Instructions to use Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO")
model = AutoModelForCausalLM.from_pretrained("Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO

SGLang

How to use Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO 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 "Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO",
    max_seq_length=2048,
)

Docker Model Runner
How to use Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO with Docker Model Runner:
```
docker model run hf.co/Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO
```

$A scene from a famous movie$

LLaMA-3-8B-Math-Majority-Vote-GRPO

Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO is a Test Time Reinforcement Learning (TTRL) trained version of ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1. It is trained on Turkish math word problems using GRPO method and a majority vote reward function.

Paper: TTRL: Test-Time Reinforcement Learning Code: https://github.com/PRIME-RL/TTRL

Training Info

Base Model: Turkish-Llama-8b-DPO-v0.1
Training Data: 2.000 open-ended math word problems. No proprietary data was included.
Training Time: 13 hours on a single L40S
LoRA Configs:
- lora_r: 16
- lora_alpha: 16
- lora_dropout: 0
- lora_target_linear: true

The goal was to train a model without using any labels or ground truth answers that can reason before generating the answer. It uses the below template:

<mantık>
...
</mantık>
<cevap>
</cevap>

For more information visit my blog post about this model please.

How to use

Install vLLM

pip install vllm

from vllm import LLM, SamplingParams
import json

llm = LLM(model="Metin/LLaMA-3-8B-Math-Majority-Vote-GRPO")

sampling_params = SamplingParams(temperature=0.5)

SYSTEM_PROMPT = """
Sana verilen matematik problemi hakkında düşün ve çözümü bul.
Düşüncelerini <mantık> ve </mantık> arasına yaz.
Sonucu ise <cevap> ve </cevap> arasına yaz. Sonucu yazarken sadece rakamları, noktayı ve virgülü kullan. Noktayı binlik ayracı, virgülü ise ondalık ayracı olarak kullanmalısın. Örnek: <cevap>1.450,02</cevap>
"""

conversation = [
  {
      "role": "system",
      "content": SYSTEM_PROMPT
  }
  {
      "role": "user",
      "content": "Nüfus 20.000'dir. Nüfus her yıl %10 artmaktadır. Buna göre üç yıl sonra nüfus kaç olur?"
  }
]

outputs = llm.chat(
  conversation,
  sampling_params=sampling_params,
  use_tqdm=False
)

result = json.loads(outputs[0].outputs[0].text)

print(result)

Citation

@article{zuo2025ttrl,
  title={Ttrl: Test-time reinforcement learning},
  author={Zuo, Yuxin and Zhang, Kaiyan and Qu, Shang and Sheng, Li and Zhu, Xuekai and Qi, Biqing and Sun, Youbang and Cui, Ganqu and Ding, Ning and Zhou, Bowen},
  journal={arXiv preprint arXiv:2504.16084},
  year={2025}
}