Shital Shah sur Twitter : "Surprising and important paper: TLDR; All the gains we get by first pre-training on large dataset and then fine tuning on small dataset could be obtained by just small dataset but with pre-training objective!!"
Tags:
Au sujet de ce document
Infos sur le fichier
Documents with similar tags (experimental)
LlamaIndex 🦙 sur X : "RAFT - Retrieval Augmented Fine Tuning..."
Tags:
2024-03-28 A propos
Jeremy Howard sur X : "It looks like @johnowhitaker & I may have found something crazy: LLMs can nearly perfectly memorise from just 1-2 examples!"
Tags:
2023-09-06 A propos
Peter J. Liu sur Twitter : "RLHF-alternative without RL"
Tags:
2023-05-18 A propos
Niels Rogge sur Twitter : "Made some new demo notebooks! - fine-tune @MetaAI's SAM and @GoogleAI's Pix2Struct on custom data"
Tags:
2023-05-09 A propos
(((ل()(ل() 'yoav))))👾 sur Twitter : "there is this genre of papers that show you can train/tune only some subset of a network's weights, freezing the rest, and things still work as well as (or better than) full training/tuning..."
Tags:
2023-02-15 A propos
Ananya Kumar sur Twitter : "How should you fine-tune a large pretrained model (CLIP, SimCLR) robustly?..."
Tags:
2022-03-03 A propos