CoolFace
Modelpublic

DEVCamiloSepulveda/11-DeepSeekR1SP-mesos-usergrid

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes5downloads
Model Card

DeepSeek R1 Qwen Story Point Estimator - mesos - usergrid

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

Model Details

  • —Base Model: DeepSeek R1 Distill Qwen 1.5B
  • —Training Project: mesos
  • —Test Project: usergrid
  • —Task: Story Point Estimation (Regression)
  • —Architecture: PEFT (LoRA)
  • —Tokenizer: DeepSeek BPE Tokenizer
  • —Input: Issue titles
  • —Output: Story point estimation (continuous value)

Usage

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

# Load peft config model
config = PeftConfig.from_pretrained("DEVCamiloSepulveda/11-DeepSeekR1SP-mesos-usergrid")

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("DEVCamiloSepulveda/11-DeepSeekR1SP-mesos-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/11-DeepSeekR1SP-mesos-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: 2 / 20 epochs
  • —Batch size: 32
  • —Training time: 215.156 seconds
  • —Mean Absolute Error (MAE): 1.405
  • —Median Absolute Error (MdAE): 1.170

Framework versions

  • —PEFT 0.14.0