Instructions to use bknyaz/Qwen3-0.6B-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bknyaz/Qwen3-0.6B-Math with Transformers:

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

pipe = pipeline("text-generation", model="bknyaz/Qwen3-0.6B-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bknyaz/Qwen3-0.6B-Math")
model = AutoModelForCausalLM.from_pretrained("bknyaz/Qwen3-0.6B-Math")
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 Settings

vLLM

How to use bknyaz/Qwen3-0.6B-Math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bknyaz/Qwen3-0.6B-Math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bknyaz/Qwen3-0.6B-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bknyaz/Qwen3-0.6B-Math

SGLang

How to use bknyaz/Qwen3-0.6B-Math 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 "bknyaz/Qwen3-0.6B-Math" \
    --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": "bknyaz/Qwen3-0.6B-Math",
		"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 "bknyaz/Qwen3-0.6B-Math" \
        --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": "bknyaz/Qwen3-0.6B-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bknyaz/Qwen3-0.6B-Math with Docker Model Runner:
```
docker model run hf.co/bknyaz/Qwen3-0.6B-Math
```

bknyaz commited on Jan 30

Commit

f937caa

verified ·

1 Parent(s): 80e33c1

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -14,7 +14,8 @@ base_model:
 # Qwen3-0.6B-Math
-This model is obtained by fine-tuning Qwen/Qwen3-0.6B on the gsm8k train split. It used in the experiments described in https://bknyaz.github.io/blog/2026/meta-merge/.
 Single A100 was used for fine-tuning and evaluation.
 The following versions were used for train/eval:
@@ -75,4 +76,4 @@ python -m lm_eval --model vllm --model_args pretrained=${model},tensor_parallel_
 ## License
-Please refer to the license of the original model [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).

 # Qwen3-0.6B-Math
+This model is obtained by fine-tuning Qwen/Qwen3-0.6B on the [gsm8k](https://huggingface.co/datasets/openai/gsm8k) train split.
+The model is used in the experiments described in https://bknyaz.github.io/blog/2026/meta-merge/.
 Single A100 was used for fine-tuning and evaluation.
 The following versions were used for train/eval:
 ## License
+Please refer to the license of the original model [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) and dataset [gsm8k](https://huggingface.co/datasets/openai/gsm8k).