Evidence receipt / belief
Published · transcript-backedVipul Ved Prakash: belief
8 Feb 2024 Latent Space Cloud Intelligence at the speed of 5000 tok/s - with Ce Zhang and Vipul Ved Prakash of Together AI
“I would say right now, the top five models on our inference stack are probably all fine-tuned versions of open models.”
Source trail
Everything needed to verify it.
- Speaker
- Vipul Ved Prakash
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 8 Feb 2024
- Publisher
- Latent Space
Transcript context
…Let's talk about the most precious resource on planet earth, GPUs. You have a lot of compute obviously, but you also have a lot of product pieces. You have inference, you have fine tuning, you have pre-training. What's the split in terms of usage? Do you see most people are just running inference on off the shelf models? Do you see maybe some last mile fine tuning? I would say right now, the top five models on our inference stack are probably all fine-tuned versions of open models. And we've seen- Who fine-tuned them? You fine-tuned them?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.