Instructions to use BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K with Transformers:

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

pipe = pipeline("text-generation", model="BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K")
model = AutoModelForCausalLM.from_pretrained("BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K")
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 Settings

vLLM

How to use BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K

SGLang

How to use BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-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 "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K" \
    --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": "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K",
		"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 "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K" \
        --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": "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K with Docker Model Runner:
```
docker model run hf.co/BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K
```

Qwen2.5-3B-GRPO-Math-GSM8K

A 3-billion-parameter Qwen2.5 model fine-tuned with Group-Relative Policy Optimization (GRPO) on the GSM8K grade-school math dataset. The aim is to turn the compact 3B model into a lightweight but highly capable step-by-step math reasoner that runs on a single consumer GPU.

Try it

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "BounharAbdelaziz/Qwen2.5-3B-GRPO-Math-GSM8K"

tok = AutoTokenizer.from_pretrained(model_id, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

problem = "If a book costs $7 and a pen costs $2, how much do 3 books and 4 pens cost in total?"

messages = [
    {"role": "system", "content": "You are a step-by-step math tutor."},
    {"role": "user", "content": problem}
]

prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
out_ids = model.generate(
    **tok(prompt, return_tensors="pt").to(model.device),
    max_new_tokens=1024,
    temperature=0.7
)
print(tok.decode(out_ids[0], skip_special_tokens=True))