Majdoddin

nlp

lexicaps

Transcription and Diarization based on OpenAI's Whisper

assessor

An assessor for Math provers

AlphaCodium

Adds function-level debugging to AlphaCodium, the official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

boolformer

gecko-dev

Read-only Git mirror of the Mercurial gecko repositories at https://hg.mozilla.org. How to contribute: https://firefox-source-docs.mozilla.org/contributing/contribution_quickref.html

llama2.c

Inference Llama 2 in one file of pure C

majdoddin.github.io

minbpe

Minimal, clean code for the Greedy Tokenization algorithm for LLM tokenization.

nanoGPT-1

The simplest, fastest repository for training/finetuning medium-sized GPTs.

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)