Hacker News Reader

Neat. Maybe you guys should make a fine tuning platform for deepseek specifically, with a fine tune API similar to openAIs. You could expand out into hosting those models too.

View on HN

you mean fine tuning that feels like SFT but is different (since you can't use that with reasoning models) built around the DeepSeek class of models?

I just want to fine tune deepseek v3 chat but it’s not possible or easy for regular consumers

Fireworks has you covered now: https://fireworks.ai/blog/fine-tuning-deepseek-models :)

Reply on news.ycombinator.com