Switch Transformers C – 2048 experts (1.6T params for 3.1 TB) (huggingface.co) | HN Screenshots

YHacker Newsscreenshots

Screenshot of huggingface.co: Switch Transformers C – 2048 experts (1.6T params for 3.1 TB)

First screen, captured 2 years ago.

Looks similar

Screenshot of huggingface.co: Yi-34B-Chat

Yi-34B-Chat (huggingface.co)

96 points by tosh 2 years ago | 55 comments

Screenshot of huggingface.co: MonadGPT – What would have happened if ChatGPT was invented in the 17th century?

MonadGPT – What would have happened if ChatGPT was invented in the 17th century?(huggingface.co)

282 points by surprisetalk 2 years ago | 96 comments

Screenshot of huggingface.co: LLaMA-Pro-8B

LLaMA-Pro-8B (huggingface.co)

75 points by tosh 2 years ago | 23 comments

Screenshot of huggingface.co: Alibaba releases 72B LLM with 32k context length

Alibaba releases 72B LLM with 32k context length (huggingface.co)

34 points by logicchains 2 years ago | 10 comments

Screenshot of huggingface.co: Qwen3-4B-Thinking-2507

Qwen3-4B-Thinking-2507 (huggingface.co)

151 points by IdealeZahlen 1 year ago | 51 comments

Screenshot of huggingface.co: Phi-2

Phi-2 (huggingface.co)

25 points by tosh 2 years ago | 4 comments