|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct |
|
language: |
|
- en |
|
- de |
|
- fr |
|
- it |
|
- pt |
|
- hi |
|
- es |
|
- th |
|
library_name: transformers |
|
license: llama3.1 |
|
pipeline_tag: text-generation |
|
tags: |
|
- facebook |
|
- meta |
|
- pytorch |
|
- llama |
|
- llama-3 |
|
--- |
|
|
|
|
|
|Weight Quantization| PPL | |
|
|-------------------|--------------------| |
|
| FP16 | 4.1892 +/- 0.01430 | |
|
| IQ_1S | 8.5005 +/- 0.03298 | |
|
|
|
Dataset used for re-calibration: Mix of [standard_cal_data](https://github.com/turboderp/exllamav2/tree/master/exllamav2/conversion/standard_cal_data) |
|
|
|
The generated `imatrix` can be downloaded from [imatrix.dat]() |
