titaenstad

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

LivePortrait

Bring portraits to life!

local-gemma

Gemma 2 optimized for your local machine.

norske-bug-bounty-program

List over kjente norske bug bounty-program 🇳🇴

DeepLearnHackathon

tokun

Tokun to can tokens

tesstrain

Train Tesseract LSTM with make

text_renderer

ScandinavianHONEST

Measuring Harmful Representations in Scandinavian Language Models

pyladies-oslo-data-viz

SATRN

Official Tensorflow Implementation of SATRN (CVPR Workshop WTDDLE 2020)

norbench

Natural language understanding benchmarks for Norwegian

tesstrain

Train Tesseract LSTM with make

llama2_aided_tesseract

Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections, complete with options for text validation and hallucination filtering.

BetterOCR

🔍 Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with 🧠 LLM.

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

fsdp_qlora

Training LLMs with QLoRA + FSDP

mergekit

Tools for merging pretrained large language models.

hunalign

Sentence aligner

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

teknologiradar

Frontend for Knowit teknologiradar