iocuydi commited on
Commit
04fcac9
1 Parent(s): fe616b6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -8,6 +8,8 @@ Uses Llama-2-7b as base. Does not use chat variant.
8
 
9
  You can use the inference demo script provided to run inference. Note that it expects to be executed in context of llama recipes (https://github.com/facebookresearch/llama-recipes/tree/main/src/llama_recipes/inference)
10
 
 
 
11
  To avoid hallucinations use low top-k.
12
 
13
  Use format "$system\nHuman: $prompt\nAssistant [Amharic] : "
 
8
 
9
  You can use the inference demo script provided to run inference. Note that it expects to be executed in context of llama recipes (https://github.com/facebookresearch/llama-recipes/tree/main/src/llama_recipes/inference)
10
 
11
+ Ensure that you replace the Llama-2 tokenizer with the Llama-2-Amharic tokenizer.
12
+
13
  To avoid hallucinations use low top-k.
14
 
15
  Use format "$system\nHuman: $prompt\nAssistant [Amharic] : "