Hey, thanks for the video ! 🙂 I'm noticing some words cutting out now and then - I'm sure you're aware too just wanted to mention it ! Again, thanks for everything 🙂
@SonGoku-pc7jl
4 ай бұрын
very interesting, best video of gemma 1.1 ;)
@samwitteveenai
4 ай бұрын
thanks much appreciated
@theunknown2090
5 ай бұрын
Thanks for the awesome video
@andyma1146
5 ай бұрын
In the section “A meditation mantra is all you need” you got better performance by adjusting the system prompt. I’m not very good at prompt engineering. Do you think that I could get comparable performance improvements if instead of playing with the system prompt, I asked LLM to reflect on or revise its answer? This would be kind of like using an agentic workflow. I’m wondering if using reflection would allow me to avoid prompt engineering for each new model I want to try out 🧐🤨
@澤翰陳
5 ай бұрын
thanks for aharing🎉. a question about 13:03 . What do you mean by output things with "tags" as what people are doing with Claude3.?
@samwitteveenai
5 ай бұрын
Claude models use XML tags for outputting and for partitioning things like exemplars for FewShot Learning etc. I cover this in the video about Claude Haiku with examples.
@tornyu
5 ай бұрын
5:00 For a true comparison, shouldn't the temperature be set to 0?
@existenceisillusion6528
5 ай бұрын
I wonder if they might have implemented Quiet-STaR
@MeinDeutschkurs
5 ай бұрын
Can‘t you tell to send the „stop-token“ after the tool decision? 15:46
@samwitteveenai
5 ай бұрын
yes though you want to send in the tool output for the next call then you don't want it using the stop token there. You want it generating to the next tool or decision etc.
@MeinDeutschkurs
5 ай бұрын
@@samwitteveenai 🤦♂️, in deed. I just thought about: how to avoid a very verbose reply.
@zacboyles1396
5 ай бұрын
9:00 👀
@katopz
5 ай бұрын
Great review! I'm surprise that you can read Thai language 😳
@samwitteveenai
5 ай бұрын
ขอบคุณครับ - I lived in Bkk a long time ago
@jimigoodmojo
5 ай бұрын
Thanks, super interesting... FYI. seems both gemma 7b colab links bring you to 1.0
@samwitteveenai
5 ай бұрын
weird I just checked it now and the top seems to be going to 1.1 fine. try again and let me know if you are still having problems
@MeinDeutschkurs
5 ай бұрын
I‘m not sure if I should watch the video: a title like ‚Gemma 1.1 finally useable‘ would be more inviting.
Пікірлер: 18