Modelpublic

DEVCamiloSepulveda/00-LLAMA3SP-appceleratorstudio-titanium

sourceHugging Facellama3.2updated 2y agoView on Hugging Face

0likes4downloads

Model Card

LLAMA 3 Story Point Estimator - appceleratorstudio - titanium

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

Model Details

—Base Model: LLAMA 3.2 1B
—Training Project: appceleratorstudio
—Test Project: titanium
—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/00-LLAMA3SP-appceleratorstudio-titanium")

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/00-LLAMA3SP-appceleratorstudio-titanium")
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/00-LLAMA3SP-appceleratorstudio-titanium")

# 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: 0 / 20 epochs
—Batch size: 32
—Training time: 63.384 seconds
—Mean Absolute Error (MAE): 3.309
—Median Absolute Error (MdAE): 2.240

Framework versions

—PEFT 0.14.0