-
Samsung Research
- Seoul, Korea
- https://becxer.github.io
Highlights
- Pro
Stars
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
✨✨Latest Advances on Multimodal Large Language Models
High-speed download of LLaMA, Facebook's 65B parameter GPT model
Research code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"
artmatsak / cnn-dailymail
Forked from becxer/cnn-dailymailCode to obtain the CNN / Daily Mail dataset (non-anonymized) for summarization (Python3)
Google Research
XLNet: Generalized Autoregressive Pretraining for Language Understanding
TensorFlow code and pre-trained models for BERT
micro-implementation of tensorflow-like utilities
A curated list of resources for NLP (Natural Language Processing) for Korean
A TensorFlow implementation of the Differentiable Neural Computer.
Datasets for Question Answering by Search and Reading
Code for the TriviaQA reading comprehension dataset
Reading Wikipedia to Answer Open-Domain Questions
End-To-End Memory Networks for bAbI question-answering tasks
Sequence to sequence learning using TensorFlow.
Models, data loaders and abstractions for language processing, powered by PyTorch
Deep Learning / NLP tutorial for Chatbot Developers
TensorFlow-based neural network library
Tutorials for TensorFlow APIs the official documentation doesn't cover
Dynamic seq2seq in TensorFlow, step by step