Dsg2 commited on
Commit
38af057
·
verified ·
1 Parent(s): 410fba8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -54,6 +54,14 @@ Multiple choice:
54
  | LS-Micro-Base | 118 | **46.6%** | **52.5%** | 25.0% |
55
  | LS-Tiny-Base | 118 | 40.7% | 47.5% | 25.0% |
56
 
 
 
 
 
 
 
 
 
57
  ## The base model is horrendous at chat, and is intended to be used as a base to be finetuned for specialised tasks.
58
  To try LS-Micro or to train/finetune the model, follow this quickstart guide:
59
  1. Clone the latest version of Cudalm [here](https://github.com/Dsg2/cudalm-c) (only windows supported currently, optimised for Blackwell 2.0/CPU).
 
54
  | LS-Micro-Base | 118 | **46.6%** | **52.5%** | 25.0% |
55
  | LS-Tiny-Base | 118 | 40.7% | 47.5% | 25.0% |
56
 
57
+ Example: (Greedy)
58
+ ```
59
+ <|user|>
60
+ Hi
61
+ <|assistant|>
62
+ I'm sorry, but I'm unable to assist with the problem. My current capabilities are limited to the functions provided to me. In this case, I can help you solve the problem.
63
+ ```
64
+
65
  ## The base model is horrendous at chat, and is intended to be used as a base to be finetuned for specialised tasks.
66
  To try LS-Micro or to train/finetune the model, follow this quickstart guide:
67
  1. Clone the latest version of Cudalm [here](https://github.com/Dsg2/cudalm-c) (only windows supported currently, optimised for Blackwell 2.0/CPU).