model merging

4 statements across 3 episodes · 2 bullish · 1 bearish · 3 people on the record · first statement May 31, 2024 by Mark Huang · across every show →

Everything said about model merging, oldest first

May 31, 2024 neutral
Insight
Huang: LoRA merging succeeds on style but fails on complex capabilities
“Like, I will not lie to say I'm really surprised how effective it is sometimes, but I do notice that for more complex abilities other than, like, more stylistic stuff, it does, it kind of falls through, because maybe it's, it requires a much deeper path in the…”
Mark Huang May 31, 2024 ▶ 40:21 How to train a Million Context LLM — with Mark Huang of Gradient.ai
May 31, 2024 negative
Opinion
Huang: Model merging is polluting open LLM leaderboards
“That is extremely interesting from the developer community, and I want to see more of it except it is, to a certain extent, kind of polluting the leaderboards these days, because it's so targeted, and like, now you can kind of game the metric by just finding a…”
Mark Huang May 31, 2024 ▶ 41:27 How to train a Million Context LLM — with Mark Huang of Gradient.ai
Aug 17, 2024 positive
Insight
Howard: Developers should distribute merged adapters rather than merged models
“To explain, it's not that you shouldn't merge models, it's that you shouldn't be distributing a merged model. You should distribute it a merged adapter. 99% of the time. And actually often, one of the best things happening in the model merging world is actuall…”
Jeremy Howard Aug 17, 2024 ▶ 46:26 Answer.ai & AI Magic with Jeremy Howard
May 9, 2025 positive
Insight
Averaging weights of models trained on separate domains works effectively
“You can have a model trained on code, and a model trained on math, and a model trained on Spanish, and you can literally average the weights, and it works.”
Will Brown May 9, 2025 ▶ 14:33 ⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.