Instructions to use XLearning-SCU/HERO-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XLearning-SCU/HERO-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="XLearning-SCU/HERO-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("XLearning-SCU/HERO-4B")
model = AutoModelForMultimodalLM.from_pretrained("XLearning-SCU/HERO-4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XLearning-SCU/HERO-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XLearning-SCU/HERO-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XLearning-SCU/HERO-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/XLearning-SCU/HERO-4B

SGLang

How to use XLearning-SCU/HERO-4B 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 "XLearning-SCU/HERO-4B" \
    --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": "XLearning-SCU/HERO-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "XLearning-SCU/HERO-4B" \
        --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": "XLearning-SCU/HERO-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use XLearning-SCU/HERO-4B with Docker Model Runner:
```
docker model run hf.co/XLearning-SCU/HERO-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

HERO-4B

Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents

🔍 Overview

HERO-4B is post-trained from Qwen3.5-4B using HERO (HiErarchical ReinfOrcement learning) to improve token efficiency while prioritizing task resolution.

Item	Description
Base model	`Qwen/Qwen3.5-4B`
Parameters	4B (dense)
Architecture and tokenizer	Inherited from Qwen3.5-4B
Training	HERO on 640 multilingual SWE tasks from SWE-Gym, Multi-SWE-bench, and SWE-rebench
Intended use	Repository-level coding agents
Format	Hugging Face weights and tokenizer

HERO combines capability-based efficiency gating, resolution-first clipping, and efficiency credit at trajectory and turn levels. Qwen3.5 is the backbone; this release contains the HERO post-trained weights.

Usage

Follow the preparation guide in the HERO code repository. From that repository's root, with this model saved under ../models/HERO-4B/:

MODEL=../models/HERO-4B bash eval/run_eval_swebench_verified.sh
MODEL=../models/HERO-4B bash eval/run_eval_swebench_multilingual.sh

Evaluation Settings

The released evaluation scripts use the following defaults for both SWE-bench Verified and SWE-bench Multilingual:

Setting	Value
Agent scaffold	Claude Code
Inference backend	SGLang
Temperature	0.6
Top-p	0.95
Context length	131,072 tokens
Maximum output per call	16,000 tokens
Maximum agent turns	200
Automatic context compaction	Disabled
Tools	Default tools, excluding WebFetch, WebSearch, and Agent

See the evaluation script for configuration options.

License

Apache-2.0. See LICENSE. We acknowledge the Qwen team for the base model.

📖 Citation

If you find HERO useful, please cite our paper:

@misc{li2026hero,
  title         = {Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents},
  author        = {Haobin Li and Liang Jiang and Zhenyu Huang and Mouxing Yang and Xi Peng},
  year          = {2026},
  eprint        = {2609.38885},
  archivePrefix = {arXiv},
  primaryClass  = {cs.SE},
  url           = {https://arxiv.org/abs/2609.38885}
}