wassname/SimPO
1
0
Fork 0
mirror of https://github.com/wassname/SimPO.git synced 2026-09-10 11:50:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Yu Meng
2024-07-17 11:34:06 -04:00
committed by GitHub
parent aa5c3062fc
commit e6c3d771a2
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -3
View File
@@ -69,13 +69,13 @@ The [CPO_SIMPO](https://github.com/fe1ixxu/CPO_SIMPO/tree/main) repository did p
## Released Models ## Released Models
### Gemma ### Gemma
We release the following two models that are built on top of the strong [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) model by training DPO and SimPO on the on-policy dataset [princeton-nlp/gemma2-ultrafeedback-armorm](https://huggingface.co/datasets/princeton-nlp/gemma2-ultrafeedback-armorm). For GSM and MMLU, we use the [EvalZero](https://github.com/yuchenlin/ZeroEval) reporistory which aims to evaluate instruction-tuned LLMs (i.e., chat models instead of base models) for their zero-shot performance on reasoning and knowledge heavy tasks. More results on [WildBench](https://huggingface.co/spaces/allenai/WildBench) are coming soon. We release the following two models that are built on top of the strong [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) model by training DPO and SimPO on the on-policy dataset [princeton-nlp/gemma2-ultrafeedback-armorm](https://huggingface.co/datasets/princeton-nlp/gemma2-ultrafeedback-armorm). For GSM and MMLU, we use the [EvalZero](https://github.com/yuchenlin/ZeroEval) repository which aims to evaluate instruction-tuned LLMs (i.e., chat models instead of base models) for their zero-shot performance on reasoning and knowledge heavy tasks. More results on [WildBench](https://huggingface.co/spaces/allenai/WildBench) are coming soon.
| models | AE2 LC | AE2 WR | AE2 Length | AH | AH Length | GSM | GSM Length | MMLU | MMLU Length | | models | AE2 LC | AE2 WR | AE2 Length | AH | AH Length | GSM | GSM Length | MMLU | MMLU Length |
|-----------------------------------|:------:|:------:|:----------:|:----:|:---------:|:----:|:----------:|:----:|:-----------:| |-----------------------------------|:------:|:------:|:----------:|:----:|:---------:|:----:|:----------:|:----:|:-----------:|
| [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) | 51.1 | 38.1 | 1571 | 40.8 | 545 | 87.4 | 395 | 72.7 | 515 | | [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) | 51.1 | 38.1 | 1571 | 40.8 | 545 | 87.4 | 395 | 72.7 | 515 |
| [princeton-nlp/gemma-2-9b-it-DPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-DPO) | 69.6 | 67.2 | 2016 | 58.9 | 717 | 88.5 | 392 | 72.2 | 624 | | [princeton-nlp/gemma-2-9b-it-DPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-DPO) | 67.8 | 65.4 | 2016 | 58.9 | 717 | 88.5 | 392 | 72.2 | 624 |
| [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO) | 73.2 | 66.7 | 1833 | 59.1 | 693 | 88.0 | 341 | 72.2 | 441 | | [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO) | 72.4 | 65.9 | 1833 | 59.1 | 693 | 88.0 | 341 | 72.2 | 441 |
Compared to the llama3 models, we found that the gemma models exhibit significantly less catastrophic forgetting on math tasks (e.g., GSM) and MMLU, despite the ultrafeedback dataset having limited math-related data. This demonstrates that the [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) model is more suitable for continued preference optimization. Compared to the llama3 models, we found that the gemma models exhibit significantly less catastrophic forgetting on math tasks (e.g., GSM) and MMLU, despite the ultrafeedback dataset having limited math-related data. This demonstrates that the [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) model is more suitable for continued preference optimization.