| ---
|
| license: apache-2.0
|
| language:
|
| - en
|
| base_model: Qwen/Qwen3-1.7B
|
| pipeline_tag: text-classification
|
| library_name: peft
|
| tags:
|
| - regression
|
| - story-point-estimation
|
| - software-engineering
|
| datasets:
|
| - talenddataquality
|
| metrics:
|
| - mae
|
| - mdae
|
| model-index:
|
| - name: Qwen3-story-point-estimation
|
| results:
|
| - task:
|
| type: regression
|
| name: Story Point Estimation
|
| dataset:
|
| name: talenddataquality Dataset
|
| type: talenddataquality
|
| split: test
|
| metrics:
|
| - type: mae
|
| value: 4.249
|
| name: Mean Absolute Error (MAE)
|
| - type: mdae
|
| value: 4.464
|
| name: Median Absolute Error (MdAE)
|
| ---
|
| # Qwen 3 Story Point Estimator - talenddataquality |
|
|
| This model is fine-tuned on issue descriptions from talenddataquality and tested on talenddataquality for story point estimation. |
|
|
| ## Model Details |
| - Base Model: Qwen 3 |
| - Training Project: talenddataquality |
| - Test Project: talenddataquality |
| - Task: Story Point Estimation (Regression) |
| - Architecture: PEFT (LoRA) |
| - Tokenizer: Qwen BPE Tokenizer |
|
|
| - Input: Issue titles |
| - Output: Story point estimation (continuous value) |
|
|
| ## Usage |
| ```python |
| from transformers import AutoModelForSequenceClassification |
| from peft import PeftConfig, PeftModel |
| from transformers import AutoTokenizer |
| |
| # Load peft config model |
| config = PeftConfig.from_pretrained("DEVCamiloSepulveda/3-Qwen3SP-talenddataquality") |
| |
| # Load tokenizer and model |
| tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/3-Qwen3SP-talenddataquality") |
| base_model = AutoModelForSequenceClassification.from_pretrained( |
| config.base_model_name_or_path, |
| num_labels=1, |
| torch_dtype=torch.float16, |
| device_map='auto' |
| ) |
| model = PeftModel.from_pretrained(base_model, "DEVCamiloSepulveda/3-Qwen3SP-talenddataquality") |
| |
| # Prepare input text |
| text = "Your issue description here" |
| inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=20, padding="max_length") |
| |
| # Get prediction |
| outputs = model(**inputs) |
| story_points = outputs.logits.item() |
| ``` |
|
|
| ## Training Details |
| - Fine-tuning method: LoRA (Low-Rank Adaptation) |
| - Sequence length: 20 tokens |
| - Best training epoch: 9 / 20 epochs |
| - Batch size: 32 |
| - Training time: 649.382 seconds |
| - Mean Absolute Error (MAE): 4.249 |
| - Median Absolute Error (MdAE): 4.464 |
| ### Framework versions |
|
|
| - PEFT 0.14.0 |
