Instructions to use little1d/MolOptAgent-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use little1d/MolOptAgent-3B with Transformers:

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

pipe = pipeline("text-generation", model="little1d/MolOptAgent-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("little1d/MolOptAgent-3B")
model = AutoModelForCausalLM.from_pretrained("little1d/MolOptAgent-3B")
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

vLLM

How to use little1d/MolOptAgent-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "little1d/MolOptAgent-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "little1d/MolOptAgent-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/little1d/MolOptAgent-3B

SGLang

How to use little1d/MolOptAgent-3B 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 "little1d/MolOptAgent-3B" \
    --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": "little1d/MolOptAgent-3B",
		"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 "little1d/MolOptAgent-3B" \
        --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": "little1d/MolOptAgent-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use little1d/MolOptAgent-3B with Docker Model Runner:
```
docker model run hf.co/little1d/MolOptAgent-3B
```

little1d commited on Dec 25, 2025

Commit

7cda672

verified ·

1 Parent(s): c5a4c07

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -1

README.md CHANGED Viewed

@@ -25,4 +25,19 @@ base_model:
 ### Links
 - **GitHub Repository:** [https://github.com/little1d/MolAct](https://github.com/little1d/MolAct)
-- **Framework:** Agentic RL with tool-integrated feedback.

 ### Links
 - **GitHub Repository:** [https://github.com/little1d/MolAct](https://github.com/little1d/MolAct)
+- **ArXiv** [https://arxiv.org/abs/2512.20135](https://arxiv.org/abs/2512.20135)
+If you use MolAct in your research, please cite:
+```bibtex
+@article{molact2025,
+  title={MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization},
+  author={Zhuo Yang and Yeyun Chen and Jiaqing Xie and Ben Gao and Shuaike Shen and Wanhao Liu and Liujia Yang and Beilun Wang and Tianfan Fu and Yuqiang Li},
+  year={2025},
+  eprint={2512.20135},
+  archivePrefix={arXiv},
+  primaryClass={cs.AI},
+  url={https://arxiv.org/abs/2512.20135}
+}
+```