Add Neuron cache for cache_mirror (#4)

- Add Neuron cache for cache_mirror (47e85cd20cf1d3d3a7c9797c1ee7fc66654f4ff1)

.gitattributes

@@ -44,3 +44,4 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_7bebb00dc9acea881b5a/model.neuron filter=lf
 neuronxcc-2.16.372.0+4a9b2326/MODULE_42c7c80374d4e8712757/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.16.372.0+4a9b2326/MODULE_fce72056449004b51385/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_925eeddec3d7c8386722/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_133436458230197705aa/model.neuron filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0/roberta/FacebookAI/roberta-base/133436458230197705aa.json

@@ -0,0 +1,49 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "FacebookAI/roberta-base",
+  "_task": "fill-mask",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "neuron": {
+    "auto_cast": null,
+    "auto_cast_type": null,
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.19.8089.0+8ab9f450",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "input_ids",
+      "attention_mask"
+    ],
+    "model_type": "roberta",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "logits"
+    ],
+    "static_batch_size": 1,
+    "static_sequence_length": 128,
+    "task": "fill-mask",
+    "tensor_parallel_size": 1
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_133436458230197705aa/config.json

@@ -0,0 +1,53 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "neuron": {
+    "auto_cast": null,
+    "auto_cast_type": null,
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.19.8089.0+8ab9f450",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "input_ids",
+      "attention_mask"
+    ],
+    "model_type": "roberta",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "logits"
+    ],
+    "static_batch_size": 1,
+    "static_sequence_length": 128,
+    "task": "fill-mask",
+    "tensor_parallel_size": 1
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_133436458230197705aa/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85268d7ceb833a9b622eccee78fe24fbb3c5277ac8164036e6231d0ed7efc2f
+size 412256570

neuronxcc-2.19.8089.0+8ab9f450/MODULE_133436458230197705aa/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_133436458230197705aa/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}