SHAH-MEER/llama-pricer

Llama Pricer

A fine-tuned Llama 3.1 model specialized for Amazon product price prediction.

Model Performance

This model achieves state-of-the-art performance on Amazon product price prediction with a Mean Absolute Error (MAE) of $47, significantly outperforming all baseline methods:

Method	MAE
Fine-tuned Llama 3.1	$47
GPT-4o Mini	$76
Random Forest + WordVec	$97
Linear Regression + WordVec	$121
Average Price Prediction	$146
Random Guess	$350

The model shows a 38% improvement over GPT-4o Mini and 51% improvement over traditional ML approaches.

Model Details

• Base Model: Llama 3.1
• Fine-tuning: Specialized for Amazon product price prediction
• Performance: MAE of $47 (38% better than GPT-4o Mini)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the model
tokenizer = AutoTokenizer.from_pretrained("SHAH-MEER/llama-pricer")
model = AutoModelForCausalLM.from_pretrained("SHAH-MEER/llama-pricer")

# Example usage
inputs = tokenizer("Predict the Amazon price for this product:", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0]))

Applications

• Amazon product price prediction
• E-commerce price forecasting
• Competitive pricing analysis
• Product pricing optimization
• Market trend analysis for Amazon products

License

Please refer to the original Llama 3.1 license terms.

Citation

If you use this model in your research, please cite:

@misc{llama-pricer,
  title={Llama Pricer: Fine-tuned Llama 3.1 for Amazon Product Price Prediction},
  author={SHAH-MEER},
  year={2024},
  publisher={Hugging Face},
  url={https://huggingface.co/SHAH-MEER/llama-pricer}
}