Instructions to use ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL with Transformers:

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

pipe = pipeline("text-generation", model="ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL")
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/Qwen3.5-9B-OutsideTheBox-RL")
model = AutoModelForCausalLM.from_pretrained("ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL", 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/Qwen3.5-9B-OutsideTheBox-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL"
# 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/Qwen3.5-9B-OutsideTheBox-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL

SGLang

How to use ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL 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/Qwen3.5-9B-OutsideTheBox-RL" \
    --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/Qwen3.5-9B-OutsideTheBox-RL",
		"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/Qwen3.5-9B-OutsideTheBox-RL" \
        --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/Qwen3.5-9B-OutsideTheBox-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL with Docker Model Runner:
```
docker model run hf.co/ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL
```

Qwen3.5-9B-OutsideTheBox-RL

This repository provides the WebShop environment-reward checkpoint developed for the paper Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

Model Description

The model is initialized from Qwen3.5-9B-OutsideTheBox-SFT and further optimized through multi-turn interaction with the WebShop environment. Training uses task instructions paired with grounded good workflows and directly rewards the final raw WebShop outcome in [0, 1]; it does not train on bad-workflow prompts.

RL Data Selection

Candidate tasks come exclusively from successful trajectories in the WebShop TRAIN split. The SFT checkpoint is sampled eight times per task, and tasks with non-constant raw rewards are retained. This produces 153 selected tasks, deterministically divided into 139 training tasks and a disjoint 14-task probe set; official WebShop test tasks are not used for selection or training.

Training Configuration

Setting	Value
Initial policy	`Qwen3.5-9B-OutsideTheBox-SFT`
Training	Multi-turn environment GRPO
Workflow condition	Grounded good workflow
Reward	Raw WebShop task outcome `[0, 1]`
Generations per prompt	8
Epochs	1
Learning rate	`1e-6`
KL coefficient	`0`
Loss	DAPO
Maximum tool calls	10
Maximum completion length	4,096 tokens

Intended Use

This checkpoint is intended for research on WebShop agents, outcome-based reinforcement learning, and selective reliance on external workflows. Reproducing the reported results requires the WebShop environment and the multi-turn interaction harness used in the paper.

Loading the Model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ElvisWang111/Qwen3.5-9B-OutsideTheBox-RL"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)