4 39 362

Bruno Henrique PRO

Bruno

AI & ML interests

None yet

Recent Activity

Reacted to rmayormartins's post with 👀 about 24 hours ago

Estamos tratando de unir, aunar fuerzas y cooperar en experimentos de IA en América Latina. Te invito a unirte a nosotros en «LatinAI». La idea es compartir y organizar espacios, modelos y conjuntos de datos en español/portugués/guaraní/mapuche o ingles para el desarrollo en América Latina. Siéntete libre de unirte a la organización : https://huggingface.co/LatinAI --- We are trying to unite, join forces and cooperate in AI experiments in Latin America. We invite you to join us in “LatinAI”. The idea is to share and organize spaces, models and datasets in Spanish/Portuguese/Guarani/Mapuche or English for development in Latin America. Feel free to join the organization : https://huggingface.co/LatinAI

Reacted to fdaudens's post with ❤️ about 24 hours ago

My new favorite bookmark: AnyChat. The ultimate AI Swiss Army knife that lets you switch between ChatGPT, Gemini, Claude, LLaMA, Grok & more—all in one place! Really cool work by @akhaliq https://huggingface.co/spaces/akhaliq/anychat

Reacted to fdaudens's post with ❤️ about 24 hours ago

View all activity

Organizations

Bruno's activity

Reacted to rmayormartins's post with 👀 about 24 hours ago

Post

324

Estamos tratando de unir, aunar fuerzas y cooperar en experimentos de IA en América Latina. Te invito a unirte a nosotros en «LatinAI». La idea es compartir y organizar espacios, modelos y conjuntos de datos en español/portugués/guaraní/mapuche o ingles para el desarrollo en América Latina.
Siéntete libre de unirte a la organización : https://huggingface.co/LatinAI
---
We are trying to unite, join forces and cooperate in AI experiments in Latin America. We invite you to join us in “LatinAI”. The idea is to share and organize spaces, models and datasets in Spanish/Portuguese/Guarani/Mapuche or English for development in Latin America.
Feel free to join the organization : https://huggingface.co/LatinAI

Reacted to fdaudens's post with ❤️❤️ about 24 hours ago

Post

875

upvoted a paper 9 days ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

Paper • 2411.04928 • Published 16 days ago • 48

liked a model 9 days ago

BAAI/bge-small-en-v1.5

Feature Extraction • Updated Feb 22 • 5.13M • 260

liked a model 15 days ago

distil-whisper/distil-large-v3

Automatic Speech Recognition • Updated Jun 7 • 208k • 257

upvoted a paper 15 days ago

Personalization of Large Language Models: A Survey

Paper • 2411.00027 • Published 26 days ago • 31

Reacted to singhsidhukuldeep's post with 👀 15 days ago

Post

2079

Exciting Research Alert: Revolutionizing Dense Passage Retrieval with Entailment Tuning!

The good folks at HKUST have developed a novel approach that significantly improves information retrieval by leveraging natural language inference.

The entailment tuning approach consists of several key steps to enhance dense passage retrieval performance.

Data Preparation
- Convert questions into existence claims using rule-based transformations.
- Combine retrieval data with NLI data from SNLI and MNLI datasets.
- Unify the format of both data types using a consistent prompting framework.

Entailment Tuning Process
- Initialize the model using pre-trained language models like BERT or RoBERTa.
- Apply aggressive masking (β=0.8) specifically to the hypothesis components while preserving premise information.
- Train the model to predict the masked hypothesis tokens from the premise content.
- Run the training for 10 epochs using 8 GPUs, taking approximately 1.5-3.5 hours.

Training Arguments for Entailment Tuning (Yes! They Shared Them)
- Use a learning rate of 2e-5 with 100 warmup steps.
- Set batch size to 128.
- Apply weight decay of 0.01.
- Utilize the Adam optimizer with beta values (0.9, 0.999).
- Maintain maximum gradient norm at 1.0.

Deployment
- Index passages using FAISS for efficient retrieval.
- Shard vector store across multiple GPUs.
- Enable sub-millisecond retrieval of the top-100 passages per query.

Integration with Existing Systems
- Insert entailment tuning between pre-training and fine-tuning stages.
- Maintain compatibility with current dense retrieval methods.
- Preserve existing contrastive learning approaches during fine-tuning.

Simple, intuitive, and effective!

This advancement significantly improves the quality of retrieved passages for question-answering systems and retrieval-augmented generation tasks.