|
--- |
|
language: |
|
- en |
|
- fr |
|
- de |
|
- es |
|
- it |
|
- pt |
|
- ru |
|
- zh |
|
- ja |
|
license: apache-2.0 |
|
--- |
|
Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [mistralai/Mistral-Nemo-Instruct-2407 |
|
](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) finetuned with [PV-Tuning](https://arxiv.org/abs/2405.14852). |
|
|
|
For this quantization, we used 1 codebook of 16 bits and groupsize of 8. |
|
|
|
Results: |
|
| Model | Quantization | MMLU (5-shot) | ArcC| ArcE| Hellaswag | PiQA | Winogrande | Model size, Gb | |
|
|------|------|-------|------|------|------|------|------|------| |
|
|mistralai/Mistral-Nemo-Instruct-2407| None | 0.6819 | 0.5606 | 0.8241 | 0.6332 | 0.8090 | 0.7498 | 24.5 | |
|
| | 1x16g8 | 0.6071 | 0.5017 | 0.7942 | 0.5930 | 0.7987 | 0.7356 | 5.8 | |
|
|
|
**Note** |
|
|
|
We used `lm-eval=0.4.0` for evaluation. |
