EricB HF staff commited on
Commit
7d50de3
โ€ข
1 Parent(s): 633fa3d

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -0
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - uqff
4
+ - mistral.rs
5
+ base_model: google/gemma-2-27b-it
6
+ base_model_relation: quantized
7
+ ---
8
+
9
+ <!-- Autogenerated from user input. -->
10
+
11
+ # `google/gemma-2-27b-it`, UQFF quantization
12
+
13
+
14
+ Run with [mistral.rs](https://github.com/EricLBuehler/mistral.rs). Documentation: [UQFF docs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/UQFF.md).
15
+
16
+ 1) **Flexible** ๐ŸŒ€: Multiple quantization formats in *one* file format with *one* framework to run them all.
17
+ 2) **Reliable** ๐Ÿ”’: Compatibility ensured with *embedded* and *checked* semantic versioning information from day 1.
18
+ 3) **Easy** ๐Ÿค—: Download UQFF models *easily* and *quickly* from Hugging Face, or use a local file.
19
+ 3) **Customizable** ๐Ÿ› ๏ธ: Make and publish your own UQFF files in minutes.
20
+ ## Files
21
+
22
+ |Quantization type(s)|Example|
23
+ |--|--|
24
+ |FP8|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-f8e4m3.uqff`|
25
+ |HQQ4|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-hqq4.uqff`|
26
+ |HQQ8|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-hqq8.uqff`|
27
+ |Q3K|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-q3k.uqff`|
28
+ |Q4K|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-q4k.uqff`|
29
+ |Q5K|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-q5k.uqff`|
30
+ |Q8_0|`./mistralrs-server -i plain -m EricB/gemma-2-27b-it-UQFF --from-uqff gemma2-27b-instruct-q8_0.uqff`|