Hugging Face's logo
Filippo B's picture
7 4

Filippo B

Filippo
·
https://www.filippobroggini.com/

AI & ML interests

NLP, data-intensive applications, cloud data platforms, information retrieval, workflows orchestration

Recent Activity

updated a collection 5 days ago
LLMs and such
upvoted a paper 5 days ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
upvoted an article 3 months ago
Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably
View all activity

Organizations

Squirro's profile picture Hugging Face Discord Community's profile picture Nerdy Face's profile picture Serendipyty's profile picture

Filippo's activity

updated a collection 5 days ago
upvoted a paper 5 days ago
upvoted an article 3 months ago
view article
Article

Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably

By abhinand •
• 12
updated 2 collections 4 months ago
upvoted a paper 4 months ago
reacted to merve's post with 🔥 4 months ago
view post
Post
5602
I have put together a notebook on Multimodal RAG, where we do not process the documents with hefty pipelines but natively use:
- vidore/colpali for retrieval 📖 it doesn't need indexing with image-text pairs but just images!
- Qwen/Qwen2-VL-2B-Instruct for generation 💬 directly feed images as is to a vision language model with no processing to text!
I used ColPali implementation of the new 🐭 Byaldi library by @bclavie 🤗
https://github.com/answerdotai/byaldi
Link to notebook: https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb
upvoted an article 4 months ago
view article
Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By manu •
• 199
New activity in Filippo/distilabel-intel-orca-dpo-pairs-filtered about 1 year ago

add distilabel and synthethic tag

1
#2 opened about 1 year ago by
davidberenstein1957
updated a dataset about 1 year ago
updated a collection about 1 year ago