First version

benchmark_model/config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "CLS",
+    "1": "SEP",
+    "2": "B-Application_Mention",
+    "3": "I-Application_Mention",
+    "4": "B-Developer",
+    "5": "I-Developer",
+    "6": "B-URL",
+    "7": "I-URL",
+    "8": "B-Version",
+    "9": "I-Version",
+    "10": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Application_Mention": 2,
+    "B-Developer": 4,
+    "B-URL": 6,
+    "B-Version": 8,
+    "CLS": 0,
+    "I-Application_Mention": 3,
+    "I-Developer": 5,
+    "I-URL": 7,
+    "I-Version": 9,
+    "O": 10,
+    "SEP": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

benchmark_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec6c606ffe34290a4df226ee9f21b078d24c4e06475692dc6c76056468b9ba4
+size 437417453

benchmark_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

benchmark_model/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": true,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

benchmark_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2189f85aa631d6f177cec6e14983cb1d89d5e20b3b5a57bead0bc8a76be7a024
+size 3579