Hugging Face's logo

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

Text Generation
Safetensors
English
Russian
gptq
conversational
Model card Files Community
qilowoq commited on
Commit
c567ae2
·
verified ·
1 Parent(s): 46cee4b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -3
README.md CHANGED
@@ -22,9 +22,6 @@ language:
22
  - 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.
23
 
24
  | Model | bits | Perplexity (russian wiki) |
25
- | --- | --- | --- |
26
  [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) | 16bit | 6.2152 |
27
- | --- | --- | --- |
28
  [Granther/Gemma-2-9B-Instruct-4Bit-GPTQ](https://huggingface.co/Granther/Gemma-2-9B-Instruct-4Bit-GPTQ) | 4bit | 6.4966 |
29
- | --- | --- | --- |
30
  this model | 4bit | 6.3593 |
 
22
  - 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.
23
 
24
  | Model | bits | Perplexity (russian wiki) |
 
25
  [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) | 16bit | 6.2152 |
 
26
  [Granther/Gemma-2-9B-Instruct-4Bit-GPTQ](https://huggingface.co/Granther/Gemma-2-9B-Instruct-4Bit-GPTQ) | 4bit | 6.4966 |
 
27
  this model | 4bit | 6.3593 |