Supervised fine tuning on curated data is reinforcement learning (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Supervised fine tuning on curated data is reinforcement learning

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: QLoRA: Efficient Finetuning of Quantized LLMs

QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org)

270 points by Garcia98 3 years ago | 90 comments

Screenshot of arxiv.org: Reverse Engineering Self-Supervised Learning

Reverse Engineering Self-Supervised Learning (arxiv.org)

72 points by headalgorithm 3 years ago | 12 comments

Screenshot of arxiv.org: CleaR: Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Labels

CleaR: Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Labels (arxiv.org)

15 points by PaulHoule 1 year ago | 0 comments

Screenshot of arxiv.org: Reinforcement Pre-Training

Reinforcement Pre-Training (arxiv.org)

48 points by frozenseven 1 year ago | 17 comments

Screenshot of arxiv.org: Unsupervised Elicitation of Language Models

Unsupervised Elicitation of Language Models (arxiv.org)

128 points by kordlessagain 1 year ago | 18 comments

Screenshot of arxiv.org: LoRA vs. Full Fine-Tuning: An Illusion of Equivalence

LoRA vs. Full Fine-Tuning: An Illusion of Equivalence (arxiv.org)

223 points by timbilt 1 year ago | 50 comments