Filippo B's picture

7 9 1

Filippo B

Filippo

·

https://www.filippobroggini.com/

AI & ML interests

GenAI, LLMs, VLMs, accelerated computing, information retrieval, workflows orchestration

Recent Activity

upvoted an article about 1 month ago

OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models

upvoted a collection 2 months ago

Hf-native ColVision Models

upvoted an article 3 months ago

Vision Language Models (Better, Faster, Stronger)

View all activity

Organizations

upvoted an article about 1 month ago

Article

OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models

By

and 3 others •

Jul 18

• 47

upvoted a collection 2 months ago

Hf-native ColVision Models

Models that can be used with the native transformers 🤗 implementation instead of colpali-engine. • 3 items • Updated Apr 16 • 7

upvoted 2 articles 3 months ago

Article

Vision Language Models (Better, Faster, Stronger)

By

and 4 others •

May 12

• 511

Article

Vision Language Models Explained

By

and 1 other •

Apr 11, 2024

• 438

upvoted an article 4 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

By

•

Mar 26

• 158

updated a Space 5 months ago

First Agent Template

Get current local time in any timezone

updated a collection 5 months ago

LLMs and such

3 items • Updated Mar 14

liked a Space 6 months ago

The Ultra-Scale Playbook

The ultimate guide to training LLM on large GPU Clusters

updated a collection 7 months ago

LLMs and such

3 items • Updated Mar 14

upvoted a paper 7 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 242

upvoted an article 9 months ago

Article

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

By

•

Aug 20, 2024

• 21

updated 2 collections 11 months ago

Search and retrieval

1 item • Updated Oct 10, 2024

Vision Language Models (VLMs)

1 item • Updated Oct 2, 2024

upvoted a paper 11 months ago

ColPali: Efficient Document Retrieval with Vision Language Models

Paper • 2407.01449 • Published Jun 27, 2024 • 51

reacted to merve's post with 🔥 11 months ago

Post

5686

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 11 months ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By

•

Jul 5, 2024

• 288

New activity in Filippo/distilabel-intel-orca-dpo-pairs-filtered over 1 year ago

add distilabel and synthethic tag

#2 opened over 1 year ago by

davidberenstein1957

updated a dataset over 1 year ago

Filippo/distilabel-intel-orca-dpo-pairs-filtered

Viewer • Updated Feb 6, 2024 • 5.92k • 20