gsajko

open_lm

A repository for research on medium sized language models.

InternLM

Official release of InternLM2.5 base and chat models. 1M context support

tweety

Twitter Scraper

Sensei

Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI

n-levels-of-rag

autofinetune

auto fine tune of models with synthetic data

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

nanotron

Minimalistic large language model 3D-parallelism training

instructor

structured outputs for llms

LUISE

LUI: Autonomous Collective Decision Making via Large Language Models

lance

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, with more integrations coming..

lex-gpt

data-engineering-zoomcamp

Free Data Engineering course!

spchengine

Scripts to create a basic search on podcast data in general

you-dont-need-a-bigger-boat

An end-to-end implementation of intent prediction with Metaflow and other cool tools

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

whisper-nextjs

Next.js app for serverless deployments of OpenAI Whisper on Banana.dev

rusty

AI-powered CLI tool to help you remember bash commands.

data-engineering

Construct a modern data stack and orchestration the workflows to create high quality data for analytics and ML applications.

obsidian-tweet-to-markdown

An Obsidian.md plugin to save tweets as Markdown files.

de4ml

Supporting materials/code examples for my course in data engineering for machine learning.

resume.github.com

Resumes generated using the GitHub informations

LoRaSystemForSoils

An underground, wireless, open-source, low-cost system for monitoring oxygen, temperature, and soil moisture

mlops-zoomcamp

Free MLOps course from DataTalks.Club

Furland

Building a real-time twitter graph of your friends

CodeGen

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

EcosystemCreatorRepo

Repo for Ecosystem Creator project based on Synthetic Silviculture Paper

math-as-code

a cheat-sheet for mathematical notation in code form

qgqa-flashcards

Question Generation - Question Answering for Automatic Flashcards

weywot

My notes on using Linux