akanyaani

akanyaani's Stars

• attardi/wikiextractor

  A tool for extracting plain text from Wikipedia dumps

  Language:Python3.8k966

• Avinash987/Coding

  Data Structures and Algorithms (DSA) Preparation sheet

  Language:C++2.3k575

• bakwc/JamSpell

  Modern spell checking library - accurate, fast, multi-language

  Language:C++623103

• EleutherAI/the-pile

  Language:Python1.5k132

• tensorflow/mesh

  Mesh TensorFlow: Model Parallelism Made Easier

  Language:Python1.6k256

• CalculatedContent/WeightWatcher

  The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

  Language:Python1.5k125

• NathanDuran/MRDA-Corpus

  Utilities for Processing the Meeting Recorder Dialogue Act Corpus

  Language:Python337

• connorferster/handcalcs

  Python library for converting Python calculations into rendered latex.

  Language:CSS5.7k435

• reiinakano/scikit-plot

  An intuitive library to add plotting functionality to scikit-learn objects.

  Language:Python2.4k286

• snorkel-team/snorkel

  A system for quickly generating training data with weak supervision

  Language:Python5.8k856

• akanyaani/gpt-2-tensorflow2.0

  OpenAI GPT2 pre-training and sequence prediction implementation in Tensorflow 2.0

  Language:Python26183

• jalammar/ecco

  Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

  Language:Jupyter Notebook2k171

• bigscience-workshop/promptsource

  Toolkit for creating, sharing and using natural language prompts.

  Language:Python2.7k356

• hellohaptik/spello

  Fast and accurate spell correction library

  Language:Python7821

• CuttleLabs/cuttle-cli

  Cuttle automates the transformation of your Python notebook into deployment-ready projects (API, ML pipeline, or just a Python script)

  Language:Python491

• karpathy/minGPT

  A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

  Language:Python20.7k2.7k

• labmlai/annotated_deep_learning_paper_implementations

  🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

  Language:Python57.7k5.9k

• abhishekkrthakur/colabcode

  Run VSCode (codeserver) on Google Colab or Kaggle Notebooks

  Language:Python2.1k278

• wolfgarbe/SymSpell

  SymSpell: 1 million times faster spelling correction & fuzzy search through Symmetric Delete spelling correction algorithm

  Language:C#3.2k299

• Layout-Parser/layout-parser

  A Unified Toolkit for Deep Learning Based Document Image Analysis

  Language:Python5k476

• jessevig/bertviz

  BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

  Language:Python7k790

• akanyaani/Illustrated_GPT2_With_Code

  Explained GPT-2 Transformer model step by step with code.

  Language:Jupyter Notebook154

• facebookresearch/fairscale

  PyTorch extensions for high performance and large scale training.

  Language:Python3.2k283

• jonnyhyman/QuantumWaves

  A Schrodinger-equation quantum wave function visualization

  Language:Python11122

• joke2k/faker

  Faker is a Python package that generates fake data for you.

  Language:Python17.9k1.9k

• goru001/inltk

  Natural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need

  Language:Python825161

• mhagiwara/100-nlp-papers

  100 Must-Read NLP Papers

  3.8k569

• elasticsearch-dump/elasticsearch-dump

  Import and export tools for elasticsearch & opensearch

  Language:JavaScript7.6k858

• streamlit/streamlit

  Streamlit — A faster way to build and share data apps.

  Language:Python36.5k3.1k

• glample/fastBPE

  Fast BPE

  Language:C++65898