Batched reward model inference and Best-of-N sampling (raw.sh) | HN Screenshots

YHacker Newsscreenshots

Screenshot of raw.sh: Batched reward model inference and Best-of-N sampling

First screen, captured 1 year ago.

Looks similar

Screenshot of ngrok.com: Prompt caching for cheaper LLM tokens

Prompt caching for cheaper LLM tokens (ngrok.com)

268 points by samwho 10 months ago | 67 comments

Screenshot of lukefleed.xyz: Cache-friendly, low-memory Lanczos algorithm in Rust

Cache-friendly, low-memory Lanczos algorithm in Rust (lukefleed.xyz)

115 points by lukefleed 11 months ago | 18 comments

Screenshot of levroai.com: The Revolution of Token-Level Rewards

The Revolution of Token-Level Rewards (levroai.com)

18 points by aagr 1 year ago | 3 comments

Screenshot of nuenki.app: Experimentation Matters: Why Nuenki isn't using pairwise evaluations

Experimentation Matters: Why Nuenki isn't using pairwise evaluations (nuenki.app)

4 points by Alex-Programs 1 year ago | 0 comments

Screenshot of antfly.io: A search-and-inference database from scratch in pure Zig

A search-and-inference database from scratch in pure Zig (antfly.io)

55 points by kingcauchy 1 month ago | 17 comments

Screenshot of marqo.ai: Matryoshka Representation Learning with CLIP

Matryoshka Representation Learning with CLIP (marqo.ai)

25 points by esleightholm 2 years ago | 0 comments