Upload initial bug severity model

README.md

@@ -0,0 +1,115 @@
+---
+language:
+- en
+library_name: transformers
+pipeline_tag: text-classification
+base_model: answerdotai/ModernBERT-base
+datasets:
+- AliArshad/Bugzilla_Eclipse_Bug_Reports_Dataset
+metrics:
+- accuracy
+- f1
+tags:
+- modernbert
+- bug-triage
+- bug-severity
+- sequence-classification
+---
+
+# ModernBERT Bug Severity Classifier
+
+This model is a fully fine-tuned version of
+`answerdotai/ModernBERT-base` for classifying short bug descriptions
+into six severity levels:
+
+- blocker
+- critical
+- major
+- normal
+- minor
+- trivial
+
+## Intended use
+
+This model is an educational demonstration of automated bug-severity
+classification.
+
+It should not be used as the sole authority for production severity
+decisions. High-impact predictions should be reviewed by a human.
+
+## Training dataset
+
+The model was trained using:
+
+`AliArshad/Bugzilla_Eclipse_Bug_Reports_Dataset`
+
+Only the `Short Description` field was used as the model input. The
+`Severity Label` field was used as the target label.
+
+## Base model
+
+`answerdotai/ModernBERT-base`
+
+## Training approach
+
+This model was trained using full fine-tuning. It is not a LoRA or
+adapter-only model.
+
+Training included:
+
+- Removing missing and empty descriptions
+- Converting severity names into numeric labels
+- Stratified training, validation, and test splits
+- Batched tokenization
+- Dynamic padding and attention masks
+- Hugging Face Trainer
+- Macro F1 checkpoint selection
+
+## Evaluation
+
+- Test accuracy: 0.871
+- Test macro F1: 0.32951261884727445
+
+Performance should also be examined separately for each severity using
+the classification report and confusion matrix.
+
+## Limitations
+
+- Severity cannot always be determined from a short description alone.
+- The training dataset may contain noisy or inconsistent labels.
+- The severity classes are imbalanced.
+- Historical bug reports may not represent current software practices.
+- Softmax confidence is not guaranteed to be a calibrated probability.
+- Human review is recommended for blocker and critical predictions.
+
+## License status
+
+The ModernBERT base model uses the Apache 2.0 license. The training
+dataset's Hugging Face page does not currently declare a dataset
+license. Confirm the applicable dataset and source-data terms before
+making this fine-tuned model public.
+
+## Example usage
+
+Install the required library:
+
+    pip install transformers torch
+
+Run inference:
+
+    from transformers import pipeline
+
+    classifier = pipeline(
+        "text-classification",
+        model="abhishes/modernbert-bug-severity",
+        revision="v1.0.0"
+    )
+
+    bug_reports = [
+        "Application crashes immediately and all data is lost.",
+        "There is a spelling mistake in the documentation."
+    ]
+
+    results = classifier(bug_reports)
+
+    print(results)

config.json

@@ -0,0 +1,95 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": null,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "blocker",
+    "1": "critical",
+    "2": "major",
+    "3": "minor",
+    "4": "normal",
+    "5": "trivial"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "blocker": 0,
+    "critical": 1,
+    "major": 2,
+    "minor": 3,
+    "normal": 4,
+    "trivial": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d297f1fc686f05bfb2933e2fae53dc3d70128a63eb451282c425cded6c6d2f8d
+size 598452088

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568d8066653a28572b586ea3950a85918512a63cd74860fd95e67e4e9cb66b61
+size 5201