Andres Marafioti's picture

Andres Marafioti

andito

·

AI & ML interests

Multimodal models, VLM and TTS

Recent Activity

upvoted an article 3 days ago

Replicating DeepSeek R1 for Information Extraction

liked a dataset 4 days ago

fixie-ai/gigaspeech

posted an update 4 days ago

Extremely bullish on @CohereForAI's Aya Vision (8B & 32B) - new SOTA open-weight VLMs - 8B wins up to 81% of the time in its class, better than Gemini Flash - 32B beats Llama 3.2 90B! - Covers 23 languages, excels in image captioning, VQA & more - Integrated on transformers from Day 0! Efficient multimodal models are here to stay!!🔥 Check out their blog! https://huggingface.co./blog/aya-vision

View all activity

Organizations

andito's activity

upvoted an article 3 days ago

Article

Replicating DeepSeek R1 for Information Extraction

By

•

Jan 31

• 38

liked a dataset 4 days ago

fixie-ai/gigaspeech

Viewer • Updated Sep 7, 2024 • 16.6M • 13.6k • 4

posted an update 4 days ago

Post

2352

Extremely bullish on @CohereForAI 's Aya Vision (8B & 32B) - new SOTA open-weight VLMs

- 8B wins up to 81% of the time in its class, better than Gemini Flash
- 32B beats Llama 3.2 90B!
- Covers 23 languages, excels in image captioning, VQA & more
- Integrated on transformers from Day 0!

Efficient multimodal models are here to stay!!🔥
Check out their blog! https://huggingface.co./blog/aya-vision

liked 2 models 4 days ago

CohereForAI/aya-vision-8b

Image-Text-to-Text • Updated 5 days ago • 144k • 206

HuggingFaceTB/SmolVLM2-256M-Video-Instruct

Image-Text-to-Text • Updated 3 days ago • 4.16k • 38

liked a Space 5 days ago

Di♪♪Rhythm

Blazingly Fast and Embarrassingly Simple Song Generation

liked a model 5 days ago

ASLP-lab/DiffRhythm-base

Updated 4 days ago • 106

upvoted an article 5 days ago

Article

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

6 days ago

• 57

liked a model 17 days ago

HuggingFaceTB/SmolVLM2-2.2B-Instruct

Image-Text-to-Text • Updated 3 days ago • 429k • 106

liked a Space 17 days ago

SmolVLM

Generate text by analyzing images and videos

upvoted an article 17 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

18 days ago

• 196

published an article 18 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

18 days ago

• 196

liked a Space 18 days ago

The Ultra-Scale Playbook

The ultimate guide to training LLM on large GPU Clusters

authored a paper about 1 month ago

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

Paper • 2502.02737 • Published Feb 4 • 199

upvoted a paper about 1 month ago

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

Paper • 2502.02737 • Published Feb 4 • 199

upvoted an article about 1 month ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.14k

New activity in HuggingFaceTB/SmolVLM-256M-Instruct about 1 month ago

Add ONNX sample code

#8 opened about 1 month ago by

liked a model about 1 month ago

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1 • 372k • 3.2k

upvoted an article about 1 month ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

• 50

New activity in HuggingFaceTB/SmolVLM-256M-Instruct about 1 month ago

Upload photo_2025-01-25_13-45-22.jpg

#5 opened about 1 month ago by