Add Neuron-optimized model files (#2)

- Add Neuron-optimized model files (4fdb0a5ceb6fe5f8ddfaf4c5931236cbb72f64e8)


Co-authored-by: ABDENNACER BADAOUI <[email protected]>

.gitattributes

@@ -15,3 +15,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
+model.neuron filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,11 +1,12 @@
 ---
 language: ko
 tags:
-  - korean
-  - klue
-mask_token: "[MASK]"
+- korean
+- klue
+- neuron
+mask_token: '[MASK]'
 widget:
-  - text: 대한민국의 수도는 [MASK] 입니다.
+- text: 대한민국의 수도는 [MASK] 입니다.
 ---
 
 # KLUE RoBERTa small

config.json

@@ -1,7 +1,11 @@
 {
-  "architectures": ["RobertaForMaskedLM"],
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
@@ -12,10 +16,40 @@
   "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": 6,
   "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.51.3",
   "type_vocab_size": 1,
-  "vocab_size": 32000,
-  "tokenizer_class": "BertTokenizer"
+  "use_cache": true,
+  "vocab_size": 32000
 }

model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a9b1bb1c2999b593c67ca7ff1fa1a32dddcf0df9900e676dcecc73081e7ea4
+size 233266810

special_tokens_map.json

@@ -1,9 +1,51 @@
 {
-  "unk_token": "[UNK]",
-  "sep_token": "[SEP]",
-  "pad_token": "[PAD]",
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "bos_token": "[CLS]",
-  "eos_token": "[SEP]"
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -5,48 +5,48 @@
   "added_tokens": [
     {
       "id": 0,
-      "special": true,
       "content": "[CLS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 1,
-      "special": true,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 2,
-      "special": true,
       "content": "[SEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 3,
-      "special": true,
       "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 4,
-      "special": true,
       "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -56,27 +56,89 @@
     "strip_accents": null,
     "lowercase": false
   },
-  "pre_tokenizer": { "type": "BertPreTokenizer" },
+  "pre_tokenizer": {
+    "type": "BertPreTokenizer"
+  },
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      { "SpecialToken": { "id": "[CLS]", "type_id": 0 } },
-      { "Sequence": { "id": "A", "type_id": 0 } },
-      { "SpecialToken": { "id": "[SEP]", "type_id": 0 } }
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      }
     ],
     "pair": [
-      { "SpecialToken": { "id": "[CLS]", "type_id": 0 } },
-      { "Sequence": { "id": "A", "type_id": 0 } },
-      { "SpecialToken": { "id": "[SEP]", "type_id": 0 } },
-      { "Sequence": { "id": "B", "type_id": 0 } },
-      { "SpecialToken": { "id": "[SEP]", "type_id": 0 } }
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      }
     ],
     "special_tokens": {
-      "[CLS]": { "id": "[CLS]", "ids": [0], "tokens": ["[CLS]"] },
-      "[SEP]": { "id": "[SEP]", "ids": [2], "tokens": ["[SEP]"] }
+      "[CLS]": {
+        "id": "[CLS]",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "[CLS]"
+        ]
+      },
+      "[SEP]": {
+        "id": "[SEP]",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "[SEP]"
+        ]
+      }
     }
   },
-  "decoder": { "type": "WordPiece", "prefix": "##", "cleanup": true },
+  "decoder": {
+    "type": "WordPiece",
+    "prefix": "##",
+    "cleanup": true
+  },
   "model": {
     "type": "WordPiece",
     "unk_token": "[UNK]",
@@ -32085,4 +32147,4 @@
       "[unused499]": 31999
     }
   }
-}
+}

tokenizer_config.json

@@ -1,16 +1,60 @@
 {
-  "do_lower_case": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
   "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
   "never_split": null,
-  "unk_token": "[UNK]",
-  "sep_token": "[SEP]",
   "pad_token": "[PAD]",
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "bos_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "tokenize_chinese_chars": true,
+  "sep_token": "[SEP]",
   "strip_accents": null,
-  "model_max_length": 512,
-  "tokenizer_class": "BertTokenizer"
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }