ArtusDev commited on
Commit
b399072
·
verified ·
1 Parent(s): 981dc8d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +38 -0
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Tesslate/UIGEN-X-32B-0727
3
+ base_model_relation: quantized
4
+ quantized_by: ArtusDev
5
+ ---
6
+
7
+ ## EXL3 Quants of Tesslate/UIGEN-X-32B-0727
8
+
9
+ EXL3 quants of [Tesslate/UIGEN-X-32B-0727](https://huggingface.co/Tesslate/UIGEN-X-32B-0727) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.
10
+
11
+ ### Quants
12
+ | Quant(Revision) | Bits per Weight | Head Bits |
13
+ | -------- | ---------- | --------- |
14
+ | [3.0_H6](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/3.0bpw_H6) | 3.0 | 6 |
15
+ | [3.5_H6](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/3.5bpw_H6) | 3.5 | 6 |
16
+ | [4.0_H6](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/4.0bpw_H6) | 4.0 | 6 |
17
+ | [4.5_H6](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/4.5bpw_H6) | 4.5 | 6 |
18
+ | [5.0_H6](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/5.0bpw_H6) | 5.0 | 6 |
19
+ | [6.0_H6](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/6.0bpw_H6) | 6.0 | 6 |
20
+ | [8.0_H8](https://huggingface.co/ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3/tree/8.0bpw_H8) | 8.0 | 8 |
21
+
22
+ ### Downloading quants with huggingface-cli
23
+
24
+ <details>
25
+ <summary>Click to view download instructions</summary>
26
+
27
+ Install hugginface-cli:
28
+
29
+ ```bash
30
+ pip install -U "huggingface_hub[cli]"
31
+ ```
32
+
33
+ Download quant by targeting the specific quant revision (branch):
34
+
35
+ ```
36
+ huggingface-cli download ArtusDev/Tesslate_UIGEN-X-32B-0727-EXL3 --revision "5.0bpw_H6" --local-dir ./
37
+ ```
38
+ </details>