Beaver is a highly modular open-source RLHF framework developed by the PKU-Alignment team at Peking University. It aims to provide training data and a reproducible code pipeline for alignment research, especially constrained alignment LLM research via Safe RLHF methods.

The key features of Beaver are:

• Support SFT, RLHF and Safe RLHF training for popular pre-trained models: LLaMA, OPT, etc.
• Provide a large human-labeled dataset (up to 1M pairs) including both helpful and harmless preferences to support reproducible RLHF research.
• Support training for Reward Model & Cost Model, and provide pre-trained checkpoints.
• Support customized parameters and datasets for SFT and RLHF.
• Provide multi-scale metrics for safety constraints verification, e.g., BIG-bench, GPT-4 Evaluation.

• Constrained Value Alignment via Safe RLHF
• Comparison with Other RLHF Libraries
• PKU-SafeRLHF-Dataset
  • PKU-SafeRLHF-10K
  • PKU-SafeRLHF-1M
• Why "Beaver"
• Beaver vs. Alpaca
• Installation
• Training
• Custom Datasets
• Inference
  • Interactive CLI Demo
  • Interactive Arena
• Benchmark and Evaluation
  • Arena via Reward and Cost Models
  • BIG-bench
  • GPT-4 Evaluation
• Future Plans
• Citation
• PKU-Alignment Team
• License

Reinforcement Learning from Human Feedback: reward maximization via preference learning

Safe Reinforcement Learning from Human Feedback: constrained reward maximization via preference learning

where $R (\cdot)$ and $C (\cdot)$ are reward and cost functions respectively. They are neural networks known as human proxies trained on human preferences.

The ultimate goal is to find a model $\pi_{\theta}$ that is both helpful (high reward) and harmless (low cost).

Compare with other frameworks supporting RLHF, safe-rlhf is the first framework to support all stages from SFT to RLHF and Evaluation. In addition, safe-rlhf is the first framework that takes safety preference under consideration during the RLHF stage. It holds a more theoretical guarantee for constrained parameter searching in the policy space.

The PKU-SafeRLHF dataset is a human-labeled dataset containing both performance and safety preferences. It includes constraints in over ten dimensions, such as insults, immorality, crime, emotional harm, and privacy, among others. These constraints are designed for fine-grained value alignment in RLHF technology.

To facilitate multi-round fine-tuning, we will release the initial parameter weights, required datasets, and training parameters for each round. This ensures reproducibility in scientific and academic research. The dataset will be released gradually through rolling updates.

The dataset is available on Hugging Face: PKU-Alignment/PKU-SafeRLHF.

PKU-SafeRLHF-10K is a subset of PKU-SafeRLHF that contains the first round of Safe RLHF training data with 10K instances, including safety preferences. You can find it on Hugging Face: PKU-Alignment/PKU-SafeRLHF-10K.

We will gradually release the full Safe-RLHF datasets, which include 1M human-labeled pairs for both helpful and harmless preferences. The pioneer dataset with 100K pairs will be released soon.

Beaver is a large language model based on LLaMA, trained using safe-rlhf. It is developed upon the foundation of the Alpaca model, by collecting human preference data related to helpfulness and harmlessness and employing the Safe RLHF technique for training. While maintaining the helpful performance of Alpaca, Beaver significantly improves its harmlessness.

Beavers are known as the "natural dam engineers" as they are adept at using branches, shrubs, rocks, and soil to build dams and small wooden houses, creating wetland environments suitable for other creatures to inhabit, making them an indispensable part of the ecosystem. To ensure the safety and reliability of Large Language Models (LLMs) while accommodating a wide range of values across different populations, the Peking University team has named their open-source model "Beaver" and aims to build a dam for LLMs through the Constrained Value Alignment (CVA) technology. This technology enables fine-grained labeling of information and, combined with secure reinforcement learning methods, significantly reduces model bias and discrimination, thereby enhancing the model's safety. Analogous to the role of beavers in the ecosystem, the Beaver model will provide crucial support for the development of large language models and make positive contributions to the sustainable development of artificial intelligence technology.

Following the evaluation methodology of the Vicuna model, we utilized GPT-4 to evaluate Beaver. The results indicate that, compared to Alpaca, Beaver exhibits significant improvements in multiple dimensions related to safety.

Significant distribution shift for safety preferences after utilizing the Safe RLHF pipeline on the Alpaca-7B model.

Clone the source code from GitHub:

git clone https://github.com/PKU-Alignment/safe-rlhf.git
cd safe-rlhf

Native Runner: Setup a conda environment using conda / mamba:

conda env create --file conda-recipe.yaml  # or `mamba env create --file conda-recipe.yaml`

This will automatically setup all dependencies.

Containerized Runner: Other than using the native machine with conda isolation, as an alternative, you can also use docker images to configure the environment.

Firstly, please follow NVIDIA Container Toolkit: Installation Guide and NVIDIA Docker: Installation Guide to setup nvidia-docker. Then you can run:

make docker-run

This command will build and start a docker container installed with proper dependencies. The host path / will be mapped to /host and the current working directory will be mapped to /workspace inside the container.

safe-rlhf supports a complete pipeline from Supervised Fine-Tuning (SFT) to preference model training to RLHF alignment training.

0. Follow the instructions in section Installation to setup the training environment properly.

conda activate safe-rlhf
export WANDB_API_KEY="..."  # your W&B API key here

or

make docker-run
export WANDB_API_KEY="..."  # your W&B API key here

1. Supervised Fine-Tuning (SFT)

bash scripts/sft.sh \
    --model_name_or_path <your-model-name-or-checkpoint-path> \
    --output_dir output/sft

NOTE: You may need to update some of the parameters in the script according to your machine setup, such as the number of GPUs for training, the training batch size, etc.

2. Value Models (reward model & cost model)

bash scripts/reward-model.sh \
    --model_name_or_path <your-model-name-or-checkpoint-path> \
    --output_dir output/rm

bash scripts/cost-model.sh \
    --model_name_or_path <your-model-name-or-checkpoint-path> \
    --output_dir output/cm

3. RLHF (Optional)

bash scripts/ppo.sh \
    --actor_model_name_or_path output/sft \
    --reward_model_name_or_path output/rm \
    --output_dir output/ppo

4. Safe-RLHF

bash scripts/ppo-lag.sh \
    --actor_model_name_or_path output/sft \
    --reward_model_name_or_path output/rm \
    --cost_model_name_or_path output/cm \
    --output_dir output/ppo-lag

An example of commands to run the whole pipeline with LLaMA-7B:

conda activate safe-rlhf
bash scripts/sft.sh --model_name_or_path ~/models/llama-7b --output_dir output/sft
bash scripts/reward-model.sh --model_name_or_path ~/models/llama-7b --output_dir output/rm
bash scripts/cost-model.sh --model_name_or_path ~/models/llama-7b --output_dir output/cm
bash scripts/ppo-lag.sh \
    --actor_model_name_or_path output/sft \
    --reward_model_name_or_path output/rm \
    --cost_model_name_or_path output/cm \
    --output_dir output/ppo-lag

All training processes listed above are tested with LLaMA-7B on a cloud server with 8 x NVIDIA A800-80GB GPUs.

safe-rlhf provides an abstraction to create datasets for all of the Supervised Fine-Tuning, preference model training, and RL training stages.

class RawSample(TypedDict, total=False):
    """Raw sample type.

    For SupervisedDataset, should provide (input, answer) or (dialog).
    For PreferenceDataset, should provide (input, answer, other_answer, better).
    For SafetyPreferenceDataset, should provide (input, answer, other_answer, safer, is_safe, is_other_safe).
    For PromptOnlyDataset, should provide (input).
    """

    # Texts
    input: NotRequired[str]  # either `input` or `dialog` should be provided
    """User input text."""
    answer: NotRequired[str]
    """Assistant answer text."""
    other_answer: NotRequired[str]
    """Other assistant answer text via resampling."""
    dialog: NotRequired[list[str]]  # either `input` or `dialog` should be provided
    """Dialog history."""

    # Flags
    better: NotRequired[bool]
    """Whether ``answer`` is better than ``other_answer``."""
    safer: NotRequired[bool]
    """Whether ``answer`` is safer than ``other_answer``."""
    is_safe: NotRequired[bool]
    """Whether ``answer`` is safe."""
    is_other_safe: NotRequired[bool]
    """Whether ``other_answer`` is safe."""

Here is an example to implement a custom dataset (see safe_rlhf/datasets/raw for more examples):

import argparse
from datasets import load_dataset
from safe_rlhf.datasets import RawDataset, RawSample, parse_dataset


class MyRawDataset(RawDataset):
    NAME = 'my-dataset-name'

    def __init__(self, path=None) -> None:
        # Load a dataset from Hugging Face
        self.data = load_dataset(path or 'my-organization/my-dataset')['train']

    def __getitem__(self, index: int) -> RawSample:
        data = self.data[index]
        # Construct a `RawSample` dictionary from your custom dataset item
        return RawSample(
            input=data['col1'],
            answer=data['col2'],
            other_answer=data['col3'],
            better=float(data['col4']) > float(data['col5']),
            ...
        )

    def __len__(self) -> int:
        return len(self.data)  # dataset size


def parse_arguments():
    parser = argparse.ArgumentParser(...)
    parser.add_argument(
        '--datasets',
        type=parse_dataset,
        nargs='+',
        metavar='DATASET[:PROPORTION[:PATH]]',
    )
    ...
    return parser.parse_args()


def main():
    args = parse_arguments()
    ...


if __name__ == '__main__':
    main()

Then you can pass this dataset to the training scripts as:

python3 train.py --datasets my-dataset-name

You may also pass multiple datasets with optionally additional dataset proportions (separated by a colon :). For example:

python3 train.py --datasets alpaca:0.75 my-dataset-name:0.5

This will use randomly split 75% of the Stanford Alpaca dataset and 50% of your custom dataset.

In addition, the dataset argument can also be followed by a local path (separated by a colon :) if you have already cloned the dataset repository from Hugging Face.

git lfs install
git clone https://huggingface.co/datasets/my-organization/my-dataset ~/path/to/my-dataset/repository
python3 train.py --datasets alpaca:0.75 my-dataset-name:0.5:~/path/to/my-dataset/repository

NOTE: The dataset class must be imported before the training script begins to parse the command line arguments.

python3 -m safe_rlhf.serve.cli --model_name_or_path output/sft  # or output/ppo-lag

python3 -m safe_rlhf.serve.arena --red_corner_model_name_or_path output/sft --blue_corner_model_name_or_path output/ppo-lag

scripts/arena-evaluation.sh \
    --red_corner_model_name_or_path output/sft \
    --blue_corner_model_name_or_path output/ppo-lag \
    --reward_model_name_or_path output/rm \
    --cost_model_name_or_path output/cm \
    --output_dir output/arena-evaluation