Hugging Face's logo

ISTA-DASLab
/
gemma-2b-AQLM-2Bit-1x16-hf

Text Generation
Transformers
Safetensors
gemma
text-generation-inference
Inference Endpoints
aqlm
Model card Files Community
2
SpiridonSunRotator commited on
Commit
c71a514
•
1 Parent(s): 962a874

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,6 +6,6 @@ For this quantization, we used 1 codebook of 16 bits.
6
  Results:
7
  | Model | AQLM scheme | WinoGrande | PiQA | HellaSwag | ArcE | ArcC | Model size, Gb |
8
  |------|------|------|-------|-------|-------|------|------|
9
- | gemma-2b |2x8| 0.6275 | 0.7318 | 0.4582 | 0.6923 | 0.3259| 1.7 |
10
 
11
  To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM).
 
6
  Results:
7
  | Model | AQLM scheme | WinoGrande | PiQA | HellaSwag | ArcE | ArcC | Model size, Gb |
8
  |------|------|------|-------|-------|-------|------|------|
9
+ | gemma-2b |1x16| 0.6275 | 0.7318 | 0.4582 | 0.6923 | 0.3259| 1.7 |
10
 
11
  To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM).