## Alternative Option For RLHF: Direct Preference Optimization
For those seeking an alternative to Reinforcement Learning from Human Feedback (RLHF), Direct Preference Optimization (DPO) presents a compelling option. DPO, as detailed in the paper (available at [https://arxiv.org/abs/2305.18290](https://arxiv.org/abs/2305.18290)), DPO offers an low-cost way to perform RLHF and usually request less computation resources compares to PPO.
For those seeking an alternative to Reinforcement Learning from Human Feedback (RLHF), Direct Preference Optimization (DPO) presents a compelling option. DPO, as detailed in this [paper](https://arxiv.org/abs/2305.18290), DPO offers an low-cost way to perform RLHF and usually request less computation resources compares to PPO.
## Alternative Option For RLHF: Simple Preference Optimization
Simple Preference Optimization (SimPO) from this [paper](https://arxiv.org/pdf/2405.14734) is similar to DPO but it abandons the use of the reference model, which makes the training more efficient. It also adds a reward shaping term called target reward margin to enhance training stability. It also use length normalization to better align with the inference process.
### DPO Training Stage1 - Supervised Instructs Tuning
@ -522,7 +525,7 @@ Coati is developed by ColossalAI Team:
- [Fazzie](https://fazzie-key.cool/about/index.html) Contributing to the algorithm and development for SFT.
- [ofey404](https://github.com/ofey404) Contributing to both front-end and back-end development.
- [Wenhao Chen](https://github.com/CWHer) Contributing to subsequent code enhancements and performance improvements.
- [Anbang Ye](https://github.com/YeAnbang) Contributing to the refactored version with updated acceleration framework, LoRA, DPO and PPO.
- [Anbang Ye](https://github.com/YeAnbang) Contributing to the refactored PPO version with updated acceleration framework. Add support for DPO, SimPO.
The PhD student from [(HPC-AI) Lab](https://ai.comp.nus.edu.sg/) also contributed a lot to this project.
- [Alternative Option For RLHF: Simple Preference Optimization](#alternative-option-for-rlhf-simple-preference-optimization)
- [List of Supported Models](#list-of-supported-models)
- [Hardware Requirements](#hardware-requirements)
- [Inference example](#inference-example)
@ -717,14 +718,29 @@ For DPO training, you only need the preference dataset. Please follow the instru
#### Step 2: Training
You can run the [train_dpo.sh](./examples/training_scripts/train_dpo.sh) to start DPO training. Please refer to the [training configuration](#training-configuration) section for details regarding supported training options.
You can run the [train_dpo.sh](./examples/training_scripts/train_dpo.sh) to start DPO training. Please refer to the [training configuration](#training-configuration) section for details regarding supported training options. Following the trend of recent research on DPO-like alignment methods, we added option for the user to choose from, including whether to do length normalization , reward shaping and whether to use a reference model in calculating implicit reward. Here are those options,
```
--beta 0.1 \ # the temperature in DPO loss, Default to 0.1
--gamma 0.0 \ # the reward target margin in the SimPO paper, Default to 0.
--disable_reference_model \ # whether to disable the reference model, if set, the implicit reward will be calculated solely from the actor. Default to enable reference model in DPO
--length_normalization \ # whether to apply length normalization, Default to not use
### Alternative Option For RLHF: Simple Preference Optimization
We support the method introduced in the paper [SimPO: Simple Preference Optimization
with a Reference-Free Reward](https://arxiv.org/pdf/2405.14734) (SimPO). Which is a reference model free aligment method that add length normalization and reward shaping to the DPO loss to enhance training stability and efficiency. As the method doesn't deviate too much from DPO, we add support for length normalization and SimPO reward shaping in our DPO implementation. Simply set the flag to disable the use of the reference model, set the reward target margin and enable length normalization in the DPO training script.
For PPO, we suggest using Tensor Parallelism. The following table shows the VRAM consumption of training a 7B model on a dummy dataset with 2048 sequence length and 512 layout length with different tp_size (equal to the number of GPUs). In this experiment, we use an H800 GPU with 80GB VRAM.
YeAnbang
5 months ago