finetuning
#1
by sujra - opened
Hello Sir,
I am also working on ER and I would like to discuss why you chose the reasoning model instead of using Qwen3-4B-Instruct-2507. Why did you decide to use the newer Qwen model? I finetune my model on 500 using Qwen3-4B-Instruct-2507 , but it is hallucinating more. Could you please share your contact details so that we can discuss this more clearly?
sujra changed discussion title from Greeting to finetuning