|
--- |
|
library_name: transformers |
|
tags: |
|
- aqlm |
|
- llama |
|
- facebook |
|
- meta |
|
- llama-3 |
|
- conversational |
|
- text-generation-inference |
|
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct |
|
--- |
|
|
|
Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [meta-llama/Meta-Llama-3.1-70B-Instruct |
|
](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-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 | |
|
|-------|--------------|---------------|--------|--------|-----------|--------|------------|----------------| |
|
| | fp16 | 0.8213 | 0.6246 | 0.8683 | 0.6516 | 0.8313 | 0.7908 | 141 | |
|
| | 1x16g8 | 0.7814 | 0.5478 | 0.8270 | 0.6284 | 0.8036 | 0.7814 | 21.9 | |
|
|
