vahbuna

plot

A concise API for exploratory data visualization implementing a layered grammar of graphics

lm_vector_arithmetic

length-generalization

Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023

do-we-need-attention

BYOD

The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"

a1gpt

throwaway GPT inference

Rethinking-instruction-effectiveness

The codebase for our ACL2023 paper: Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning

DeepNLP-models-MindSpore

About MindSpore implementations of various Deep NLP models in cs-224n(Stanford Univ)

PythonNumericalDemos

Well-documented Python demonstrations for spatial data analytics, geostatistical and machine learning to support my courses.

GPTnum.py

gpt 2 with only numpy

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

neural-networks-from-scratch

An implementation of convolutional networks in NumPy!

llm

Access large language models from the command-line

talk

Let's make sand talk

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

dolma

Data and tools for generating and inspecting OLMo pre-training data.

seglearn

Python module for machine learning time series:

tslearn

The machine learning toolkit for time series analysis in Python

nolitsa

A Python module implementing some standard algorithms used in nonlinear time series analysis

Non-Linear-Time-Series-Analysis-Using-Machine-Learning-Time-Series-Analysis-and-Deep-Learning

Different models based on different techinques were built to check the forecasting accuracy on the training set

gpt-llm-trainer

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

LWM

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

llama2.rs

A fast llama2 decoder in pure Rust.

metavoice-src

Foundational model for human-like, expressive TTS

ml-mgie

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text