dinhanhx's picture

dinhanhx

dinhanhx

·

dinhanhx

AI & ML interests

Vision Language

Recent Activity

liked a model 8 days ago

allenai/olmOCR-2-7B-1025-FP8

upvoted an article 10 days ago

🪆 Introduction to Matryoshka Embedding Models

liked a model 10 days ago

nanonets/Nanonets-OCR2-3B

View all activity

Organizations

upvoted an article 10 days ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

• 178

upvoted a collection 20 days ago

InternVL3.5-Flash

InternVL3.5-Flash is a fast variant of InternVL3.5 using semantic aware dynamic high-resolution strategy. • 9 items • Updated 16 days ago • 6

upvoted a collection about 1 month ago

ERNIE 4.5

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 26 items • Updated Sep 24 • 174

upvoted 2 papers about 2 months ago

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

Paper • 2506.03487 • Published Jun 4 • 4

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29 • 28

upvoted a collection 3 months ago

Describe Anything

Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 7 items • Updated 9 days ago • 58

upvoted 3 articles 4 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

• 705

Article

Large-scale Near-deduplication Behind BigCode

May 16, 2023

• 35

Article

Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

By

and 11 others •

Jun 27

• 29

upvoted an article 6 months ago

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21

• 186

upvoted a collection 6 months ago

DocAI

21 items • Updated 18 days ago • 1

upvoted 2 articles 6 months ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15, 2024

• 189

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26

• 168

upvoted 2 collections 6 months ago

Unsloth 4-bit Dynamic Quants

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated about 2 hours ago • 87

NVILA

11 items • Updated Sep 13 • 16

upvoted a paper 8 months ago

π_0: A Vision-Language-Action Flow Model for General Robot Control

Paper • 2410.24164 • Published Oct 31, 2024 • 29

upvoted 4 articles 9 months ago

Article

Vision Language Models Explained

Apr 11, 2024

• 478

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Jan 23

• 186

Article

Visual Document Retrieval Goes Multilingual

Jan 10

• 77

Article

Better RAG 1: Advanced Basics

By

•

Mar 14, 2024

• 32