Instructions to use zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep with Transformers:

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

pipe = pipeline("text-generation", model="zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep")
model = AutoModelForCausalLM.from_pretrained("zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep")
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 zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep

SGLang

How to use zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep 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 "zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep" \
    --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": "zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep",
		"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 "zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep" \
        --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": "zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep with Docker Model Runner:
```
docker model run hf.co/zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep
```

Qwen2.5-0.5B-Instruct Math SFT 100K 2 Epochs

Fine-tuned from Qwen/Qwen2.5-0.5B-Instruct on a 100K math reasoning SFT mixture for 2 epochs with learning rate 1e-5.

Prompt format used during training:

System: Please reason step by step, and put your final answer within \boxed{}.
User: {problem}
Assistant: {solution}

Training mixture:

Source	Count
nvidia/OpenMathReasoning CoT	40,000
AI-MO/NuminaMath-1.5 filtered, no AMC/AIME source	25,000
meta-math/MetaMathQA	15,000
MATH train, especially levels 4-5	15,000
GSM8K train	5,000

Training summary:

Setting	Value
Base model	`Qwen/Qwen2.5-0.5B-Instruct`
Training examples	100,000
Epochs	2
Learning rate	`1e-5`
Max sequence length	4096
Effective batch size	32
Final train loss	0.6923
Final token accuracy	about 0.803

Evaluation results are not included in this model card yet.

Downloads last month: 18

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(796)

this model

zbeeb
/

Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep

Qwen2.5-0.5B-Instruct Math SFT 100K 2 Epochs

Model tree for zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep

Datasets used to train zbeeb/Qwen2.5-0.5B-Instruct-Math-SFT-100K-2ep