Instructions to use Elliott/LUFFY-Qwen-Math-1.5B-Zero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Elliott/LUFFY-Qwen-Math-1.5B-Zero with Transformers:

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

pipe = pipeline("text-generation", model="Elliott/LUFFY-Qwen-Math-1.5B-Zero")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Elliott/LUFFY-Qwen-Math-1.5B-Zero")
model = AutoModelForCausalLM.from_pretrained("Elliott/LUFFY-Qwen-Math-1.5B-Zero")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Elliott/LUFFY-Qwen-Math-1.5B-Zero with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Elliott/LUFFY-Qwen-Math-1.5B-Zero"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Elliott/LUFFY-Qwen-Math-1.5B-Zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Elliott/LUFFY-Qwen-Math-1.5B-Zero

SGLang

How to use Elliott/LUFFY-Qwen-Math-1.5B-Zero 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 "Elliott/LUFFY-Qwen-Math-1.5B-Zero" \
    --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": "Elliott/LUFFY-Qwen-Math-1.5B-Zero",
		"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 "Elliott/LUFFY-Qwen-Math-1.5B-Zero" \
        --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": "Elliott/LUFFY-Qwen-Math-1.5B-Zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Elliott/LUFFY-Qwen-Math-1.5B-Zero with Docker Model Runner:
```
docker model run hf.co/Elliott/LUFFY-Qwen-Math-1.5B-Zero
```

Elliott commited on Apr 23, 2025

Commit

e252461

verified ·

1 Parent(s): e607abb

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -3

README.md CHANGED Viewed

@@ -49,9 +49,6 @@ print(outputs[0].outputs[0].text)
 # 📃Evaluation
-LUFFY is evaluated on six competition-level benchmarks, achieving state-of-the-art results among all zero-RL methods. It surpasses both on-policy RL and imitation learning (SFT), especially in generalization:
 | **Model** | **AIME 24** | **AIME 25** | **AMC** | **MATH-500** | **Minerva** | **Olympiad** | **Avg.** |
 |-------|---------|---------|-----|----------|---------|----------|------|
 | Qwen2.5-Math-1.5B-Base | 7.9 | 4.7 | 26.4 | 31.0 | 12.1 | 21.5 | 17.3 |

 # 📃Evaluation
 | **Model** | **AIME 24** | **AIME 25** | **AMC** | **MATH-500** | **Minerva** | **Olympiad** | **Avg.** |
 |-------|---------|---------|-----|----------|---------|----------|------|
 | Qwen2.5-Math-1.5B-Base | 7.9 | 4.7 | 26.4 | 31.0 | 12.1 | 21.5 | 17.3 |