Llama.cpp now has an official website: llama.apptwitter.com17 points·by julien_c·2 เดือนที่ผ่านมา·4 comments
Tiny Agent: a MCP-powered agent in 50 lines of codehuggingface.co3 points·by julien_c·ปีที่แล้ว·0 comments
Benchmarking Versioning Tools for ML: S3, DVC, Git LFS, and XetHubabout.xethub.com1 points·by julien_c·2 ปีที่แล้ว·1 comments
CoreWeave (AI Hyperscaler) raises $7.5B in debtcoreweave.com4 points·by julien_c·2 ปีที่แล้ว·0 comments
HuggingChat Assistant plugged on the HN front pagehuggingface.co1 points·by julien_c·2 ปีที่แล้ว·0 comments
Hugging Face introduces Pull Requests and Discussionshuggingface.co6 points·by julien_c·4 ปีที่แล้ว·0 comments
T0* – Series of encoder-decoder models trained on a large set of different taskshuggingface.co218 points·by julien_c·5 ปีที่แล้ว·153 comments
HuggingPics: Easily train and deploy image classifiers for anythinggithub.com3 points·by julien_c·5 ปีที่แล้ว·0 comments
OpenAI API: preliminary beta pricing announcedbeta.openai.com2 points·by julien_c·6 ปีที่แล้ว·0 comments
julien_c·3 เดือนที่ผ่านมา·discuss> Ollama eventually added ollama run hf.co/{repo}:{quant} to pull directly from Hugging Face, which partially addresses the availability problem.uh actually, _we_ did (generates a Docker-style manifest on the fly)
julien_c·5 เดือนที่ผ่านมา·discussand a lot of traction on paid (private in particular) storage these days; sneak peek at new landing page: https://huggingface.co/storage
julien_c·3 ปีที่แล้ว·discuss[i work at Hugging Face]BTW the reporting in this article is sloppy/incorrect
julien_c·3 ปีที่แล้ว·discussFlamingo-style, see for instance the recently released IDEFICS: https://huggingface.co/blog/idefics
julien_c·3 ปีที่แล้ว·discusswe have a secret plan to change our logo to a Face Hugger some time in the future :)
julien_c·3 ปีที่แล้ว·discussquite cool! haven't tried it yet, but what's the latency on hot-loading a model? (for instance, loading `stabilityai/stable-diffusion-2-1` for the first API call)
julien_c·5 ปีที่แล้ว·discussArXiv link to the paper: https://arxiv.org/abs/2110.08207GitHub repo: https://github.com/bigscience-workshop/promptsource
julien_c·5 ปีที่แล้ว·discussFWIW this is extractive question answering so the output of the model can only be a span of the input paragraph.SQuAD is the prototypical example of a dataset for this task, see https://rajpurkar.github.io/SQuAD-explorer/
uh actually, _we_ did (generates a Docker-style manifest on the fly)