Quantization made by Richard Erkhov.
Gemma-2-9B-It-SPPO-Iter1 - GGUF
- Model creator: https://huggingface.co/UCLA-AGI/
- Original model: https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1/
Original model description:
license: gemma datasets:
- openbmb/UltraFeedback language:
- en pipeline_tag: text-generation
Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675)
Gemma-2-9B-It-SPPO-Iter1
This model was developed using Self-Play Preference Optimization at iteration 1, based on the google/gemma-2-9b-it architecture as starting point. We utilized the prompt sets from the openbmb/UltraFeedback dataset, splited to 3 parts for 3 iterations by snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset. All responses used are synthetic.
Terms of Use: Terms
Links to Other Models
Model Description
- Model type: A 8B parameter GPT-like model fine-tuned on synthetic datasets.
- Language(s) (NLP): Primarily English
- License: Apache-2.0
- Finetuned from model: google/gemma-2-9b-it
AlpacaEval Leaderboard Evaluation Results
| Model | LC. Win Rate | Win Rate | Avg. Length |
|---|---|---|---|
| Llama-3-8B-SPPO Iter1 | 48.70 | 40.76 | 1669 |
| Llama-3-8B-SPPO Iter2 | 50.93 | 44.64 | 1759 |
| Llama-3-8B-SPPO Iter3 | 53.27 | 47.74 | 1803 |
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- eta: 1000
- per_device_train_batch_size: 8
- gradient_accumulation_steps: 1
- seed: 42
- distributed_type: deepspeed_zero3
- num_devices: 8
- optimizer: RMSProp
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_train_epochs: 1.0
Citation
@misc{wu2024self,
title={Self-Play Preference Optimization for Language Model Alignment},
author={Wu, Yue and Sun, Zhiqing and Yuan, Huizhuo and Ji, Kaixuan and Yang, Yiming and Gu, Quanquan},
year={2024},
eprint={2405.00675},
archivePrefix={arXiv},
primaryClass={cs.LG}
}