Instructions to use lmassaron/gemma-2-2b-it-grpo-gsm8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmassaron/gemma-2-2b-it-grpo-gsm8k with Transformers:

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

pipe = pipeline("text-generation", model="lmassaron/gemma-2-2b-it-grpo-gsm8k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lmassaron/gemma-2-2b-it-grpo-gsm8k")
model = AutoModelForCausalLM.from_pretrained("lmassaron/gemma-2-2b-it-grpo-gsm8k")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lmassaron/gemma-2-2b-it-grpo-gsm8k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmassaron/gemma-2-2b-it-grpo-gsm8k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmassaron/gemma-2-2b-it-grpo-gsm8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lmassaron/gemma-2-2b-it-grpo-gsm8k

SGLang

How to use lmassaron/gemma-2-2b-it-grpo-gsm8k 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 "lmassaron/gemma-2-2b-it-grpo-gsm8k" \
    --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": "lmassaron/gemma-2-2b-it-grpo-gsm8k",
		"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 "lmassaron/gemma-2-2b-it-grpo-gsm8k" \
        --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": "lmassaron/gemma-2-2b-it-grpo-gsm8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lmassaron/gemma-2-2b-it-grpo-gsm8k with Docker Model Runner:
```
docker model run hf.co/lmassaron/gemma-2-2b-it-grpo-gsm8k
```

Model Card for Model ID

This model is a fine-tuned version of Google/gemma-2-2b-it on the dataset GSM8k. It has been trained using GRPOTrainer from TRL.

Quick start

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

tokenizer_name = "Google/gemma-2-2b-it"
model_name="lmassaron/gemma-2-2b-it-grpo-gsm8k"
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name,
                                          trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             device_map="auto",
                                             use_cache=True)

FORMAT = """<reasoning>\n</reasoning>\n<answer>\n</answer>\n"""

question = "Which is bigger? 9.11 or 9.9?"
generator = pipeline("text-generation",
                      model=model,
                      tokenizer=tokenizer,
                      do_sample=False,
                      batch_size=1)
output = generator([{"role": "user", "content": FORMAT + question}],
                    max_new_tokens=256,
                    return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Framework versions

TRL: 0.15.1
Transformers: 4.49.0
Pytorch: 2.5.1+cu124
Datasets: 3.3.1
Tokenizers: 0.21.0

Citations

Cite GRPO as:

@article{zhihong2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}