Sergey Zuev's repositories
ai-llm.github.io
LLM and AI thoughts and experiments
asv-drones
Open source implementation of ground control station application for ArduPilot and PX4 autopilot
Awesome-LLM
Awesome-LLM: a curated list of Large Language Model
awesome-llm-powered-agent
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
calendar
A simple printable calendar with the full year on a single page
chain-of-density
Implementing the Chain Of Density text summarisation technique from recent NLP research by researchers at Salesforce, MIT, Columbia, etc. Takes a long text input and iteratively generates increasingly concise, entity-dense summaries using LLMs (default: OpenAI's GPT-4). Feedback and contributions welcome!
DeepSeek-Coder
DeepSeek Coder: Let the Code Write Itself
enex2md
A Python command-line utility to convert enex-files to Markdown
evernote2md
Convert Evernote .enex files to Markdown
evo
DNA foundation modeling from molecular to genome scale
finetuning
Finetune Llama-3-8b on the MathInstruct dataset
gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topic
graph-of-thoughts
Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
Intelligent-Liquidity-Provisioning-Framework-V1
Reinforcement learning based framework to optimize liquidity provisioning in Uniswap V3
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
NerdMiner_v2
Improved version of first ESP32 NerdMiner
neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
obsidian-git
Backup your Obsidian.md vault with git
OpenDevin
🐚 OpenDevin: Code Less, Make More
OpenHRV
Heart rate variability (HRV) biofeedback with Polar ECG chest straps.
puppeteer-extra
💯 Teach puppeteer new tricks through plugins.
RouteLLM
A framework for serving and evaluating LLM routers.
simple-pid
A simple and easy to use PID controller in Python
statsforecast
Lightning ⚡️ fast forecasting with statistical and econometric models.
storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.
tg2obsidian
This script pulls new messages from a Telegram group and puts them into Obsidian vault on a local machine
time-series-analysis
Collection of notebooks for time series analysis