Pushing model, tokenizer and model card

README.md

@@ -0,0 +1,31 @@
+---
+library_name: transformers
+license: mit
+language:
+- en
+metrics:
+- seqeval
+base_model:
+- microsoft/codebert-base
+pipeline_tag: token-classification
+---
+
+# CodeBERT base for detecting software engineering terminology
+
+This model detects software engineering terminology in developer forums (e.g., Stack Overflow) as 'Data_Structure', 'Application', 'Code_Block', 'Function", 'Data_Type', 'Language', 'Library', 'Variable', 'Device', 'User_Name', 'User_Interface_Element', 'Class', 'Website', 'Version', 'File_Name', 'File_Type',  'Operating_System', 'Output_Block', 'Algorithm' or 'HTML_XML_Tag'.
+
+- **Developed by:** Fabian C. Peña, Steffen Herbold
+- **Finetuned from:** [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base)
+- **Replication kit:** [https://github.com/aieng-lab/senlp-benchmark](https://github.com/aieng-lab/senlp-benchmark)
+- **Language:** English
+- **License:** MIT
+
+## Citation
+
+```
+@misc{pena2025benchmark,
+  author    = {Fabian Peña and Steffen Herbold},
+  title     = {Evaluating Large Language Models on Non-Code Software Engineering Tasks},
+  year      = {2025}
+}
+```

config.json

@@ -0,0 +1,114 @@
+{
+  "_name_or_path": "microsoft/codebert-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "O",
+    "1": "B-Data_Structure",
+    "2": "I-Data_Structure",
+    "3": "B-Application",
+    "4": "I-Application",
+    "5": "B-Code_Block",
+    "6": "I-Code_Block",
+    "7": "B-Function",
+    "8": "I-Function",
+    "9": "B-Data_Type",
+    "10": "I-Data_Type",
+    "11": "B-Language",
+    "12": "I-Language",
+    "13": "B-Library",
+    "14": "I-Library",
+    "15": "B-Variable",
+    "16": "I-Variable",
+    "17": "B-Device",
+    "18": "I-Device",
+    "19": "B-User_Name",
+    "20": "I-User_Name",
+    "21": "B-User_Interface_Element",
+    "22": "I-User_Interface_Element",
+    "23": "B-Class",
+    "24": "I-Class",
+    "25": "B-Website",
+    "26": "I-Website",
+    "27": "B-Version",
+    "28": "I-Version",
+    "29": "B-File_Name",
+    "30": "I-File_Name",
+    "31": "B-File_Type",
+    "32": "I-File_Type",
+    "33": "B-Operating_System",
+    "34": "I-Operating_System",
+    "35": "B-Output_Block",
+    "36": "I-Output_Block",
+    "37": "B-Algorithm",
+    "38": "I-Algorithm",
+    "39": "B-HTML_XML_Tag",
+    "40": "I-HTML_XML_Tag"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Algorithm": 37,
+    "B-Application": 3,
+    "B-Class": 23,
+    "B-Code_Block": 5,
+    "B-Data_Structure": 1,
+    "B-Data_Type": 9,
+    "B-Device": 17,
+    "B-File_Name": 29,
+    "B-File_Type": 31,
+    "B-Function": 7,
+    "B-HTML_XML_Tag": 39,
+    "B-Language": 11,
+    "B-Library": 13,
+    "B-Operating_System": 33,
+    "B-Output_Block": 35,
+    "B-User_Interface_Element": 21,
+    "B-User_Name": 19,
+    "B-Variable": 15,
+    "B-Version": 27,
+    "B-Website": 25,
+    "I-Algorithm": 38,
+    "I-Application": 4,
+    "I-Class": 24,
+    "I-Code_Block": 6,
+    "I-Data_Structure": 2,
+    "I-Data_Type": 10,
+    "I-Device": 18,
+    "I-File_Name": 30,
+    "I-File_Type": 32,
+    "I-Function": 8,
+    "I-HTML_XML_Tag": 40,
+    "I-Language": 12,
+    "I-Library": 14,
+    "I-Operating_System": 34,
+    "I-Output_Block": 36,
+    "I-User_Interface_Element": 22,
+    "I-User_Name": 20,
+    "I-Variable": 16,
+    "I-Version": 28,
+    "I-Website": 26,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8caf3420c30ec0b789bb109e9c0c6b4473f641ec1a3357c54f3c1cba7e4b87b9
+size 248197210

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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>"
+}