TheBloke commited on
Commit
97c314f
1 Parent(s): 58e0071

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -29,9 +29,20 @@ Please note that these GGMLs are **not compatible with llama.cpp, or currently w
29
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/cassandra-6.9B-GGML)
30
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/wbrown/cassandra-6.9b)
31
 
32
- ## Prompt template
33
 
34
- I don't know! Let me know if you figure it out.
 
 
 
 
 
 
 
 
 
 
 
35
 
36
  <!-- compatibility_ggml start -->
37
  ## Compatibilty
 
29
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/cassandra-6.9B-GGML)
30
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/wbrown/cassandra-6.9b)
31
 
32
+ ## Prompt template: NovelAI-style
33
 
34
+ Examples:
35
+
36
+ ```
37
+ [ Author: Haven Ross; Title: The Biker's Buddy; Tags: friendship, slice of life, funny; Genre: thriller ]
38
+ ```
39
+
40
+ ```
41
+ [Style: text adventure]
42
+ The Deepest Dungeon, a Text Adventure
43
+ > examine room
44
+ ```
45
+ If using the latter, set `>` as a stop token in your UI.
46
 
47
  <!-- compatibility_ggml start -->
48
  ## Compatibilty