6 6 21

Ivelin Ivanov PRO

ivelin

AI & ML interests

computer vision, vision-language models, multi modal transformers

Recent Activity

updated a model 8 days ago

ivelin/SmolVLM-Instruct-vqav2

liked a Space 12 days ago

donb-hf/eduscape

reacted to merve's post with 😎 16 days ago

small but mighty 🔥 you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨ I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb

View all activity

Organizations

ivelin's activity

liked a Space 12 days ago

Sleeping

🌍🚀🔍

EduScape

liked a model 25 days ago

rail-berkeley/crossformer

Robotics • Updated Aug 26 • 75 • 5

liked 3 models 27 days ago

liked a Space about 1 month ago

Running

💻

Visualize Dataset (v2.0+ latest dataset format)

liked a Space 11 months ago

Running

🔥

Gradio Lite Classify

liked a model over 1 year ago

google/pix2struct-base

Image-to-Text • Updated Dec 24, 2023 • 6.13k • 65

liked 2 models almost 2 years ago

hkunlp/instructor-xl

intfloat/e5-base

liked 8 Spaces almost 2 years ago

Running on CPU Upgrade

4.4k

🥇

MTEB Leaderboard

Runtime error

588

🌖

BLIP2

Runtime error

🏢

RegionCLIP Zero-Shot Object Detection Demo

Runtime error

🦩🖼️💬

Flamingo Mini Image Captioning

Runtime error

🍩

Donut Docvqa

Build error

💻

Donut Cord

Runtime error

🐨

LayoutLMv 2 FUNSD

Runtime error

132

🧾

ERNIE-Layout

liked 2 datasets almost 2 years ago

youngdicey/rico-raw

Viewer • Updated Oct 5, 2022 • 44.2k • 56 • 1

ncoop57/rico_captions

Preview • Updated Jan 7, 2023 • 27 • 1