50% on HumanEval with just 1.3B model (twitter.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of twitter.com: 50% on HumanEval with just 1.3B model

First screen, captured 3 years ago.

Looks similar

Screenshot of twitter.com: Why MMAP in llama.cpp hides true memory usage

Why MMAP in llama.cpp hides true memory usage (twitter.com)

95 points by flurly 3 years ago | 69 comments

Screenshot of twitter.com: Wikidata, with 12B facts, can ground LLMs to improve their factuality

Wikidata, with 12B facts, can ground LLMs to improve their factuality (twitter.com)

195 points by raybb 2 years ago | 78 comments

Screenshot of twitter.com: Neural networks in the 1990s

Neural networks in the 1990s (twitter.com)

122 points by jrott 3 years ago | 75 comments

Screenshot of twitter.com: Curious about the training data of OpenAI's new GPT-OSS models? I was too

Curious about the training data of OpenAI's new GPT-OSS models? I was too (twitter.com)

220 points by flabber 1 year ago | 52 comments

Screenshot of twitter.com: Running a 180B parameter LLM on a single Apple M2 Ultra

Running a 180B parameter LLM on a single Apple M2 Ultra (twitter.com)

209 points by tbruckner 3 years ago | 109 comments

Screenshot of twitter.com: Svelte 5 is going to be radical

Svelte 5 is going to be radical (twitter.com)

61 points by thunderbong 3 years ago | 37 comments