Instructions to use zzzzk77/Qwen3-0.6B-SafeMath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zzzzk77/Qwen3-0.6B-SafeMath with Transformers:

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

pipe = pipeline("text-generation", model="zzzzk77/Qwen3-0.6B-SafeMath")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zzzzk77/Qwen3-0.6B-SafeMath")
model = AutoModelForCausalLM.from_pretrained("zzzzk77/Qwen3-0.6B-SafeMath", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zzzzk77/Qwen3-0.6B-SafeMath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zzzzk77/Qwen3-0.6B-SafeMath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zzzzk77/Qwen3-0.6B-SafeMath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zzzzk77/Qwen3-0.6B-SafeMath

SGLang

How to use zzzzk77/Qwen3-0.6B-SafeMath 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 "zzzzk77/Qwen3-0.6B-SafeMath" \
    --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": "zzzzk77/Qwen3-0.6B-SafeMath",
		"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 "zzzzk77/Qwen3-0.6B-SafeMath" \
        --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": "zzzzk77/Qwen3-0.6B-SafeMath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zzzzk77/Qwen3-0.6B-SafeMath with Docker Model Runner:
```
docker model run hf.co/zzzzk77/Qwen3-0.6B-SafeMath
```

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

Fine-tuned Qwen3 causal language model checkpoint for SafeMath experiments.

Model Details

Architecture: Qwen3ForCausalLM
Model type: qwen3
Precision: bfloat16
Context length: 40,960 tokens
Hidden layers: 28
Hidden size: 1,024
Attention heads: 16

Training Summary

Epochs: 1.0
Batch size: 8
Gradient accumulation: 2
Max sequence length: 1,024
Learning rate: 1.5e-5
Weight decay: 0.1
Warmup ratio: 0.05
Global steps: 2,023
Validation loss: 0.8385
Validation perplexity: 2.3129

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zzzzk77/Qwen3-0.6B-SafeMath"

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

Files

This repository contains a safetensors model checkpoint, tokenizer files, generation config, training config, and training metrics.

Downloads last month: 3

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for zzzzk77/Qwen3-0.6B-SafeMath

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1363)

this model