Update README.md
Browse files
README.md
CHANGED
@@ -3,13 +3,11 @@ license: apache-2.0
|
|
3 |
---
|
4 |
EXL2 quants of [Qwen2-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)
|
5 |
|
6 |
-
[2.30 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/2.3bpw)
|
7 |
-
[2.50 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/2.5bpw)
|
8 |
-
[3.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/3.0bpw)
|
9 |
-
[3.50 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/3.5bpw)
|
10 |
[4.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/4.0bpw)
|
11 |
[4.50 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/4.5bpw)
|
12 |
[5.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/5.0bpw)
|
13 |
[6.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/6.0bpw)
|
14 |
|
|
|
|
|
15 |
[measurement.json](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/blob/main/measurement.json)
|
|
|
3 |
---
|
4 |
EXL2 quants of [Qwen2-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)
|
5 |
|
|
|
|
|
|
|
|
|
6 |
[4.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/4.0bpw)
|
7 |
[4.50 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/4.5bpw)
|
8 |
[5.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/5.0bpw)
|
9 |
[6.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/6.0bpw)
|
10 |
|
11 |
+
(2.3bpw to 3.5bpw revisions are in also this repo, but they are unstable. Working on it.)
|
12 |
+
|
13 |
[measurement.json](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/blob/main/measurement.json)
|