vechtomov Goto Github PK

agentbench

A Comprehensive Benchmark to Evaluate LLMs as Agents

alphacodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

annunciator

Приложение для уведомления о событиях в сообщениях вк.

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

autogen

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

bitsandbytes

8-bit CUDA functions for PyTorch

chat-langchain-telegram

Telegram ChatGPT bot

dom-q-net

Graph-based Deep Q Network for Web Navigation

flash-attention

Fast and memory-efficient exact attention

glados

Personality Core

langchain-assistant

Interact with LLM's (GPT-3, GPT-3.5, GPT-4) via messenger apps like Telegram, Whatsapp and Facebook Messenger

langchainjs

leetcode

llama-cpp-python

Python bindings for llama.cpp

llama.cpp

Port of Facebook's LLaMA model in C/C++

llama2.c

Inference Llama 2 in one file of pure C

localai

:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs ggml, gguf, GPTQ, onnx, TF compatible models: llama, llama2, rwkv, whisper, vicuna, koala, cerebras, falcon, dolly, starcoder, and many others

memgpt

Teaching LLMs memory management for unbounded context 📚🦙

montyhallparadox

Проект включает себя консольное и веб приложения для проверки парадокса Монти Холла

open-assistant

open-interpreter

OpenAI's Code Interpreter in your terminal, running locally

planercnn

PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image

robomaster-sdk

DJI RoboMaster Python SDK and Sample Code for RoboMaster EP.

stable-diffusion

stepik-algorithms-course

stepik-data-structures-course

stepik-dl-nlp

Материалы мини-курса на Stepik "Нейронные сети и обработка текста"

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.

talk-llama-fast

Port of OpenAI's Whisper model in C/C++ with xtts and wav2lip

tampermonkey-scripts

Tampemonkey advertisement blocking scripts