Akintunde Oladipo's repositories
anserini
Anserini is a Lucene toolkit for reproducible information retrieval research
anserini-tools
Evaluation tools shared across anserini, pyserini, and pygaggle
bbc_pidgin_scraper
A simple python scraper for BBC Pidgin News - https://www.bbc.com/pidgin
code
Example application code for the python architecture book
conversational-uptake
Code and data for the paper "Measuring Conversational Uptake: A Case-Study on Student-Teacher Interactions"
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
masakhane_xqa
Crosslingual Question Answering for African Languages
pygaggle
a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
pyserini
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
rank_llm
Borrows code from RankGPT repo to expand LLM reranking to other LLMs (Vicuna) and Prompt generation methods (LRL, etc)
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
t5-experiments
Tools and scripts for experimenting with Transformers: Bert, T5...
tevatron
Tevatron - A flexible toolkit for dense retrieval research and development.
text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.