Editorial opinion startupxo
If it's a decision model that supports image input from the start and can handle 64k tokens, unlike general text-based classification, I'd like to experience how effectively it can handle complex tasks utilizing visual information. Especially since it runs on Cloudflare's edge infrastructure with short response times, that's a notable point to experience firsthand. However, fine-tuning is currently only available through partner collaboration, so if you want to try custom adjustments directly, you'll have to wait a bit longer.
Writing language: Korean