green-tea-llama-3.1-8b-energy-sft/README.md

license, base_model, pipeline_tag, library_name, tags

license	base_model	pipeline_tag	library_name	tags
llama3.1	unsloth/Meta-Llama-3.1-8B	text-generation	transformers	code energy-efficient-code-generation green-software-engineering merged

Llama-3.1-8B Energy-SFT

Part of the Green Tea replication package for Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning (Rajput and Sharma). Energy-contrastive supervised fine-tuning. On the 143-problem held-out benchmark it achieves 5.97% CARET (Correctness-Adjusted Reduction in Energy Total).

• Base model: unsloth/Meta-Llama-3.1-8B
• Training: Energy-contrastive supervised fine-tuning
• Code and full replication: https://github.com/SMART-Dal/green-tea
• Dataset (Zenodo): https://doi.org/10.5281/zenodo.21210099

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained('saurabh-singh-rajput/green-tea-llama-3.1-8b-energy-sft', device_map='auto')
t = AutoTokenizer.from_pretrained('saurabh-singh-rajput/green-tea-llama-3.1-8b-energy-sft')

Citation

@misc{rajput2026greentea,
  title={Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning},
  author={Rajput, Saurabhsingh and Sharma, Tushar},
  year={2026},
  note={Preprint}
}