Commit
•
ee26de3
1
Parent(s):
a6a5190
Minor fix
Browse files
README.md
CHANGED
|
@@ -12,8 +12,6 @@ Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [CohereForAI/c
|
|
| 12 |
|
| 13 |
For this quantization, we used 1 codebook of 16 bits.
|
| 14 |
|
| 15 |
-
Results:
|
| 16 |
-
|
| 17 |
Results:
|
| 18 |
| Model | Quantization | MMLU (5-shot) | Model size, Gb |
|
| 19 |
|------|------|-------|------|
|
|
|
|
| 12 |
|
| 13 |
For this quantization, we used 1 codebook of 16 bits.
|
| 14 |
|
|
|
|
|
|
|
| 15 |
Results:
|
| 16 |
| Model | Quantization | MMLU (5-shot) | Model size, Gb |
|
| 17 |
|------|------|-------|------|
|