Instructions to use Vantuk/Qwen3-1.7B-Countdown with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vantuk/Qwen3-1.7B-Countdown with Transformers:

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

pipe = pipeline("text-generation", model="Vantuk/Qwen3-1.7B-Countdown")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vantuk/Qwen3-1.7B-Countdown")
model = AutoModelForCausalLM.from_pretrained("Vantuk/Qwen3-1.7B-Countdown")
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 Vantuk/Qwen3-1.7B-Countdown with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vantuk/Qwen3-1.7B-Countdown"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vantuk/Qwen3-1.7B-Countdown",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vantuk/Qwen3-1.7B-Countdown

SGLang

How to use Vantuk/Qwen3-1.7B-Countdown 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 "Vantuk/Qwen3-1.7B-Countdown" \
    --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": "Vantuk/Qwen3-1.7B-Countdown",
		"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 "Vantuk/Qwen3-1.7B-Countdown" \
        --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": "Vantuk/Qwen3-1.7B-Countdown",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vantuk/Qwen3-1.7B-Countdown with Docker Model Runner:
```
docker model run hf.co/Vantuk/Qwen3-1.7B-Countdown
```

🧮 Qwen3-1.7B-GRPO-Countdown

Qwen3-1.7B-GRPO-Countdown is a fine-tuned version of Qwen/Qwen3-1.7B using GRPO (Group Relative Policy Optimization) to improve mathematical reasoning and step-by-step accuracy in solving Countdown-style arithmetic problems.

Source Code

My sourcse code for fine-tuning and evaluating can be found here github.com/Tuprott991/GRPO_LLM note that I use flash_attention_2 an A100 40GB for fine-tunng

🧠 Model Overview

Property	Description
Base Model	Qwen3-1.7B
Fine-tuning Method	GRPO (Reinforcement Learning)
Task	Countdown Math Problem Solving
Dataset	justinphan3110/Countdown-Tasks-3to4
Language	English
Objective	Improve reasoning chain and final accuracy on multi-step arithmetic tasks

🏗️ Training Details

Algorithm: GRPO (Group Relative Policy Optimization)
Reward Function:
- +1.0: Perfect - equation is valid, uses correct numbers, equals target
- +0.1: Partial - has tag but equation is incorrect
- 0.0: Failed - no tag found
Environment: Simulated Countdown math environment
Batch Size: 16
Learning Rate: 1e-6
Training Steps: 180

📊 Evaluation

Metric	Score
Accuracy	54%

💡 Example Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Vantuk/Qwen3-1.7B-Countdown"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "Use 3, 4, 7, 8, 25, and 50 to make 952."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 8

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Vantuk/Qwen3-1.7B-Countdown

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(761)

this model

Vantuk
/

Qwen3-1.7B-Countdown