Update README.md

README.md

@@ -15,11 +15,11 @@ datasets:
 - ProlificAI/social-reasoning-rlhf
 - arcee-ai/reasoning-sharegpt
 base_model:
-- unsloth/Qwen2.5-7B-Instruct
+- unsloth/Qwen2.5-7B-Instruct-bnb-4bit
 ---
 
 # Your Model Name
 Reason_Qwen
 
 ## Model Description
-Model is finetuned version of unsloth/Qwen2.5-7B-Instruct. It is finetuned to reason better.
+Model is finetuned version of unsloth/Qwen2.5-7B-Instruct-bnb-4bit. It is finetuned to reason better.