89d56d1bbac419af1e4e307d5d
+size 3103744
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_9278928fd84a21a91a59+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_9278928fd84a21a91a59+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_9278928fd84a21a91a59+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_9278928fd84a21a91a59+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_9278928fd84a21a91a59+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..f749ece7f01c736cefa246782030962d7a92301d
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_9278928fd84a21a91a59+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07dd146c5284a257d6b40fdaf686ea6111b4f605a9984a5b61e0d65094e77127
+size 295537
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..319404c3d7cde709daa24858b611044b10dc760f
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523773fbfb5fcb65958793eef10cede18b4f29eb0000dd8b5eadfa28d08a9c0c
+size 225998
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f6beac0f85e067b1783796730d9263d7add32692
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_9b8a4b44cab7fd6a36b6+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70590c26bb648b4fcbaa924459c803db721af42cbd8d63ed8ee6badd36ec0100
+size 1731584
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..0986a9a2a8b755dd08df7f4e68d699d1b93de562
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02643af119934dfbf6104863ca64d217c8374d48d944802f5a74714b8566011
+size 225998
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..651ff786261b4f5a545bb16426f3b80aeb4b0df6
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_bd284532da36dbde1d9d+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a786ade92464a476f97e1b945c349ac991ab5bf4591753e34878b472b18eb31f
+size 1680384
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b0e45b762ea96443d8c28cc00e45f7260527f13f
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eee6818db4e307c3ed592714a5c1a21a4d696ab4d3f9650bcc3160b93bef0a9
+size 493747
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..892a7995cfff7c6fa485d409be293684b68e664b
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_dd3fcd08d9d80a1eff7d+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45ec0ae33707e270c0fd8b1ac7484acb9028a204eba040441c761ea8e32b3fc
+size 7465984
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..a1cee892ad53c40c8a5acbcdf3a3ac8b78592880
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6e200059bab3e36b02b738de968e2e164ec97b384c3e00c192b240b318c6da
+size 223497
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..9e9ef337d118f5adbfbd185e9086178c5aa535e7
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_e342da015657e3ad5e30+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938f3131e88c6e5654a974e26ba27da3afb045a77fed23164896bad4c6406e1f
+size 2284544
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..b733df7f4414bf6b5a744d8ff1855ee1a9046978
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876698de9a90ca96dc16358568e6e0f3c49fc90c35ecb3b13dc68fa3ff5745d6
+size 223497
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4a2ae913c76e189c5ab83c394bb4cba9ac0c78c3
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_e6d595b44e212a97a91e+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89be47501ccfe21f3a24db91972a607537c9cfd07753322761baaaf7bfe1e529
+size 1864704
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..53f070ff76f028a2476f567a705c1880ea009a2b
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3512690aa43bfed7205bb6220270f8d78d1d255f0a6eb2a90950ae10228ef737
+size 287274
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..4a776efdc59b2ea469bdbf690c16ebe2cb91f9e4
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_eb5999be2069b95cacd6+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85028e4b4162e763ee88815453e9739fdc84fd0645ec579c884b86626a96cb4
+size 3441664
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..da1706d45c627aa70154e7966b8eec6b9003c585
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d46817d012c6cbbbf3a09ea7bd52a95c430600e03e6c80b33cf1db2b96e596
+size 225998
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.neff b/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..f355c2340504cb9c3e736130a608052061299a7c
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_f0ced8f5974d435da438+2c2d707e/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6fe3778edcf7f7a9c7c9f69e098ce2580d4fb21343617d34e001f8cece5903
+size 1700864
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_fb71a9057cac250df758+2c2d707e/compile_flags.txt b/neuronxcc-2.12.68.0+4480452af/MODULE_fb71a9057cac250df758+2c2d707e/compile_flags.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3fd72d102654c531414d7f703987c9729e8cb438
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_fb71a9057cac250df758+2c2d707e/compile_flags.txt
@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none
\ No newline at end of file
diff --git a/neuronxcc-2.12.68.0+4480452af/MODULE_fb71a9057cac250df758+2c2d707e/model.hlo.pb b/neuronxcc-2.12.68.0+4480452af/MODULE_fb71a9057cac250df758+2c2d707e/model.hlo.pb
new file mode 100644
index 0000000000000000000000000000000000000000..eb523da6b35f63409f8f1bbd94d8c6f6db8be895
--- /dev/null
+++ b/neuronxcc-2.12.68.0+4480452af/MODULE_fb71a9057cac250df758+2c2d707e/model.hlo.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8681c3565719bef1860533d1018e247ed6a3f6323df0a04b0812dbafed8a62
+size 261709