Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- de
|
| 6 |
+
- fr
|
| 7 |
+
- it
|
| 8 |
+
- pt
|
| 9 |
+
- hi
|
| 10 |
+
- es
|
| 11 |
+
- th
|
| 12 |
+
library_name: transformers
|
| 13 |
+
license: llama3.1
|
| 14 |
+
pipeline_tag: text-generation
|
| 15 |
+
tags:
|
| 16 |
+
- facebook
|
| 17 |
+
- meta
|
| 18 |
+
- pytorch
|
| 19 |
+
- llama
|
| 20 |
+
- llama-3
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|Weight Quantization| PPL |
|
| 25 |
+
|-------------------|--------------------|
|
| 26 |
+
| FP16 | 4.1892 +/- 0.01430 |
|
| 27 |
+
| IQ_1S | 8.5005 +/- 0.03298 |
|
| 28 |
+
|
| 29 |
+
Dataset used for re-calibration: Mix of [standard_cal_data](https://github.com/turboderp/exllamav2/tree/master/exllamav2/conversion/standard_cal_data)
|
| 30 |
+
|
| 31 |
+
The generated `imatrix` can be downloaded from [imatrix.dat]()
|