metadata
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:
- usergrid
metrics:
- mae
- mdae
model-index:
- name: Qwen3-story-point-estimation
results:
- task:
type: regression
name: Story Point Estimation
dataset:
name: usergrid Dataset
type: usergrid
split: test
metrics:
- type: mae
value: 1.481
name: Mean Absolute Error (MAE)
- type: mdae
value: 1.271
name: Median Absolute Error (MdAE)
Qwen 3 Story Point Estimator - usergrid
This model is fine-tuned on issue descriptions from usergrid and tested on usergrid for story point estimation.
Model Details
Base Model: Qwen 3
Training Project: usergrid
Test Project: usergrid
Task: Story Point Estimation (Regression)
Architecture: PEFT (LoRA)
Tokenizer: Qwen BPE Tokenizer
Input: Issue titles
Output: Story point estimation (continuous value)
Usage
from transformers import AutoModelForSequenceClassification
from peft import PeftConfig, PeftModel
from transformers import AutoTokenizer
# Load peft config model
config = PeftConfig.from_pretrained("DEVCamiloSepulveda/3-Qwen3SP-usergrid")
# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/3-Qwen3SP-usergrid")
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-usergrid")
# 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: 10 / 20 epochs
- Batch size: 32
- Training time: 277.065 seconds
- Mean Absolute Error (MAE): 1.481
- Median Absolute Error (MdAE): 1.271
Framework versions
- PEFT 0.14.0