Added evaluation
Browse files
README.md
CHANGED
|
@@ -14,4 +14,8 @@ For this quantization, we used 1 codebook of 16 bits.
|
|
| 14 |
|
| 15 |
Results:
|
| 16 |
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
Results:
|
| 16 |
|
| 17 |
+
Results:
|
| 18 |
+
| Model | Quantization | MMLU (5-shot) | Model size, Gb |
|
| 19 |
+
|------|------|-------|------|
|
| 20 |
+
|CohereForAI/c4ai-command-r-v01| None |0.7425 | 208 |
|
| 21 |
+
| | 1x16 | 0.6795 | 31.9 |
|