Update README.md

README.md

@@ -3,9 +3,7 @@ license: mit
 language:
 - en
 tags:
-- peft
-- lora
-- merge
+- sft
 ---
 ```Dimensity-3B```
 
@@ -32,5 +30,4 @@ This prompts the model to take on an assistant role.
 As the model was trained on public conversational data, it may generate responses that contain harmful stereotypes or toxic content. The model should be used with caution in sensitive contexts.
 
 # Caveats and Recommendations
-This model is designed for open-ended conversation. It may sometimes generate plausible-sounding but incorrect information. Outputs should be validated against external sources.
-
+This model is designed for open-ended conversation. It may sometimes generate plausible-sounding but incorrect information. Outputs should be validated against external sources.