Instructions to use tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha with Transformers:

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

pipe = pipeline("text-generation", model="tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha")
model = AutoModelForCausalLM.from_pretrained("tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha", device_map="auto")
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 tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha

SGLang

How to use tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha 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 "tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha" \
    --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": "tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha",
		"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 "tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha" \
        --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": "tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha with Docker Model Runner:
```
docker model run hf.co/tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha
```

Qwen2.5-1.5B SFT (Practice Model)

This is a practice / for-learning-only model based on Qwen/Qwen2.5-1.5B, fine-tuned with Supervised Fine-Tuning (SFT) as a personal study exercise.

What this is

Base model: Qwen/Qwen2.5-1.5B
Training method: SFT (Supervised Fine-Tuning)
Purpose: educational / practice only — not intended for production use
Expect poor or inconsistent outputs; this checkpoint exists to learn the SFT pipeline, not to be a useful assistant

Intended use

Studying how SFT changes a small base model
Comparing SFT vs. base model behavior
Experimenting with training data, hyperparameters, and merges

Do not use this model for any real-world task or deployment.

License

Apache 2.0, inherited from the base Qwen2.5 model. See the Qwen2.5 license for details.

Downloads last month: 294

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for tayaee/Qwen2.5-1.5B-Instruct-ko-Reasoning-alpha

Base model

Qwen/Qwen2.5-1.5B

Finetuned

(404)

this model