ISTA-DASLab
/

c4ai-command-r-v01-AQLM-2Bit-1x16

Text Generation

text-generation-inference

Inference Endpoints

Inference Endpoints

Model card Files Files and versions Community

SpiridonSunRotator commited on Apr 13

Commit

1139e72

•

1 Parent(s): 282cbe3

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [CohereForAI/c
 For this quantization, we used 1 codebook of 16 bits.
 Results:
-| Model      | Quantization | MMLU | GSM8k | Model size, Gb |
 |------|------|-------|------|------|
 |CohereForAI/c4ai-command-r-v01| None |0.6755 | 0.6065 | 70.0 |
 |  | 1x16 | 0.5719 | 0.3760 | 12.7 |

 For this quantization, we used 1 codebook of 16 bits.
 Results:
+| Model      | Quantization | MMLU (5-shot) | GSM8k (8-shot) | Model size, Gb |
 |------|------|-------|------|------|
 |CohereForAI/c4ai-command-r-v01| None |0.6755 | 0.6065 | 70.0 |
 |  | 1x16 | 0.5719 | 0.3760 | 12.7 |