🔄 In a Training Loop

Gabriel Borg

Gabriel

·

Borg93

AI & ML interests

None yet

Recent Activity

upvoted an article 29 days ago

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

updated a Space about 2 months ago

Gabriel/diffu-trackio

published a Space about 2 months ago

Gabriel/diffu-trackio

View all activity

Organizations

liked 3 models 3 months ago

Riksarkivet/trocr-base-handwritten-hist-swe-2

Image-to-Text • 0.4B • Updated Jun 4 • 79.8k • 17

Riksarkivet/oldbertur-diplomatic-old-icelandic-ner

Token Classification • 0.1B • Updated Jul 17 • 14 • 4

Riksarkivet/oldbertur-normalised-old-icelandic-ner

Token Classification • Updated Jul 17 • 8 • 3

liked a Space 3 months ago

DiffusionGemma vs Gemma-4 — Post-OCR Correction

Diffusion vs autoregressive LLM on historical OCR cleanup

liked a model 4 months ago

numind/NuExtract3

Image-to-Text • 5B • Updated 21 days ago • 79.8k • 356

liked a Space 5 months ago

Multimodal Lab

Whisper speech-to-text, 100% in your browser.

liked a Space 6 months ago

RA-ATR

Extract digital text from handwritten images

liked a Space 11 months ago

RA-MCP

ra-mcp enhances search at Riksarkivet

liked a model about 1 year ago

dots-studio/dots.ocr

Image-Text-to-Text • 3B • Updated Oct 31, 2025 • 322k • 1.33k

liked a Space about 1 year ago

Htrflow Mcp

Image to text, alto- or page-xml

liked 6 models over 1 year ago

Qwen/Qwen2.5-VL-72B-Instruct

Image-Text-to-Text • 73B • Updated Jun 6, 2025 • 157k • • 651

microsoft/Florence-2-large

Image-Text-to-Text • 0.8B • Updated Aug 4, 2025 • 620k • 1.86k

rhymes-ai/Aria

Image-Text-to-Text • 25B • Updated Apr 23, 2025 • 46.8k • 639

Qwen/Qwen2.5-VL-3B-Instruct

Image-Text-to-Text • 4B • Updated Apr 6, 2025 • 3.07M • • 696

nvidia/NV-Embed-v2

Feature Extraction • 8B • Updated Jul 21, 2025 • 22.3k • 516

nomic-ai/nomic-embed-vision-v1.5

Image Feature Extraction • 92.9M • Updated Mar 31, 2025 • 78k • 228

liked a Space almost 2 years ago

HTRflow App

HTR (Handwritten Text Recognition) demo application

liked a model almost 2 years ago

vidore/colqwen2-v0.1

Visual Document Retrieval • Updated 21 days ago • 10.9k • 197

liked 2 Spaces almost 2 years ago

Emu3

Generate images and answer questions using text input

ColPali fine-tuning Query Generator

Generate document retrieval queries from a page image