2:41:00 why domain specialized model Using in-context learning to address hallucination is the best method. Therefore we need longer context length. Enterprises need about 1000 few shots to be reliable.
3:01:00 why phi-3 model does show an infinite generations: It's because EOS token and PAD token were the same. Dam... You nailed it. This is so useful. I was so annoyed by Phi-3 for this particular issue.
Immense learnings in these talks! Adding video chapters will be super helpful because finding the video of interest is hard and easy to miss :)
absolutely. so much solid intel has been shared at this conference
2:41:00
why domain specialized model
Using in-context learning to address hallucination is the best method. Therefore we need longer context length. Enterprises need about 1000 few shots to be reliable.
3:01:00 why phi-3 model does show an infinite generations: It's because EOS token and PAD token were the same.
Dam... You nailed it. This is so useful. I was so annoyed by Phi-3 for this particular issue.
Awesome talks!
omg these talks are 🔥🔥
Huge !!!!
2:56:40
Anyone have a timestamp of each speaker and talk title?
Kisses and hugs❤❤❤❤"