Models giving irrelevant responses

Hello! I recently watched the Youtube video about workers AI on the cloudflare workers channel. I was excited to try out the chat app that the presenter built and eventually ported the application to a Svelte app that handled app state in a cleaner way. Anyways, when I get to testing the models out, they are giving me some pretty irrelevant responses, I've attached a screenshot of the responses to the post. I also have logs of the models and messages sent to the AI binding: Model @cf/qwen/qwen1.5-0.5b-chat Messages [{"role":"user","content":"What are the top 3 tasks where you excel? Please keep things brief."}] Model @cf/defog/sqlcoder-7b-2 Messages [{"role":"user","content":"What are the top 3 tasks where you excel? Please keep things brief."}] Model @cf/deepseek-ai/deepseek-math-7b-instruct Messages [{"role":"user","content":"What are the top 3 tasks where you excel? Please keep things brief."}] Please note that I switched to only sending the latest message because including the chat history was only making the responses even more irrelevant. I do use copilot but am new to AI in general and would like to find some uses for these models. Is this just to be expected from these models? Or is this a problem on my end?