metadata
library_name: transformers
tags:
- llama
- facebook
- meta
- llama-3
- conversational
- text-generation-inference
Official AQLM quantization of meta-llama/Meta-Llama-3.1-8B finetuned with PV-Tuning.
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 | None | 0.6521 | 0.5145 | 0.8144 | 0.5998 | 0.8014 | 0.7356 | 16.1 |
| 1x16g8 | 0.5524 | 0.4437 | 0.7765 | 0.5603 | 0.7797 | 0.6851 | 4.1 |
Note
We used lm-eval=0.4.0 for evaluation.