Weight Transfer for RL Post-Training in under 2 seconds (research.perplexity.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of research.perplexity.ai: Weight Transfer for RL Post-Training in under 2 seconds

First screen, captured 9 months ago.

Looks similar

Screenshot of research.perplexity.ai: Rethinking search as code generation

Rethinking search as code generation (research.perplexity.ai)

62 points by 1zael 4 months ago | 18 comments

Screenshot of blog.doubleword.ai: What happens when a GPU writes memory

What happens when a GPU writes memory (blog.doubleword.ai)

61 points by ibobev 1 month ago | 1 comments

Screenshot of blog.research.google: Outperforming larger language models with less training data and smaller models

Outperforming larger language models with less training data and smaller models (blog.research.google)

272 points by atg_abhishek 3 years ago | 99 comments

Screenshot of research.google: ML-Enhanced Code Completion Improves Developer Productivity (2022)

ML-Enhanced Code Completion Improves Developer Productivity (2022)(research.google)

17 points by ddadon10 1 year ago | 3 comments

Screenshot of openai.com: Prover-Verifier Games improve legibility of language model outputs

Prover-Verifier Games improve legibility of language model outputs (openai.com)

122 points by davidbarker 2 years ago | 26 comments

Screenshot of neuralmagic.com: What happens if we remove 50 percent of Llama?

What happens if we remove 50 percent of Llama?(neuralmagic.com)

184 points by BUFU 1 year ago | 107 comments