Orion-zhen
commited on
Commit
•
cb8cbe0
1
Parent(s):
4256392
Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,12 @@ tags:
|
|
11 |
|
12 |
# Qwen2-72B-Instruct
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
## Introduction
|
15 |
|
16 |
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 72B Qwen2 model.
|
|
|
11 |
|
12 |
# Qwen2-72B-Instruct
|
13 |
|
14 |
+
## Quantization
|
15 |
+
|
16 |
+
This model is an exl2 quantisized model using [mixed-exl-calibration](https://huggingface.co/datasets/Orion-zhen/mixed-exl-calibration) as calibration dataset.
|
17 |
+
|
18 |
+
Compared to normal wikitext calibration, this could provide slightly better performance on both English and Chinese, etc.
|
19 |
+
|
20 |
## Introduction
|
21 |
|
22 |
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 72B Qwen2 model.
|