Tulu, every mention
6 scenes, the whole family · ← back to Tulu
tap a year for its mentions
every year anyone Shawn Wang 3Nathan Lambert 3Luca Soldani 3
Verbatim, from the transcripts: the passages where Tulu comes up
The RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)
- ▶ 1:21 Shawn Wang So you've been, you've been doing, like, really good work, uh, and, and honestly, like, I think one of the things that we wanted to kind of establish was Tulu 3 times in the scene
- ▶ 1:37 Nathan Lambert I think that we can recap kind of the story of what Tulu three was aiming to be, and then kind of how it got folded into what the new narrative is.
- ▶ 11:10 Nathan Lambert If you want that, you can like annoy me to try to release all, like for Tulu, like we have a final data set, but we have completions and ratings from more models.
Best of 2024: Open Models [LS LIVE! at NeurIPS 2024]
- ▶ 16:20 Luca Soldani Um, on, on the post-training side, uh, we recently released Tulu-III. 3 times in the scene
The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
- ▶ 1:17:41 unnamed speaker One thing I wanted to make sure I cover before we leave this topic, DPO, you know, one of the DPO models that we're trained, apart from Zephyr and Mixed Draw, which is two of the more high profile ones, is Tulu from 3 times in the scene
- ▶ 1:27:25 Nathan Lambert And then AlpacaVal is a little bit different where you're comparing a candidate model, so the model we've trained, so like when we're training Tulu, we compare that, we submit this, and what it's doing under the hood is comparing the new…