Update README.md

README.md

@@ -7,7 +7,7 @@ pipeline_tag: text-generation
 
 ## Summary
 
-`Deer-3b`, an instruction-following large language model based on `Bloom-3b`. Deer is trained on ~15k instruction/response fine tuning records.
+`Deer-3b`, an instruction-following large language model based on `Bloom-3b`. Deer is fine-tuned using ±15k instructions.
 
 Deer will also be available in larger models size.