Instructions to use bdytx5/ppo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bdytx5/ppo with Transformers:

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

pipe = pipeline("text-generation", model="bdytx5/ppo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bdytx5/ppo")
model = AutoModelForCausalLM.from_pretrained("bdytx5/ppo", 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 bdytx5/ppo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bdytx5/ppo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bdytx5/ppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bdytx5/ppo

SGLang

How to use bdytx5/ppo 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 "bdytx5/ppo" \
    --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": "bdytx5/ppo",
		"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 "bdytx5/ppo" \
        --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": "bdytx5/ppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bdytx5/ppo with Docker Model Runner:
```
docker model run hf.co/bdytx5/ppo
```

ppo / README.md

bdytx5

End of training

ca9737f verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

2.17 kB

	---
	base_model: cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
	library_name: transformers
	model_name: ppo
	tags:
	- generated_from_trainer
	licence: license
	---

	# Model Card for ppo

	This model is a fine-tuned version of [cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr](https://huggingface.co/cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr).
	It has been trained using [TRL](https://github.com/huggingface/trl).

	## Quick start

	```python
	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="bdytx5/ppo", device="cuda")
	output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
	print(output["generated_text"])
	```

	## Training procedure

	[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/byyoung3/huggingface/runs/99ekcp31)

	This model was trained with PPO, a method introduced in [Fine-Tuning Language Models from Human Preferences](https://huggingface.co/papers/1909.08593).

	### Framework versions

	- TRL: 0.12.0
	- Transformers: 4.53.3
	- Pytorch: 2.2.1
	- Datasets: 4.0.0
	- Tokenizers: 0.21.2

	## Citations

	Cite PPO as:

	```bibtex
	@article{mziegler2019fine-tuning,
	title = {{Fine-Tuning Language Models from Human Preferences}},
	author = {Daniel M. Ziegler and Nisan Stiennon and Jeffrey Wu and Tom B. Brown and Alec Radford and Dario Amodei and Paul F. Christiano and Geoffrey Irving},
	year = 2019,
	eprint = {arXiv:1909.08593}
	}
	```

	Cite TRL as:

	```bibtex
	@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}}
	}
	```