2 18 73

João Palmeiro PRO

joaompalmeiro

AI & ML interests

None yet

Recent Activity

reacted to merve's post with ❤️ about 20 hours ago

Fine-tune Gemma3n on videos with audios inside with Colab A100 🔥 Just dropped the notebook where you can learn how to fine-tune Gemma3n on images+audio+text at the same time! keep in mind, it's made for educational purposes 🫡 we do LoRA, audio resampling & video downsampling to be able to train <40GB VRAM stretch modalities and unfreeze layers as you wish! 🙏🏻 https://huggingface.co/merve/smol-vision/blob/main/Gemma3n_Fine_tuning_on_All_Modalities.ipynb

reacted to erikkaum's post with 🤗 1 day ago

We just released native support for @SGLang and @vllm-project in Inference Endpoints 🔥 Inference Endpoints is becoming the central place where you deploy high performance Inference Engines. And that provides the managed infra for it. Instead of spending weeks configuring infrastructure, managing servers, and debugging deployment issues, you can focus on what matters most: your AI model and your users 🙌

liked a model 4 days ago

neulab/Pangea-7B-hf

View all activity

Organizations

upvoted an article 10 days ago

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

and 1 other •

10 days ago

• 573

upvoted an article 11 days ago

Article

SmolLM3: smol, multilingual, long-context reasoner

and 22 others •

11 days ago

• 555

upvoted a paper 16 days ago

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

Paper • 2506.17218 • Published 29 days ago • 27

upvoted a paper about 1 month ago

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Paper • 2412.04467 • Published Dec 5, 2024 • 117

upvoted a paper about 2 months ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published Jun 2 • 114

upvoted an article about 2 months ago

Article

Context Is Gold to Find the Gold Passage: Evaluating and Training Contextual Document Embeddings

and 1 other •

Jun 2

• 24

upvoted a paper about 2 months ago

Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding

Paper • 2502.11492 • Published Feb 17 • 2

upvoted an article about 2 months ago

Article

Common AI Model Formats

•

Feb 27

• 44

upvoted a paper 2 months ago

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

Paper • 2505.13444 • Published May 19 • 16

upvoted 2 articles 2 months ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

•

Jul 29, 2024

• 348

Article

Preference Optimization for Vision Language Models

and 3 others •

Jul 10, 2024

• 79

upvoted a paper 2 months ago

Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis

Paper • 2505.09358 • Published May 14 • 26

upvoted a collection 2 months ago

Marigold Computer Vision

Collection

All things Marigold • 17 items • Updated May 15 • 21

upvoted 3 articles 2 months ago

Article

The Transformers Library: standardizing model definitions

and 3 others •

May 15

• 115

Article

Synthetic data: save money, time and carbon with open source

•

Feb 16, 2024

• 77

Article

Vision Language Models (Better, Faster, Stronger)

and 4 others •

May 12

• 481

upvoted a paper 3 months ago

ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering

Paper • 2504.05506 • Published Apr 7 • 23

upvoted an article 3 months ago

Article

Optimise AI Models and Make Them Faster, Smaller, Cheaper, Greener

and 2 others •

Apr 4

• 18

João Palmeiro PRO

AI & ML interests

Recent Activity

Organizations

joaompalmeiro's activity

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

SmolLM3: smol, multilingual, long-context reasoner

*Context Is Gold to Find the Gold Passage*: Evaluating and Training Contextual Document Embeddings

Common AI Model Formats

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Preference Optimization for Vision Language Models

The Transformers Library: standardizing model definitions

Synthetic data: save money, time and carbon with open source

Vision Language Models (Better, Faster, Stronger)

Optimise AI Models and Make Them Faster, Smaller, Cheaper, Greener

Context Is Gold to Find the Gold Passage: Evaluating and Training Contextual Document Embeddings