---
license: llama3.2
language:
- en
base_model: meta-llama/Llama-3.2-1B
pipeline_tag: text-classification
library_name: peft
tags:
- regression
- story-point-estimation
- software-engineering
datasets:
- usergrid
metrics:
- mae
- mdae
model-index:
- name: llama-3.2-1b-story-point-estimation
  results:
  - task:
      type: regression
      name: Story Point Estimation
    dataset:
      name: usergrid Dataset
      type: usergrid
      split: test
    metrics:
    - type: mae
      value: 1.765
      name: Mean Absolute Error (MAE)
    - type: mdae
      value: 1.583
      name: Median Absolute Error (MdAE)
---
# LLAMA 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: LLAMA 3.2 1B
- Training Project: usergrid
- Test Project: usergrid
- Task: Story Point Estimation (Regression)
- Architecture: PEFT (LoRA)

- Input: Issue titles
- Output: Story point estimation (continuous value)

## Usage
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
from peft import PeftConfig, PeftModel

# Load peft config model
config = PeftConfig.from_pretrained("DEVCamiloSepulveda/0-LLAMA3SP-usergrid")

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/0-LLAMA3SP-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/0-LLAMA3SP-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: 17 / 20 epochs
- Batch size: 32
- Training time: 301.615 seconds
- Mean Absolute Error (MAE): 1.765
- Median Absolute Error (MdAE): 1.583
### Framework versions

- PEFT 0.14.0