ludis commited on
Commit
bf00b4a
1 Parent(s): 8c9de5f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -6
README.md CHANGED
@@ -4,6 +4,10 @@ datasets:
4
  - lemonilia/LimaRP
5
  ---
6
 
 
 
 
 
7
  ## Training
8
 
9
  [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
@@ -18,9 +22,3 @@ base model mistralai/Mixtral-8x7B-v0.1 tuned on koishi commit 6e675d1 for one ep
18
  then tuned on pippa 6412b0c for one epoch (metharme completion)
19
 
20
  then tuned on limarp Version 2023-10-19 for 2 epochs in metharme completion format
21
-
22
- ## Prompting
23
-
24
- The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
25
-
26
- The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
 
4
  - lemonilia/LimaRP
5
  ---
6
 
7
+ ## Gen Settings & Prompting
8
+
9
+ https://rentry.org/tsukasamodel
10
+
11
  ## Training
12
 
13
  [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
 
22
  then tuned on pippa 6412b0c for one epoch (metharme completion)
23
 
24
  then tuned on limarp Version 2023-10-19 for 2 epochs in metharme completion format