oopus (@oopus_hongsu) 's Twitter Profile
oopus

@oopus_hongsu

ID: 869800198922522624

calendar_today31-05-2017 06:18:22

84 Tweet

7 Followers

92 Following

oopus (@oopus_hongsu) 's Twitter Profile Photo

TableGPT2-7B is a large-scale decoder optimized for data-intensive tasks, specializing in the interpretation and analysis of tabular data. huggingface.co/tablegpt/Table…

oopus (@oopus_hongsu) 's Twitter Profile Photo

After enabling the WebGPU feature in Chrome on my Android and testing it with the Qwen 1.5B model, I fully understand why deploying LLMs on mobile devices is challenging. Even with a 1.5B webassembly model, the performance is still too slow. (Local .so might be more efficient

oopus (@oopus_hongsu) 's Twitter Profile Photo

論文引文也要講性別,瑟瑟發抖 "Edited only to reduce gender-specific references." DEFENSIVE COMMUNICATION reagle.org/joseph/2010/co…

oopus (@oopus_hongsu) 's Twitter Profile Photo

Good job! "Bypassing regulatory locks, Faraday cages and upgrading your hearing" lagrangepoint.substack.com/p/airpods-hear…

oopus (@oopus_hongsu) 's Twitter Profile Photo

Aha! ai.google.dev/gemini-api/doc… is down. Error: Server Error The server encountered an error and could not complete your request.Please try again in 30 seconds.

Aha! ai.google.dev/gemini-api/doc… is down. Error: Server Error
The server encountered an error and could not complete your request.Please try again in 30 seconds.
oopus (@oopus_hongsu) 's Twitter Profile Photo

Reason-ModernColBERT is a late interaction model trained on the reasonir-hq dataset. It achieves extremely competitive performance on the BRIGHT benchmark... huggingface.co/lightonai/Reas…

oopus (@oopus_hongsu) 's Twitter Profile Photo

GitHub free LLM API token "How much it costs: Free tier for all personal accounts and OSS orgs; metered paid tier unlocks higher throughput and larger context windows." docs.github.com/en/github-mode…