Instructions to use yuuxia/acts-controller with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuuxia/acts-controller with Transformers:

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

pipe = pipeline("text-generation", model="yuuxia/acts-controller")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yuuxia/acts-controller")
model = AutoModelForCausalLM.from_pretrained("yuuxia/acts-controller")
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 yuuxia/acts-controller with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yuuxia/acts-controller

SGLang

How to use yuuxia/acts-controller 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 "yuuxia/acts-controller" \
    --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": "yuuxia/acts-controller",
		"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 "yuuxia/acts-controller" \
        --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": "yuuxia/acts-controller",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yuuxia/acts-controller with Docker Model Runner:
```
docker model run hf.co/yuuxia/acts-controller
```

nielsr HF Staff commited on 1 day ago

Commit

451deb6

verified ·

1 Parent(s): 8a18545

Add model card for ACTS Controller

Browse files

This PR adds a comprehensive model card for the ACTS (Agentic Chain-of-Thought Steering) controller agent.

It includes:
- Metadata for `pipeline_tag`, `library_name`, and `license`.
- Links to the research paper [Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning](https://huggingface.co/papers/2606.03965).
- A link to the official [GitHub repository](https://github.com/Andree-9/ACTS).
- Sample usage instructions for running the inference demo as found in the repository's README.
- The BibTeX citation from the paper.

Files changed (1) hide show

README.md +47 -0

README.md ADDED Viewed

	@@ -0,0 +1,47 @@

+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- reasoning
+- agent
+- chain-of-thought
+---
+# ACTS: Agentic Chain-of-Thought Steering Controller
+This repository contains the controller agent for **ACTS (Agentic Chain-of-Thought Steering)**, presented in the paper [Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning](https://huggingface.co/papers/2606.03965).
+ACTS is a framework where a lightweight controller agent adaptively steers a frozen reasoner (such as DeepSeek-R1) step-by-step under a thinking-token budget. By formulating reasoning steering as a Markov decision process, the controller chooses a reasoning strategy and a short steering phrase at each step to enable controllable accuracy–efficiency trade-offs.
+## Resources
+- **Paper:** [Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning](https://huggingface.co/papers/2606.03965)
+- **Repository:** [Andree-9/ACTS](https://github.com/Andree-9/ACTS)
+- **SFT Data:** [yuuxia/controller-sft-data](https://huggingface.co/datasets/yuuxia/controller-sft-data)
+## Quick Start Inference
+To use this controller to steer a reasoner, follow the setup instructions in the [GitHub repository](https://github.com/Andree-9/ACTS) and run the following command:
+```bash
+conda activate slime
+./scripts/run_acts_inference.sh \
+    --controller yuuxia/acts-controller \
+    --reasoner   deepseek-ai/DeepSeek-R1-Distill-Qwen-7B \
+    --benchmark  aime2024 \
+    --budget     10000
+```
+## Citation
+```bibtex
+@misc{xia2026acts,
+      title={Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning},
+      author={Yu Xia and Zhouhang Xie and Xin Xu and Byungkyu Kang and Prarit Lamba and Xiang Gao and Julian McAuley},
+      year={2026},
+      eprint={2606.03965},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2606.03965},
+}
+```