Instructions to use little1d/MolEditAgent-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use little1d/MolEditAgent-7B with Transformers:

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

pipe = pipeline("text-generation", model="little1d/MolEditAgent-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("little1d/MolEditAgent-7B")
model = AutoModelForCausalLM.from_pretrained("little1d/MolEditAgent-7B", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use little1d/MolEditAgent-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "little1d/MolEditAgent-7B"
# 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/MolEditAgent-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/little1d/MolEditAgent-7B

SGLang

How to use little1d/MolEditAgent-7B 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/MolEditAgent-7B" \
    --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/MolEditAgent-7B",
		"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/MolEditAgent-7B" \
        --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/MolEditAgent-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use little1d/MolEditAgent-7B with Docker Model Runner:
```
docker model run hf.co/little1d/MolEditAgent-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MolEditAgent-7B

MolEditAgent is the Stage-1 model of the MolAct framework. It is fine-tuned to master basic molecular editing primitives within an agentic loop.

Key Features

Actionable Operations: Learns to perform Add, Delete, and Substitute operations on SMILES.
Tool-Augmented: Trained to interact with chemical tools for validity checking and similarity control.
Agentic Reasoning: Unlike static generators, it can "Think" and "Call" tools to refine the editing process.

Training & Usage

This model serves as the foundation for property-driven optimization.

Code: https://github.com/little1d/MolAct
ArXiv https://arxiv.org/abs/2512.20135

If you use MolAct in your research, please cite:

@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}
}