Instructions to use ElvisWang111/Qwen3-4B-OutsideTheBox-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ElvisWang111/Qwen3-4B-OutsideTheBox-SFT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ElvisWang111/Qwen3-4B-OutsideTheBox-SFT") 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("ElvisWang111/Qwen3-4B-OutsideTheBox-SFT") model = AutoModelForCausalLM.from_pretrained("ElvisWang111/Qwen3-4B-OutsideTheBox-SFT", 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 ElvisWang111/Qwen3-4B-OutsideTheBox-SFT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ElvisWang111/Qwen3-4B-OutsideTheBox-SFT
- SGLang
How to use ElvisWang111/Qwen3-4B-OutsideTheBox-SFT 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 "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT" \ --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": "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT", "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 "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT" \ --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": "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ElvisWang111/Qwen3-4B-OutsideTheBox-SFT with Docker Model Runner:
docker model run hf.co/ElvisWang111/Qwen3-4B-OutsideTheBox-SFT
Qwen3-4B-OutsideTheBox-SFT
This repository provides the supervised fine-tuning checkpoint developed for the paper Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Model Description
The model is initialized from Qwen3-4B and fine-tuned on workflow-conditioned mathematical reasoning data. The training examples pair problems with external workflows of varying quality so that the model can learn to use helpful guidance while handling misleading guidance.
Intended Use
This checkpoint is intended for research on mathematical reasoning, external workflow utilization, and robustness to incorrect guidance. It corresponds to the SFT stage reported in the paper.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
Base Model
- Base model:
Qwen/Qwen3-4B - Training stage: supervised fine-tuning (SFT)
- Domain: workflow-conditioned mathematical reasoning
- Downloads last month
- 15
