|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
|
|
# zephyr-7b-dpo-full-ExPO |
|
|
|
The extrapolated (ExPO) model based on [`alignment-handbook/zephyr-7b-dpo-full`](https://huggingface.co/alignment-handbook/zephyr-7b-dpo-full) and [`alignment-handbook/zephyr-7b-sft-full`](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper. |
|
|
|
Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. |
|
|
|
This model achieves the **18.0%** win rate and **20.2%** LC win rate on **AlpacaEval 2.0**. |
|
|
|
## Evaluation Results |
|
|
|
Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_alpaca)): |
|
|
|
| | Win Rate (Ori) | LC Win Rate (Ori) | Win Rate (+ ExPO) | LC Win Rate (+ ExPO) | |
|
| ------------------------------------ | -------------- | ----------------- | ----------------- | -------------------- | |
|
| `HuggingFaceH4/zephyr-7b-alpha` | 6.7% | 10.0% | **10.6%** | **13.6%** | |
|
| `HuggingFaceH4/zephyr-7b-beta` | 10.2% | 13.2% | **11.1%** | **14.0%** | |
|
| `berkeley-nest/Starling-LM-7B-alpha` | 15.0% | 18.3% | **18.2%** | **19.5%** | |
|
| `Nexusflow/Starling-LM-7B-beta` | 26.6% | 25.8% | **29.6%** | **26.4%** | |
|
| `snorkelai/Snorkel-Mistral-PairRM` | 24.7% | 24.0% | **28.8%** | **26.4%** | |
|
| `RLHFlow/LLaMA3-iterative-DPO-final` | 29.2% | 36.0% | **32.7%** | **37.8%** | |
|
| `internlm/internlm2-chat-1.8b` | 3.8% | 4.0% | **5.2%** | **4.3%** | |
|
| `internlm/internlm2-chat-7b` | 20.5% | 18.3% | **28.1%** | **22.7%** | |
|
| `internlm/internlm2-chat-20b` | 36.1% | 24.9% | **46.2%** | **27.2%** | |
|
| `allenai/tulu-2-dpo-7b` | 8.5% | 10.2% | **11.5%** | **11.7%** | |
|
| `allenai/tulu-2-dpo-13b` | 11.2% | 15.5% | **15.6%** | **17.6%** | |
|
| `allenai/tulu-2-dpo-70b` | 15.4% | 21.2% | **23.0%** | **25.7%** | |
|
|
|
Evaluation results on the **MT-Bench** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_mtbench)): |
|
|
|
| | Original | + ExPO | |
|
| ------------------------------------ | -------- | -------- | |
|
| `HuggingFaceH4/zephyr-7b-alpha` | 6.85 | **6.87** | |
|
| `HuggingFaceH4/zephyr-7b-beta` | 7.02 | **7.06** | |
|
| `berkeley-nest/Starling-LM-7B-alpha` | 7.82 | **7.91** | |
|
| `Nexusflow/Starling-LM-7B-beta` | 8.10 | **8.18** | |
|
| `snorkelai/Snorkel-Mistral-PairRM` | 7.63 | **7.69** | |
|
| `RLHFlow/LLaMA3-iterative-DPO-final` | 8.08 | **8.45** | |
|
| `internlm/internlm2-chat-1.8b` | 5.17 | **5.26** | |
|
| `internlm/internlm2-chat-7b` | 7.72 | **7.80** | |
|
| `internlm/internlm2-chat-20b` | 8.13 | **8.26** | |
|
| `allenai/tulu-2-dpo-7b` | 6.35 | **6.38** | |
|
| `allenai/tulu-2-dpo-13b` | 7.00 | **7.26** | |
|
| `allenai/tulu-2-dpo-70b` | 7.79 | **8.03** | |
|
|
|
|
