jong-inn

guardrails

Adding guardrails to large language models.

Conference-Acceptance-Rate

Acceptance rates for the major AI conferences

PyMuPDF

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

ArxivPapers

Code behind Arxiv Papers

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

website

mm-github-pages-starter

Minimal Mistakes GitHub Pages site starter.

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

alpagasus

Unofficial implementation of AlpaGasus

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

minimal-mistakes

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

sec-parser

Parse SEC EDGAR HTML documents into a tree of elements that correspond to the visual (semantic) structure of the document.

pandoc-mm

Generate a mindmap from an org-mode file. Complete with annotations.

MindGeniusAI

Auto generate MindMap with ChatGPT

data_cube_ui

Data Cube user interface allowing users to interact with the Data Cube and run sample analysis cases

ydata-synthetic

Synthetic data generators for tabular and time-series data

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

summvis

SummVis is an interactive visualization tool for text summarization.

ddia-references

Literature references for “Designing Data-Intensive Applications”

rags

Build ChatGPT over your data, all with natural language

UltraFastBERT

The repository for the code of the UltraFastBERT paper

cobbler

Code and data for Koo et al's ACL 2024 paper "Benchmarking Cognitive Biases in Large Language Models as Evaluators"

instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

flask-login

Flask user session management.

flask-cors

Cross Origin Resource Sharing ( CORS ) support for Flask

reward-system

Code for Koo and Martin et al's in2writing paper on "Decoding the End-to-end Writing Trajectory in Scholarly Manuscripts"