Konstantin Dobler's repositories
nlp-research-template
An opinionated NLP research template
multi-conditional-stylegan
[IJCAI 2022] Official code: Art Creation With Multi-Conditional StyleGANs
dargparser
dargparser - the typed argparser with dataclasses for deep learning research
print-on-steroids
A lean and hackable rich logger and print function
git-re-basin-pytorch-transformers
Git Re-Basin: Merging Models modulo Permutation Symmetries for HuggingFace Transformers in PyTorch
hashiwokakero
Typescript Implementation of Japanese Game Hashiwokakero
gan-n1
GAN research project for conditional generation of faces based on the CelebA dataset
genart
Implementation of multiple GAN versions and upsampling operations
stubs
The best StubS
al-folio
A beautiful, simple, clean, and responsive Jekyll theme for academics
client
🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.
Cross-Lingual-Consistency
Easy-to-use framework for evaluating cross-lingual consistency of factual knowledge (Supported LLaMA, BLOOM, mT5, RoBERTa, etc.) Paper here: https://aclanthology.org/2023.emnlp-main.658/
datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
dlib
Utility library for deep learning research
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
lm-evaluation-harness-idk
A framework for few-shot evaluation of language models.
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
pytorch-lightning
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
staged-recipes
A place to submit conda recipes before they become fully fledged conda-forge feedstocks
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
typed-argument-parser
Typed argument parser for Python
wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
wikiextractor
A tool for extracting plain text from Wikipedia dumps
xtreme
XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.