Lewdiculous commited on
Commit
6122b6e
1 Parent(s): b230208

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -9,6 +9,11 @@ language:
9
 
10
  GGUF-IQ-Imatrix quants for [jeiku/Average_Normie_l3_v1_8B](https://huggingface.co/jeiku/Average_Normie_l3_v1_8B).
11
 
 
 
 
 
 
12
  > [!WARNING]
13
  > Compatible SillyTavern presets [here (simple)](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here (Virt's)](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
14
  > Use the latest version of KoboldCpp. **Use the provided presets.** <br>
 
9
 
10
  GGUF-IQ-Imatrix quants for [jeiku/Average_Normie_l3_v1_8B](https://huggingface.co/jeiku/Average_Normie_l3_v1_8B).
11
 
12
+ > [!IMPORTANT]
13
+ > **Updated!**
14
+ > These quants have been redone with the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920) in mind. <br>
15
+ > Use **KoboldCpp version 1.64** or higher.
16
+
17
  > [!WARNING]
18
  > Compatible SillyTavern presets [here (simple)](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here (Virt's)](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
19
  > Use the latest version of KoboldCpp. **Use the provided presets.** <br>