DEVCamiloSepulveda/0-LLAMA3SP-duracloud

LLAMA 3 Story Point Estimator - duracloud

This model is fine-tuned on issue descriptions from duracloud and tested on duracloud for story point estimation.

Model Details

• Base Model: LLAMA 3.2 1B

• Training Project: duracloud

• Test Project: duracloud

• Task: Story Point Estimation (Regression)

• Architecture: PEFT (LoRA)

• Input: Issue titles

• Output: Story point estimation (continuous value)

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer
from peft import PeftConfig, PeftModel

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

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/0-LLAMA3SP-duracloud")
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-duracloud")

# 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: 13 / 20 epochs
• Batch size: 32
• Training time: 288.061 seconds
• Mean Absolute Error (MAE): 1.118
• Median Absolute Error (MdAE): 0.944

Framework versions

• PEFT 0.14.0