qilowoq
/

gemma-2-9B-it-4Bit-GPTQ

Text Generation

Model card Files Files and versions Community

qilowoq commited on Sep 20, 2024

Commit

2fca325

·

verified ·

1 Parent(s): c567ae2

Update README.md

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -21,7 +21,8 @@ language:
 - This model was quantized with the Auto-GPTQ library and dataset containing english and russian wikipedia articles. It has lower perplexity on russian data then other GPTQ models.
-| Model | bits | Perplexity (russian wiki) |
-[gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) | 16bit | 6.2152 |
-[Granther/Gemma-2-9B-Instruct-4Bit-GPTQ](https://huggingface.co/Granther/Gemma-2-9B-Instruct-4Bit-GPTQ) | 4bit | 6.4966 |
-this model | 4bit | 6.3593 |

 - This model was quantized with the Auto-GPTQ library and dataset containing english and russian wikipedia articles. It has lower perplexity on russian data then other GPTQ models.
+| Model                                                                                                 |          bits | Perplexity (russian wiki) |
+| ----------------------------------------------------------------------------------------------------- | ------------- | ------------------------- |
+[gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it)                                            | 16bit         | 6.2152                    |
+[Granther/Gemma-2-9B-Instruct-4Bit-GPTQ](https://huggingface.co/Granther/Gemma-2-9B-Instruct-4Bit-GPTQ) | 4bit          | 6.4966                    |
+this model                                                                                              | 4bit          | 6.3593                    |