News for hackers. Stuff that matters.
Re:Phi-3 Technical Report by svnt on Tuesday April 23, 2024 @01:08AM (#40128703)
Both are saying the same thing: in order for the base model that is phi to perform well as a chat agent, it would need to be tuned for that purpose before its benchmark results could have real-world value.
Re:Phi-3 Technical Report by imjonse on Tuesday April 23, 2024 @01:49AM (#40128906)
From this report. Phi-2 was not instruct tuned indeed.

"Our models went through post-training with both supervised instruction fine-tuning, and preference tuning with DPO. We have worked on generating and curating various instruction and preference data. This has improved the model chat capabilities, robustness, as well as its safety."