Instructions to use seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500 with Transformers:

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

pipe = pipeline("text-generation", model="seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500")
model = AutoModelForCausalLM.from_pretrained("seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500", 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 seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500

SGLang

How to use seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500 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 "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500" \
    --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": "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500",
		"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 "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500" \
        --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": "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500 with Docker Model Runner:
```
docker model run hf.co/seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500
```

Qwen3-4B OpenThoughts3 Math SFT — Step 500

This is the Hugging Face export of global step 500 from an experimental supervised fine-tuning run of Qwen/Qwen3-4B on the math portion of open-thoughts/OpenThoughts3-1.2M.

The training data contains 103,760 examples built from OpenThoughts3 math traces. Only complete responses with a closed reasoning block and a boxed final answer were retained. The open target format was used: the Qwen3 thinking block is left empty and the source reasoning plus final answer are trained in the visible response channel.

Training configuration

Checkpoint: global_step_500 (the run was stopped after this checkpoint)
Objective: full-parameter SFT
Global batch size: 256
Micro batch size per GPU: 1 with dynamic batching
Maximum sequence length: 32,768 tokens
Optimizer: AdamW
Learning rate: 5e-6
Scheduler: cosine, 3% warmup
Weight decay: 0.01
Gradient clipping: 1.0
Precision: bfloat16
Hardware for this run: 4 GPUs with sequence parallel size 4

Intended use

This checkpoint is intended for research on mathematical reasoning, SFT, and on-policy distillation. It is an intermediate experimental checkpoint, not a production model. AIME evaluation for this checkpoint has not yet been added to this model card.

Inference

Use the tokenizer and chat template shipped in this repository. For the non-thinking behavior used during training, render prompts with enable_thinking=False when supported by your inference stack.

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype="auto",
    device_map="auto",
)

Data note

Filtering incomplete OpenThoughts3 generations changes the difficulty distribution: questions whose sampled solutions repeatedly hit the source generation limit are underrepresented. Results should therefore be interpreted as training on the complete-answer subset rather than the full unfiltered math distribution.

Downloads last month: 199

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for seomh/Qwen3-4B-OpenThoughts3-Math-SFT-step500

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1006)

this model

seomh
/

Qwen3-4B-OpenThoughts3-Math-SFT-step500