metadata
library_name: transformers
tags:
- cohere
- conversational
- 10languages
- text-generation-inference
- Inference Endpoints
Official AQLM quantization of CohereForAI/c4ai-command-r-v01 .
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 |