50 43 103

Andres Marafioti

andito

AI & ML interests

Multimodal models, VLM and TTS

Recent Activity

updated a dataset about 7 hours ago

huggingface/documentation-images

Reacted to merve's post with 🔥 about 7 hours ago

The authors of ColPali trained a retrieval model based on SmolVLM 🤠 https://huggingface.co/vidore/colsmolvlm-alpha TLDR; - ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks - ColSmolVLM is more memory efficient than ColQwen2 💗

New activity about 8 hours ago

HuggingFaceTB/SmolVLM-Instruct:ValueError: `resolution_max_side` cannot be larger than `max_image_size` with N=5

View all activity

Articles

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Jul 25

• 18

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 68

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Jun 24

• 177

Organizations

andito's activity

upvoted 3 articles about 1 month ago

Article

Llama 3.2 in Keras

Oct 21

• 9

Article

Welcome, Gradio 5

Oct 9

• 72

Article

Tool Use, Unified

Aug 12

• 64

upvoted 3 articles 2 months ago

Article

FineVideo: behind the scenes

Sep 23

• 23

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 68

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18

• 204

upvoted a collection 2 months ago

RWKV v6

Collection

5 items • Updated Sep 3 • 9

upvoted 2 articles 2 months ago

Article

A failed experiment: Infini-Attention, and why we should keep trying?

Aug 14

• 50

Article

Accelerate 1.0.0

Sep 13

• 50

upvoted 2 collections 3 months ago

🤖 Agents

Collection

17 items • Updated 6 days ago • 35

Image to Video

Collection

4 items • Updated Dec 10, 2023 • 9

upvoted 5 articles 3 months ago

Article

Announcing New Dataset Search Features

Jul 8

• 22

Article

DEMO: French Spoken Language Understanding with the new speech resources from NAVER LABS Europe

•

Aug 28

• 9

Article

Scaling robotics datasets with video encoding

Aug 27

• 34

Article

Deep Learning over the Internet: Training Language Models Collaboratively

Jul 15, 2021

• 4

Article

MicroJAX

•

Aug 25

• 16

upvoted a paper 3 months ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22 • 121

upvoted 3 articles 3 months ago

Article

How to communicate in a Pull Request?

•

Aug 22

• 18

Article

The 5 Most Under-Rated Tools on Hugging Face

Aug 22

• 85

Article

Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI

Aug 19

• 18

Andres Marafioti

AI & ML interests

Recent Activity

Articles

SmolVLM - small yet mighty Vision Language Model

Deploying Speech-to-Speech on Hugging Face

FineVideo: behind the scenes

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Docmatix - a huge dataset for Document Visual Question Answering

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Organizations

andito's activity

Llama 3.2 in Keras

Welcome, Gradio 5

Tool Use, Unified

FineVideo: behind the scenes

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

A failed experiment: Infini-Attention, and why we should keep trying?

Accelerate 1.0.0

Announcing New Dataset Search Features

DEMO: French Spoken Language Understanding with the new speech resources from NAVER LABS Europe

Scaling robotics datasets with video encoding

Deep Learning over the Internet: Training Language Models Collaboratively

MicroJAX

How to communicate in a Pull Request?

The 5 Most Under-Rated Tools on Hugging Face

Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI