Instructions to use saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft")
model = AutoModelForCausalLM.from_pretrained("saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft

SGLang

How to use saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft with Docker Model Runner:
```
docker model run hf.co/saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft
```

Qwen2.5-Coder-14B 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 4.45% CARET (Correctness-Adjusted Reduction in Energy Total).

Base model: unsloth/Qwen2.5-Coder-14B
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-qwen2.5-coder-14b-energy-sft', device_map='auto')
t = AutoTokenizer.from_pretrained('saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-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}
}

Downloads last month: 390

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for saurabh-singh-rajput/green-tea-qwen2.5-coder-14b-energy-sft

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

unsloth/Qwen2.5-Coder-14B

Finetuned

(1)

this model

Adapters

1 model