John Locke's picture

John Locke

johnlockejrr

·

johnlockejrr@gmail.com

AI & ML interests

NLP, OCR, AI

Recent Activity

liked a model 1 day ago

prithivMLmods/LightOnOCR-2-1B-f32-GGUF

liked a model 2 days ago

ai4bharat/indic-conformer-600m-multilingual

liked a Space 2 days ago

ACE-Step/Ace-Step-v1.5

View all activity

Organizations

upvoted a collection 12 days ago

SecureCode

10 items • Updated 2 days ago • 3

upvoted a paper 17 days ago

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

Paper • 2601.14251 • Published 20 days ago • 24

upvoted an article 19 days ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

Oct 23, 2025

•

73

upvoted an article about 1 month ago

Article

M2.1: Multilingual and Multi-Task Coding with Strong Generalization

Jan 5

•

37

upvoted a collection about 1 month ago

IQuest-Coder

13 items • Updated Dec 31, 2025 • 90

upvoted an article about 1 month ago

Article

New in llama.cpp: Model Management

Dec 11, 2025

•

118

upvoted an article about 2 months ago

Article

Efficient MultiModal Data Pipeline

+3

Jul 8, 2025

•

70

upvoted a changelog 2 months ago

Changelog

Duplicate Datasets

Dec 3, 2025

• 104

upvoted an article 2 months ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

Dec 1, 2025

•

292

upvoted a collection 3 months ago

SHAMIYAT: A Collection of Syrian Dialect Datasets & LLMs

A collection of datasets and language models focused on the Syrian dialect, supporting NLP research and applications for Syria • 4 items • Updated Nov 28, 2025 • 2

upvoted an article 3 months ago

Article

How to train a new language model from scratch using Transformers and Tokenizers

Feb 14, 2020

•

58

upvoted a collection 3 months ago

Yiddish Whisper Training

Yiddish based Whisper post-training - Crowd Sourced Open Data • 10 items • Updated Oct 24, 2025 • 4

upvoted a collection 5 months ago

Scaling Low-Res MT via Synthetic Data Generation with LLMs

Synthetic baselines trained for our paper "Scaling Low-Resource MT via Synthetic Data Generation with LLMs" accepted as a main in EMNLP 2025. • 8 items • Updated Sep 16, 2025 • 1

upvoted a paper 5 months ago

Scaling Low-Resource MT via Synthetic Data Generation with LLMs

Paper • 2505.14423 • Published May 20, 2025 • 2

upvoted a collection about 1 year ago

DictaBERT

Collection of state-of-the-art language model for Hebrew, finetuned for various tasks, as detailed in the article: https://arxiv.org/abs/2308.16687 • 17 items • Updated Apr 4, 2024 • 5

upvoted a paper about 1 year ago

Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction

Paper • 2411.17835 • Published Nov 19, 2024 • 4

upvoted an article about 1 year ago

Article

HTRflow - A tool for HTR and OCR

Oct 1, 2024

•

22

upvoted a collection almost 2 years ago

ZeroGPU Spaces

ZeroGPU Spaces made by the community • 17 items • Updated Jun 6, 2024 • 247