Clelia (Astra) Bertelli's picture

Clelia (Astra) Bertelli

as-cle-bert

AI & ML interests

Biology + Artificial Intelligence = ❤️ | AI for sustainable development, sustainable development for AI | Researching on Machine Learning Enhancement | I love automation for everyday things | Blogger | Open Source

Recent Activity

Articles

Organizations

Social Post Explorers's profile picture Hugging Face Discord Community's profile picture GreenFit AI's profile picture

Posts 33

view post
Post
1509
🚀𝐍𝐞𝐰 𝐝𝐞𝐦𝐨 𝐚𝐥𝐞𝐫𝐭🚀

Convert (almost) everything to PDF with 𝐏𝐝𝐟𝐈𝐭𝐃𝐨𝐰𝐧, now on Spaces! 👉 as-cle-bert/pdfitdown

You can also install it locally:

python3 -m pip install pdfitdown


Don't forget to star it on GitHub, if you find it useful! 👉 https://www.github.com/AstraBert/PdfItDown

view post
Post
522
Hi HuggingFace Community🤗, I am thrilled to announce:

𝐪𝐝𝐮𝐫𝐥𝐥𝐦 𝚟𝟷-𝚛𝚌.𝟷 (https://github.com/AstraBert/qdurllm/tree/january-2025)

Qdurllm (𝗤𝗱rant, 𝗨𝗥Ls, 𝗟arge 𝗟anguage 𝗠odels) is a local Gradio (Gradio) application that lets you upload you web content to a local Qdrant (Qdrant) database and search through it or chat with it.

The 𝗻𝗲𝘄 𝗽𝗿𝗲-𝗿𝗲𝗹𝗲𝗮𝘀𝗲 (https://github.com/AstraBert/qdurllm/releases/tag/v1.0.0-rc.0) implements 𝘀𝗽𝗮𝗿𝘀𝗲 𝘀𝗲𝗮𝗿𝗰𝗵 (with prithivida/Splade_PP_en_v1) + 𝗿𝗲𝗿𝗮𝗻𝗸𝗶𝗻𝗴 (with nomic-ai/modernbert-embed-base by Hugging Face + Nomic AI) and 𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗰𝗮𝗰𝗵𝗶𝗻𝗴 (based on Qdrant) and switched 𝗳𝗿𝗼𝗺 google/gemma-2-2b-it 𝘁𝗼 Qwen/Qwen2.5-1.5B-Instruct to conform to the SOTA landscape and to finally make the application based 𝗼𝗻𝗹𝘆 𝗼𝗻 𝘁𝗿𝘂𝗹𝘆 𝗼𝗽𝗲𝗻 𝗺𝗼𝗱𝗲𝗹𝘀.

The pre-release is 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲 𝗳𝗼𝗿 𝘁𝗲𝘀𝘁𝗶𝗻𝗴 and I would be really really happy if you wanted to give it a try and leave your feedback on the discussion thread on GitHub (https://github.com/AstraBert/qdurllm/discussions/8) or here on Hugging Face forum via comments under this post✨.
Find all the information to install and launch it here 👉 https://astrabert.github.io/qdurllm/#2-installation