EricB HF staff commited on
Commit
a666d8b
1 Parent(s): 2fc1f0e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -6
README.md CHANGED
@@ -19,9 +19,12 @@ Run with [mistral.rs](https://github.com/EricLBuehler/mistral.rs). Documentation
19
  3) **Customizable** 🛠️: Make and publish your own UQFF files in minutes.
20
  ## Files
21
 
22
- |Name|Quantization type(s)|Example|
23
- |--|--|--|
24
- |mistral-nemo-instruct-2407-q4k.uqff|Q4K|`./mistralrs-server -i plain -m mistralai/Mistral-Nemo-Instruct-2407 --from-uqff EricB/Mistral-Nemo-Instruct-2407-UQFF/mistral-nemo-instruct-2407-q4k.uqff`|
25
- |mistral-nemo-instruct-2407-q5k.uqff|Q5K|`./mistralrs-server -i plain -m mistralai/Mistral-Nemo-Instruct-2407 --from-uqff EricB/Mistral-Nemo-Instruct-2407-UQFF/mistral-nemo-instruct-2407-q5k.uqff`|
26
- |mistral-nemo-instruct-2407-q6k.uqff|Q6K|`./mistralrs-server -i plain -m mistralai/Mistral-Nemo-Instruct-2407 --from-uqff EricB/Mistral-Nemo-Instruct-2407-UQFF/mistral-nemo-instruct-2407-q6k.uqff`|
27
- |mistral-nemo-instruct-2407-q8_0.uqff|Q8_0|`./mistralrs-server -i plain -m mistralai/Mistral-Nemo-Instruct-2407 --from-uqff EricB/Mistral-Nemo-Instruct-2407-UQFF/mistral-nemo-instruct-2407-q8_0.uqff`|
 
 
 
 
19
  3) **Customizable** 🛠️: 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/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-f8e4m3.uqff`|
25
+ |HQQ4|`./mistralrs-server -i plain -m EricB/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-hqq4.uqff`|
26
+ |HQQ8|`./mistralrs-server -i plain -m EricB/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-hqq8.uqff`|
27
+ |Q3K|`./mistralrs-server -i plain -m EricB/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-q3k.uqff`|
28
+ |Q4K|`./mistralrs-server -i plain -m EricB/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-q4k.uqff`|
29
+ |Q5K|`./mistralrs-server -i plain -m EricB/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-q5k.uqff`|
30
+ |Q8_0|`./mistralrs-server -i plain -m EricB/Mistral-Nemo-Instruct-2407-UQFF --from-uqff mistral-nemo-2407-instruct-q8_0.uqff`|