Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,36 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-sa-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-sa-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- mc4
|
| 5 |
+
- cc100
|
| 6 |
+
- oscar
|
| 7 |
+
- togethercomputer/RedPajama-Data-1T
|
| 8 |
+
language:
|
| 9 |
+
- ja
|
| 10 |
+
- en
|
| 11 |
+
library_name: transformers
|
| 12 |
+
base_model: meta-llama/Llama-2-70b-hf
|
| 13 |
+
pipeline_tag: text-generation
|
| 14 |
+
tags:
|
| 15 |
+
- llama
|
| 16 |
+
- llama-2
|
| 17 |
---
|
| 18 |
+
|
| 19 |
+
This repository contains the exl2 quants of [karakuri-ai/karakuri-lm-70b-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-v0.1).
|
| 20 |
+
|
| 21 |
+
Compatible with [exllamav2](https://github.com/turboderp/exllamav2) version 0.0.11 and later. For optimal model loading, it is recommended to use [tabbyAPI](https://github.com/theroyallab/tabbyAPI).
|
| 22 |
+
|
| 23 |
+
The measurement file is attached in the branch `main` and all quants are stored in their respective branches.
|
| 24 |
+
|
| 25 |
+
The chart below presents the calibration perplexity and [wikitext-103-v1](https://huggingface.co/datasets/wikitext) test perplexity for all provided quants.
|
| 26 |
+
|
| 27 |
+
| Quant | Calibration Perplexity | wikitext-103-v1 Test Perplexity |
|
| 28 |
+
|-----------------------------------------------------------------------------------------|------------------------|---------------------------------|
|
| 29 |
+
| [2.4bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/2.4bpw-h6) | | |
|
| 30 |
+
| [2.65bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/2.65bpw-h6) | 8.1743 | |
|
| 31 |
+
| [3.0bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/3.0bpw-h6) | 7.9927 | |
|
| 32 |
+
| [4.0bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/4.0bpw-h6) | 7.6440 | |
|
| 33 |
+
| [4.65bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/4.65bpw-h6) | 7.5872 | |
|
| 34 |
+
| [5.0bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/5.0bpw-h6) | 7.5745 | |
|
| 35 |
+
| [6.0bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/6.0bpw-h6) | | |
|
| 36 |
+
| [8.0bpw-h8](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/8.0bpw-h8) | | |
|