|
--- |
|
library_name: transformers |
|
tags: |
|
- llama |
|
- facebook |
|
- meta |
|
- llama-3 |
|
- conversational |
|
- text-generation-inference |
|
--- |
|
Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [meta-llama/Meta-Llama-3.1-8B-Instruct |
|
](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) 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 | |
|
|------|------|-------|------|------|------|------|------|------| |
|
|meta-llama/Meta-Llama-3.1-8B-Instruct| None | 0.6817 | 0.5162 | 0.8186 | 0.5909 | 0.8014 | 0.7364 | 16.1 | |
|
| | 1x16g8 | 0.5917 | 0.4377 | 0.7681 | 0.5233 | 0.7748 | 0.6867 | 4.1 | |
|
|
|
**Note** |
|
|
|
We used `lm-eval=0.4.0` for evaluation. |
