Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,8 @@ Llama-2-Amharic
|
|
6 |
|
7 |
Uses Llama-2-7b as base. Does not use chat variant.
|
8 |
|
|
|
|
|
9 |
To avoid hallucinations use low top-k.
|
10 |
|
11 |
Use format "$system\nHuman: $prompt\nAssistant [Amharic] : "
|
@@ -20,3 +22,4 @@ The AI is supposed to answer test questions from the human with short responses
|
|
20 |
Human: α ααα αααα α¨αα½α αα½α αααͺα« αα΄αα ααα΅α°ααα
α¨α
α α₯αα α»αα’ α’α«αα΅ 3 α αααΎα½ ααα α αα£αΈαα’
|
21 |
|
22 |
Assistant [Amharic] : "
|
|
|
|
6 |
|
7 |
Uses Llama-2-7b as base. Does not use chat variant.
|
8 |
|
9 |
+
You can use the inference demo script provided to run inference. Note that it expects to be executed in context of llama recipes (https://github.com/facebookresearch/llama-recipes/tree/main/src/llama_recipes/inference)
|
10 |
+
|
11 |
To avoid hallucinations use low top-k.
|
12 |
|
13 |
Use format "$system\nHuman: $prompt\nAssistant [Amharic] : "
|
|
|
22 |
Human: α ααα αααα α¨αα½α αα½α αααͺα« αα΄αα ααα΅α°ααα
α¨α
α α₯αα α»αα’ α’α«αα΅ 3 α αααΎα½ ααα α αα£αΈαα’
|
23 |
|
24 |
Assistant [Amharic] : "
|
25 |
+
|