Instructions to use ImReallyOK/qwen3-0.6b-safemath-balanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ImReallyOK/qwen3-0.6b-safemath-balanced with Transformers:

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

pipe = pipeline("text-generation", model="ImReallyOK/qwen3-0.6b-safemath-balanced")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ImReallyOK/qwen3-0.6b-safemath-balanced")
model = AutoModelForCausalLM.from_pretrained("ImReallyOK/qwen3-0.6b-safemath-balanced", 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 ImReallyOK/qwen3-0.6b-safemath-balanced with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ImReallyOK/qwen3-0.6b-safemath-balanced"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ImReallyOK/qwen3-0.6b-safemath-balanced",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ImReallyOK/qwen3-0.6b-safemath-balanced

SGLang

How to use ImReallyOK/qwen3-0.6b-safemath-balanced 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 "ImReallyOK/qwen3-0.6b-safemath-balanced" \
    --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": "ImReallyOK/qwen3-0.6b-safemath-balanced",
		"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 "ImReallyOK/qwen3-0.6b-safemath-balanced" \
        --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": "ImReallyOK/qwen3-0.6b-safemath-balanced",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ImReallyOK/qwen3-0.6b-safemath-balanced with Docker Model Runner:
```
docker model run hf.co/ImReallyOK/qwen3-0.6b-safemath-balanced
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3-0.6B SafeMath Balanced

This model is a safety- and mathematics-oriented fine-tuned version of Qwen3-0.6B.

The released weights correspond to the merged V6 SFT checkpoint-500 model. It is intended for research on mathematical reasoning, safe responses, and general instruction following.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ImReallyOK/qwen3-0.6b-safemath-balanced"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "求方程 x^2 - 5x + 6 = 0 的解。"}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.inference_mode():
    outputs = model.generate(
        **inputs,
        max_new_tokens=2048,
        do_sample=False,
    )

answer = tokenizer.decode(
    outputs[0, inputs.input_ids.shape[1]:],
    skip_special_tokens=True,
)

print(answer)

Downloads last month: -

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for ImReallyOK/qwen3-0.6b-safemath-balanced

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1142)

this model