119 lines
7.0 KiB
Markdown
119 lines
7.0 KiB
Markdown
Quantization made by Richard Erkhov.
|
|
|
|
[Github](https://github.com/RichardErkhov)
|
|
|
|
[Discord](https://discord.gg/pvy7H8DZMG)
|
|
|
|
[Request more models](https://github.com/RichardErkhov/quant_request)
|
|
|
|
|
|
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/
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q2_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q2_K.gguf) | Q2_K | 3.54GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.IQ3_XS.gguf) | IQ3_XS | 3.86GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.IQ3_S.gguf) | IQ3_S | 4.04GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q3_K_S.gguf) | Q3_K_S | 4.04GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.IQ3_M.gguf) | IQ3_M | 4.19GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q3_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q3_K.gguf) | Q3_K | 4.43GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q3_K_M.gguf) | Q3_K_M | 4.43GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q3_K_L.gguf) | Q3_K_L | 4.78GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.IQ4_XS.gguf) | IQ4_XS | 4.86GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q4_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q4_0.gguf) | Q4_0 | 5.07GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.IQ4_NL.gguf) | IQ4_NL | 5.1GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q4_K_S.gguf) | Q4_K_S | 5.1GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q4_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q4_K.gguf) | Q4_K | 5.37GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q4_K_M.gguf) | Q4_K_M | 5.37GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q4_1.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q4_1.gguf) | Q4_1 | 5.55GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q5_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q5_0.gguf) | Q5_0 | 6.04GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q5_K_S.gguf) | Q5_K_S | 6.04GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q5_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q5_K.gguf) | Q5_K | 6.19GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q5_K_M.gguf) | Q5_K_M | 6.19GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q5_1.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q5_1.gguf) | Q5_1 | 6.52GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q6_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q6_K.gguf) | Q6_K | 7.07GB |
|
|
| [Gemma-2-9B-It-SPPO-Iter1.Q8_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Gemma-2-9B-It-SPPO-Iter1-gguf/blob/main/Gemma-2-9B-It-SPPO-Iter1.Q8_0.gguf) | Q8_0 | 9.15GB |
|
|
|
|
|
|
|
|
|
|
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](https://arxiv.org/abs/2405.00675) at iteration 1, based on the [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) architecture as starting point. We utilized the prompt sets from the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, splited to 3 parts for 3 iterations by [snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset](https://huggingface.co/datasets/snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset). All responses used are synthetic.
|
|
|
|
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-9b-it)
|
|
|
|
## Links to Other Models
|
|
- [Gemma-2-9B-It-SPPO-Iter1](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1)
|
|
- [Gemma-2-9B-It-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2)
|
|
- [Gemma-2-9B-It-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3)
|
|
|
|
### 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](https://tatsu-lab.github.io/alpaca_eval/)
|
|
|
|
|
|
| Model | LC. Win Rate | Win Rate | Avg. Length |
|
|
|-------------------------------------------|:------------:|:--------:|:-----------:|
|
|
|[Llama-3-8B-SPPO Iter1](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1) |48.70 |40.76 | 1669
|
|
|[Llama-3-8B-SPPO Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2) |50.93 | 44.64 | 1759
|
|
|[Llama-3-8B-SPPO Iter3](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-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}
|
|
}
|
|
```
|
|
|
|
|
|
|