Instructions to use SaminSkyfall/rloo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SaminSkyfall/rloo with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SaminSkyfall/rloo")
model = AutoModelForCausalLM.from_pretrained("SaminSkyfall/rloo")
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 SaminSkyfall/rloo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SaminSkyfall/rloo

SGLang

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

Docker Model Runner
How to use SaminSkyfall/rloo with Docker Model Runner:
```
docker model run hf.co/SaminSkyfall/rloo
```

Model Card for rloo

This model is a fine-tuned version of Qwen/Qwen3-0.6B. 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="SaminSkyfall/rloo", 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 RLOO, a method introduced in Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs.

Framework versions

TRL: 0.15.2
Transformers: 4.51.3
Pytorch: 2.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citations

Cite RLOO as:

@inproceedings{ahmadian2024back,
    title        = {{Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs}},
    author       = {Arash Ahmadian and Chris Cremer and Matthias Gall{'{e}} and Marzieh Fadaee and Julia Kreutzer and Olivier Pietquin and Ahmet {"{U}}st{"{u}}n and Sara Hooker},
    year         = 2024,
    booktitle    = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), {ACL} 2024, Bangkok, Thailand, August 11-16, 2024},
    publisher    = {Association for Computational Linguistics},
    pages        = {12248--12267},
    editor       = {Lun{-}Wei Ku and Andre Martins and Vivek Srikumar},
}

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 Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 8

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for SaminSkyfall/rloo

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(894)

this model

Paper for SaminSkyfall/rloo

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Paper • 2402.14740 • Published Feb 22, 2024 • 18