Hugging Face's logo

Lewdiculous
/
L3-TheSpice-8b-v0.1.3-GGUF-IQ-Imatrix

GGUF
Inference Endpoints
imatrix
Model card Files Community
3
Lewdiculous commited on
Commit
39ca461
•
1 Parent(s): d501eb5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -11,7 +11,10 @@ GGUF-IQ-Imatrix quants for **cgato/L3-TheSpice-8b-v0.1.3**.
11
  > Use **KoboldCpp version 1.64** or higher.
12
 
13
  > [!NOTE]
14
- > Prompt format is relatively simple, author seems to recommend ChatML.
 
 
 
15
 
16
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png)
17
 
 
11
  > Use **KoboldCpp version 1.64** or higher.
12
 
13
  > [!NOTE]
14
+ > **Prompt formatting...** <br>
15
+ > Prompt format is relatively simple, author seems to recommend the **Default** context preset and **Instruct Mode - Disabled**. <br>
16
+ > I recommend reading original [**model card page information**](https://huggingface.co/cgato/L3-TheSpice-8b-v0.1.3#prompt-format-chat--the-default-ooba-template-and-silly-tavern-template-).
17
+
18
 
19
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png)
20