chiragjn

sentry_structlog_experiments

Sample django app - Make log events from structlog similar to log events from logging for Sentry

torchserve-t5-translation

Example T5 deployment with torchserve

bert

TensorFlow code and pre-trained models for BERT

chiragjn

About me

ecco

Visualize and explore NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2).

gitbook-experiments

gnostic

A compiler for APIs described by the OpenAPI Specification with plugins for code generation and other API support tasks.

google-search-shortcuts

Use the number row on the keyboard to quickly open a search result

human_id

Human readable IDs, in Python

nlpaug

Data augmentation for NLP

rusty_competitive

Trying competitive programming with Rust

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

small_bert_tf2hft

Scripts that convert small bert checkpoints to transformers lib format

spello

Fast and accurate spell correction library

structlog-sentry

Sentry integration for structlog

torch-1.8.1-reproducibility-bug

truefoundry-nlp-demo

zenml

ZenML 🙏: Build portable, production-ready MLOps pipelines. https://zenml.io.

axolotl

Go ahead and axolotl questions

bottlerocket

An operating system designed for hosting containers

bullshit.js

A bookmarklet for translating marketing speak into human-readable text. :poop:

deepdoctection

A Repo For Document AI

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

experiments

Just a mono-repo for temp stuff

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

flash-attention

Fast and memory-efficient exact attention

kohya_ss

nvidia-container-toolkit

Build and run containers leveraging NVIDIA GPUs

text-generation-inference

Large Language Model Text Generation Inference

vllm

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