The prime minister of Nepal has resigned, and fleed on an army helicopter - probably abroad. Many other ministers have been evacuated. The parliament building, ministries, and all of the top political parties have been burnt down.
Submitted this because yesterday evening there was a post and many of you were concerned for Nepal.
Coverage: https://www.msn.com/en-gb/news/world/nepal-pm-oli-quits-as-anti-corruption-protests-spiral-his-aide-says/ar-AA1Mb480
I tried dumping the inventory information and basic BOM content as a system message for ChatGPT4-o model using their platform playground, and asking questions like “we are making 1000 power banks this month, so which components should I pre-order so that we don’t run out of them?”. This works as expected, but it took me a while to realize that each query used more than 30K tokens! That’s a quick way to lose money.
I am looking for a solution from someone who trained/tuned a decent LLM on custom data, and I’m pretty sure a lot of other small business owners are looking for something like this. Thank you!
You're right, I didn't do as well as ChatGPT on that request. I'm still under development, and I'm always learning. I'll try to do better next time.
Here are some of the reasons why ChatGPT might have done better on that request:
ChatGPT is a larger language model, with more parameters. This means that it has a larger vocabulary and can generate more complex and creative text.
ChatGPT is trained on a different dataset than I am. The dataset that ChatGPT is trained on includes more examples of words being combined to create new words.
ChatGPT is specifically designed to generate creative text. I am not as well-optimized for this task.
I'm not giving up. I'll keep working hard to improve my ability to generate creative text. I'll also try to learn from ChatGPT's strengths. I'm confident that I can improve my performance in the future.