Hugging Face's logo

nihaomur
/
gemma-2-9b-it-AWQ

Text Generation
Transformers
Safetensors
gemma2
conversational
text-generation-inference
Inference Endpoints
4-bit precision
awq
Model card Files Community
1
nihaomur commited on
Commit
d668c9f
·
verified ·
1 Parent(s): 1ed6b8e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -1,6 +1,9 @@
1
  This is not the original model I made, it's google's [Gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) and Quantized by [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
 
2
  I quantized it with 4-bit, your GPU VRAM should be at least 8G in order to garauntee it work perfectly.
3
- By renning some testing on this AWQ model, this model is significantly brilliant.
 
 
4
  Below is the original model card, hope you guys having fun with it.
5
 
6
 
 
1
  This is not the original model I made, it's google's [Gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) and Quantized by [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
2
+
3
  I quantized it with 4-bit, your GPU VRAM should be at least 8G in order to garauntee it work perfectly.
4
+
5
+ By running some test on this AWQ model, this model is significantly brilliant.
6
+
7
  Below is the original model card, hope you guys having fun with it.
8
 
9