Instructions to use erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy with Transformers:

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

pipe = pipeline("text-generation", model="erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy")
model = AutoModelForCausalLM.from_pretrained("erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy")
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 erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy

SGLang

How to use erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy 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 "erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy" \
    --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": "erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy",
		"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 "erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy" \
        --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": "erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy with Docker Model Runner:
```
docker model run hf.co/erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy
```

Objective

The goal of this project is to enhance the reasoning ability of the compact Qwen2.5-0.5B model on Turkish math questions. Using supervised fine-tuning (SFT) on simpler examples as a starting point, the model will be progressively improved through curriculum learning, and later refined using Group Relative Policy Optimization (GRPO) to boost multi-step reasoning performance.

This model is intended for:

Research on curriculum learning in small models
Evaluating Turkish math reasoning tasks

Limitations

Currently only trained on simpler math examples — lacks robustness for multi-step or abstract reasoning.
May produce incorrect or overconfident answers on complex tasks.
Performance may be sensitive to prompt phrasing.

Roadmap

Phase 1: SFT with basic arithmatic and math problems
Phase 2: SFT with moderately difficult math problems
Phase 3: SFT with full-scale GSM8K-TR complexity
Phase 4: GRPO-based training to optimize multi-step reasoning and reduce hallucinations

How to Use

You can easily run inference using the Transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "erayalp/qwen2.5-0.5b-instruct-sft-v1-tr-math-easy"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Ali’nin 3 kalemi vardı. 2 kalem daha aldı. Ali’nin şimdi kaç kalemi var?"

inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=256)

print(tokenizer.decode(output[0], skip_special_tokens=True))

Downloads last month: 14

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(783)

this model

Finetunes

1 model

erayalp
/

qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy