Ok fair, it would have been of course more interesting if they did SFT v1 -> SFT v2 -> SFT v3 -> … SFT v1 -> SFT v2 -> RLHF v1 -> … RLHF v1 -> RLHF v2 -> RLHF v2 -> …
Suggestions for More Interesting Model Training Progression Sequences
By
–
Global AI News Aggregator
By
–
Ok fair, it would have been of course more interesting if they did SFT v1 -> SFT v2 -> SFT v3 -> … SFT v1 -> SFT v2 -> RLHF v1 -> … RLHF v1 -> RLHF v2 -> RLHF v2 -> …
Leave a Reply