metadata
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:
- bamboo
metrics:
- mae
- mdae
model-index:
- name: llama-3.2-1b-story-point-estimation
results:
- task:
type: regression
name: Story Point Estimation
dataset:
name: bamboo Dataset
type: bamboo
split: test
metrics:
- type: mae
value: 1.104
name: Mean Absolute Error (MAE)
- type: mdae
value: 0.832
name: Median Absolute Error (MdAE)
LLAMA 3 Story Point Estimator - bamboo
This model is fine-tuned on issue descriptions from bamboo and tested on bamboo for story point estimation.
Model Details
Base Model: LLAMA 3.2 1B
Training Project: bamboo
Test Project: bamboo
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-bamboo")
# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/0-LLAMA3SP-bamboo")
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-bamboo")
# 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: 11.101 seconds
- Mean Absolute Error (MAE): 1.104
- Median Absolute Error (MdAE): 0.832
Framework versions
- PEFT 0.14.0