MikeRoz commited on
Commit
d73c6bc
·
verified ·
1 Parent(s): 1db3215

Update README.md

Browse files

remove now-deleted defective quants, disclaimer about dev version of exl3

Files changed (1) hide show
  1. README.md +2 -12
README.md CHANGED
@@ -11,7 +11,7 @@ tags:
11
  - exl3
12
  ---
13
 
14
- exllamav3 quantizations of [zai-org/GLM-4.5](https://huggingface.co/zai-org/GLM-4.5). Please note that support for this model is currently in the dev branch of exllamav3.
15
 
16
  [2.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/2.00bpw_H6_Revised) 84.517 GiB
17
  [3.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/3.00bpw_H6_Revised) 125.398 GiB
@@ -20,14 +20,4 @@ exllamav3 quantizations of [zai-org/GLM-4.5](https://huggingface.co/zai-org/GLM-
20
  [6.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/6.00bpw_H6_Revised) 248.043 GiB
21
  [8.00 bpw h8](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/8.00bpw_H8_Revised) 329.987 GiB
22
 
23
- ### The quants below were made with an older version of the dev branch of exllamav3. It is not yet clear whether the initial bug that made inference incoherent also had an effect on the resulting weights during quantization. Revised weights will be uploaded over the coming days unless evidence suggests they're not needed. Use the weights below with caution. I apologize to anyone who ends up having to re-download.
24
-
25
- I'll take a crack at some optimized quants once the fixed-size quants are all done.
26
-
27
- [2.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/2.00bpw_H6) 84.517 GiB
28
- [2.90 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/2.90bpw_H6) ("Unoptimized") 121.270 GiB
29
- [3.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/3.00bpw_H6) 125.398 GiB
30
- [4.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/4.00bpw_H6) 166.280 GiB
31
- [5.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/5.00bpw_H6) 207.165 GiB
32
- [6.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/6.00bpw_H6) (Cancelled)
33
- [8.00 bpw h8](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/8.00bpw_H8) (Cancelled)
 
11
  - exl3
12
  ---
13
 
14
+ exllamav3 quantizations of [zai-org/GLM-4.5](https://huggingface.co/zai-org/GLM-4.5).
15
 
16
  [2.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/2.00bpw_H6_Revised) 84.517 GiB
17
  [3.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/3.00bpw_H6_Revised) 125.398 GiB
 
20
  [6.00 bpw h6](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/6.00bpw_H6_Revised) 248.043 GiB
21
  [8.00 bpw h8](https://huggingface.co/MikeRoz/GLM-4.5-exl3/tree/8.00bpw_H8_Revised) 329.987 GiB
22
 
23
+