nakodanei commited on
Commit
c2e5cae
1 Parent(s): 04801e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -2
README.md CHANGED
@@ -3,6 +3,24 @@ license: apache-2.0
3
  ---
4
  **Nomachi-7b-v1**
5
 
6
- Roleplaying model based on Mistral-7b-v0.1. Aims to produce natural human-like text, free from slop.
7
 
8
- Uses a selection of LoRas trained on almost entirely human text, then merged together with Noromaid-7b-v0.2 back into the mistral base model with LMCocktail to maintain generalisation and intelligence.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
  **Nomachi-7b-v1**
5
 
6
+ Roleplaying focused model based on Mistral-7b-v0.1. Aims to produce natural human-like text, free from slop.
7
 
8
+ Uses a selection of LoRA trained on almost entirely human text, then merged together with Noromaid-7b-v0.2 back into the Mistral base model with LM Cocktail to maintain generalisation and intelligence.
9
+
10
+ ## Prompt template:
11
+
12
+ ```
13
+ ### Input:
14
+ User: {prompt}
15
+
16
+ ### Response:
17
+ Character:
18
+
19
+ ```
20
+
21
+ Alpaca prompt template should work fine too.
22
+
23
+
24
+ Noromaid: https://huggingface.co/NeverSleep/Noromaid-7b-v0.2/
25
+
26
+ LM Cocktail: https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail