Instructions to use CLAUSE-Bielefeld/communicative-baby-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CLAUSE-Bielefeld/communicative-baby-dpo with Transformers:

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

pipe = pipeline("text-generation", model="CLAUSE-Bielefeld/communicative-baby-dpo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CLAUSE-Bielefeld/communicative-baby-dpo")
model = AutoModelForCausalLM.from_pretrained("CLAUSE-Bielefeld/communicative-baby-dpo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CLAUSE-Bielefeld/communicative-baby-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CLAUSE-Bielefeld/communicative-baby-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CLAUSE-Bielefeld/communicative-baby-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CLAUSE-Bielefeld/communicative-baby-dpo

SGLang

How to use CLAUSE-Bielefeld/communicative-baby-dpo 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 "CLAUSE-Bielefeld/communicative-baby-dpo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CLAUSE-Bielefeld/communicative-baby-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "CLAUSE-Bielefeld/communicative-baby-dpo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CLAUSE-Bielefeld/communicative-baby-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CLAUSE-Bielefeld/communicative-baby-dpo with Docker Model Runner:
```
docker model run hf.co/CLAUSE-Bielefeld/communicative-baby-dpo
```

Model Card for dpo_synthetic

This model is a fine-tuned version of bbunzeck/llamalogue. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="fpadovani/communicative-baby-dpo", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with DPO, a method introduced in Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Framework versions

TRL: 0.19.1
Transformers: 4.53.2
Pytorch: 2.7.1
Datasets: 4.0.0
Tokenizers: 0.21.2

Citations

For further information please consult the accompanying paper. If you make use of this model in your work, please also cite the paper:

@inproceedings{padovani-etal-2025-dialogue,
    title = "Dialogue Is Not Enough to Make a Communicative {B}aby{LM} (But Neither Is Developmentally Inspired Reinforcement Learning)",
    author = "Padovani, Francesca  and Bunzeck, Bastian  and Ali, Manar  and Momen, Omar  and Bisazza, Arianna  and Buschmeier, Hendrik  and Zarrie{\ss}, Sina",
    editor = "Charpentier, Lucas  and Choshen, Leshem  and Cotterell, Ryan  and Gul, Mustafa Omer  and Hu, Michael Y.  and Liu, Jing  and Jumelet, Jaap  and Linzen, Tal  and Mueller, Aaron  and Ross, Candace  and Shah, Raj Sanjay  and Warstadt, Alex  and Wilcox, Ethan Gotlieb  and Williams, Adina",
    booktitle = "Proceedings of the First BabyLM Workshop",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.babylm-main.29/",
    pages = "421--435",
}

Cite DPO as:

@inproceedings{rafailov2023direct,
    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
    year         = 2023,
    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}