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

Libraries

How to use CogEvol/CogEvol-4B with Transformers:

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

pipe = pipeline("text-generation", model="CogEvol/CogEvol-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("CogEvol/CogEvol-4B")
model = AutoModelForMultimodalLM.from_pretrained("CogEvol/CogEvol-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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CogEvol/CogEvol-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CogEvol/CogEvol-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": "CogEvol/CogEvol-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CogEvol/CogEvol-4B

SGLang

How to use CogEvol/CogEvol-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 "CogEvol/CogEvol-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": "CogEvol/CogEvol-4B",
		"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 "CogEvol/CogEvol-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": "CogEvol/CogEvol-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

CogEvol-4B

CogEvol-4B is an open post-trained model for Learning Environment Generation (LEG): given a natural-language course brief, it generates complete, usable learning artifacts in a single pass — a structured-JSON slide page, or a self-contained interactive HTML page that runs directly in the browser (simulations, visualizations, interactive exercises, and more).

It is the small open member of the CogEvol family, trained with a three-stage recipe (mix SFT → Slide RL → interactive-HTML RL) on 53,687 verified samples, using a hybrid rule + VLM reward system hardened against reward hacking — interactivity is measured by automated probes, never just judged. Paper: CogEvol: Towards Efficient and Reliable Learning Environment Generation (link below).

Quick start

Run it on your laptop: the GitHub repository is the complete deployment guide — a step-by-step llama.cpp setup, a serve.sh with the validated flags, the OpenMAIC app integration (runs fully offline), evaluation scripts, and a troubleshooting table. A quantized Q4_K_M GGUF (~2.4 GB) is available at CogEvol/CogEvol-4B-Q4_K_M-GGUF.
Serving this BF16 checkpoint: sglang / vLLM / llama.cpp all work. Two rules from the serving guide: disable thinking mode at inference, and when generating slides use the system prompt template shipped in the GitHub repository.

Citation

If you find CogEvol useful, please cite:

@misc{tu2026cogevolefficientreliablelearning,
      title={CogEvol: Towards Efficient and Reliable Learning Environment Generation}, 
      author={Shangqing Tu and Daniel Zhang-Li and Yucheng Wang and Shiyu Gan and Yanpeng Wang and Huiqiang Rong and Mofei Chen and Shen Yang and Yini Chen and Yinuo Duan and Haoxuan Li and Binglin Liu and Ye He and Danqi Zheng and Zhanxin Hao and Yuxuan Wu and Mengting Tao and Yuqiu Liu and Jifan Yu and Juanzi Li and Bin Xu and Lei Hou and Huiqin Liu and Yu Zhang},
      year={2026},
      eprint={2608.30968},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2608.30968}
}

Downloads last month: 1

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for CogEvol/CogEvol-4B

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(561)

this model

Quantizations

3 models

Space using CogEvol/CogEvol-4B 1

Paper for CogEvol/CogEvol-4B

CogEvol: Towards Efficient and Reliable Learning Environment Generation

Paper • 2608.30968 • Published 1 day ago • 24

CogEvol
/

CogEvol-4B