ddh0 commited on
Commit
55bbcd6
1 Parent(s): ad78884

detail prompt format

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -18,6 +18,15 @@ This is a linear merge with the following composition:
18
  - [NeverSleep/MiquMaid-v3-70B](https://huggingface.co/NeverSleep/MiquMaid-v3-70B) at weight 0.3
19
  - [maywell/miqu-evil-dpo](https://huggingface.co/maywell/miqu-evil-dpo) at weight 0.2
20
 
 
 
 
 
 
 
 
 
 
21
  ## Merge Configuration
22
 
23
  The following YAML configuration was used to produce this model:
 
18
  - [NeverSleep/MiquMaid-v3-70B](https://huggingface.co/NeverSleep/MiquMaid-v3-70B) at weight 0.3
19
  - [maywell/miqu-evil-dpo](https://huggingface.co/maywell/miqu-evil-dpo) at weight 0.2
20
 
21
+ ## Prompt format
22
+ The model responds well to general-purpose prompt formats such as Alpaca. Alternatively, I suggest trying the following format:
23
+
24
+ ```
25
+ <message from='system'>{your system prompt here}</message><message from='user'>{user prompt here}</message><message from='bot'>{bot response here}</message><message from='user'>{user prompt here}</message><message from='bot'>{bot response here}</message> [... and so on ...]
26
+ ```
27
+
28
+ This format is readily understood by the model, and leads to the expected high-quality responses. Note the lack of newlines `\n` - they are not necessary and might actually make it harder for the model to follow along.
29
+
30
  ## Merge Configuration
31
 
32
  The following YAML configuration was used to produce this model: