Instructions to use ChongliQin/iw-SFT-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChongliQin/iw-SFT-32B with Transformers:

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

pipe = pipeline("text-generation", model="ChongliQin/iw-SFT-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChongliQin/iw-SFT-32B")
model = AutoModelForCausalLM.from_pretrained("ChongliQin/iw-SFT-32B")
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 ChongliQin/iw-SFT-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChongliQin/iw-SFT-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChongliQin/iw-SFT-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChongliQin/iw-SFT-32B

SGLang

How to use ChongliQin/iw-SFT-32B 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 "ChongliQin/iw-SFT-32B" \
    --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": "ChongliQin/iw-SFT-32B",
		"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 "ChongliQin/iw-SFT-32B" \
        --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": "ChongliQin/iw-SFT-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChongliQin/iw-SFT-32B with Docker Model Runner:
```
docker model run hf.co/ChongliQin/iw-SFT-32B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

This is our model using our algorithm iw-SFT (importance weighted SFT). For more details of the algorithm please refer to our paper below.

At a high level, the algorithm is motivated by showing first that SFT and RL are connected: the SFT objective lower bounds the RL objective. We show that by reweighting the curated dataset adaptively during training, i.e. iw-SFT, we can obtain a much tighter bound to RL than SFT alone.

We benchmark our algorithm on maths reasoning tasks, see table below.

Authors

Chongli Qin and Jost Tobias Springenberg

Model Details

Blog Post: Supervised Fine Tuning is Reinforcement Learning (and can be improved)

Repository: iw-sft

Paper: Supervised Fine Tuning is Reinforcement Learning (and can be improved)

For all links and general information see [here](For more general information see here.

Evaluation

Metric	s1-32B	s1.1-32B	iw-SFT-32B	o1-preview	o1	DeepSeek-R1	DeepSeek-R1-Distill-Qwen-32B
# examples	1K	1K	1K	?	?	>800K	800K
AIME2024	56.7	56.7	66.7	40.0	74.4	79.8	72.6
AIME2025 I	26.7	60.0	53.3	37.5	?	65.0	46.1
MATH500	93.0	95.4	94.8	81.4	94.8	97.3	94.3
GPQA-Diamond	59.6	63.6	64.1	75.2	77.3	71.5	62.1