Hugging Face's logo

Lewdiculous
/
Test1_SLIDE-GGUF-IQ-Imatrix

GGUF
Inference Endpoints
Model card Files Community
1
Lewdiculous commited on
Commit
d75edd3
·
verified ·
1 Parent(s): 96e1c21

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -3,6 +3,11 @@ license: apache-2.0
3
  ---
4
  GGUF-IQ-Imatrix quants for NLPark/Test1_SLIDE as requested in [#27](https://huggingface.co/Lewdiculous/Model-Requests/discussions/27).
5
 
 
 
 
 
 
6
  > [!WARNING]
7
  > Recommended presets [here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
8
  > Use the latest version of KoboldCpp. **Use the provided presets.** <br>
 
3
  ---
4
  GGUF-IQ-Imatrix quants for NLPark/Test1_SLIDE as requested in [#27](https://huggingface.co/Lewdiculous/Model-Requests/discussions/27).
5
 
6
+ > [!IMPORTANT]
7
+ > **Updated!**
8
+ > These quants have been redone with the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920) in mind. <br>
9
+ > Use **KoboldCpp version 1.64** or higher.
10
+
11
  > [!WARNING]
12
  > Recommended presets [here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
13
  > Use the latest version of KoboldCpp. **Use the provided presets.** <br>