gvl610 raspiduino

About MemGPT's free endpoint

MemGPT provides you a free endpoint for trying. It's at https://inference.memgpt.ai/chat/completions From official docs it's claimed that the free endpoint is running on variants of Mixtral 8x7b:

MemGPT Free Endpoint: select this if you'd like to try MemGPT on a top open LLM for free (currently variants of Mixtral 8x7b!)

However, after I manually try running Mixtral 8x7b on my own machine, I saw that the model cannot be compared to the free endpoint in term of accuracy (function calling + response). This makes me want to find out the real model behind this endpoint.

TL;DR:

Free endpoint just forwards your call to OpenAI's ChatGPT 3.5. However, I cannot be sure if they log our requests or not.

Disclaimer

Me (@raspiduino/gvl610) DID NOT do any Process Explorer reverse engineer. This API had appeared multiple times on the Internet before I wrote this.
This API key is not intended for any uses outside of the Process Explorer program itself.
I takes absolutely NO responsibilities for any damage and/or problems that may occur when using this API.
DON'T ABUSE this API.

The API itself

Basic API is as following. You can use curlconverter to convert to any programming language you would like.

How to build QEMU ESP32 for Windows

QEMU ESP32 is a fork of QEMU with Espressif patches for emulating ESP32 microcontroller series. Normally there is prebuilt files in Releases tab, but for some reasons if you want to (or have to) build yourself, then you can follow this guide.

I would recommend Windows environment with MSYS2 for building this. This guide aims at building for x64 architecture, but probably you can do the same for x86 by replacing x86_64 packages with x86 ones.

Step 1: Install MSYS2.
Step 2: Open MSYS2 MINGW64 prompts.
Step 3: Install required packages

I recently have Armbian installed on my set-top box and its apt got crazy when I used it:

$ sudo apt install xfce4-terminal
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
The following additional packages will be installed:
  libvte-2.91-0 libvte-2.91-common
The following NEW packages will be installed:

	D:\dev>git clone --recursive https://github.com/mapillary/OpenSfM
	D:\dev>cd OpenSfM
	D:\dev\OpenSfM>git clone https://github.com/microsoft/vcpkg
	Cloning into 'vcpkg'...
	remote: Enumerating objects: 247401, done.
	remote: Counting objects: 100% (59827/59827), done.
	remote: Compressing objects: 100% (4389/4389), done.
	remote: Total 247401 (delta 55699), reused 55438 (delta 55438), pack-reused 187574 (from 1)
	Receiving objects: 100% (247401/247401), 75.41 MiB \| 10.16 MiB/s, done.
	Resolving deltas: 100% (164296/164296), done.

	# Import
	import cv2
	from deepsparse.pipeline import Pipeline
	from deepsparse.yolo.schemas import YOLOInput
	from deepsparse.yolo.utils import COCO_CLASSES
	import time

	# Model settings
	task = "yolo"
	model_path = "zoo:yolov5-l-coco-pruned.4block_quantized"

	# Install required Termux packages
	apt update
	apt install openssh openssl openssl-1.1 proot-distro

	# Setup ssh (optional)
	passwd # Type your password here
	whoami # Get your username
	ifconfig # Get your IP

	# Add openssl-1.1 library to path (otherwise curl and other programs won't work)

	<!DOCTYPE html>
	<html>
	<head>
	<meta charset="utf-8">
	<title></title>
	<script>
	var uniqueId = 0;function genUniqueKeyframeName(){return"seq-"+uniqueId++}var uniqueId=0,SceneItem=function(n,t,i,r,u){n.style.visibility="visible";this.keyframe_sequence=u;this.element=n;this.animation_name=t;this.animation_duration=r;this.keyframes="@-ms-keyframes "+t+" {"+i+"}"},KeyframeSequencer=function(n){this._created_keyframes=[];this.container_element=n;this._sequences=[];var t=document.createElement("style");document.head.appendChild(t);this.stylesheet=t.sheet},ScenesManager;KeyframeSequencer.prototype.addSequence=function(n,t,i,r){var u={},e,s,f,o,h,c;for(u.element=n,u.keyframe_name=genUniqueKeyframeName(),u.keyframe_style_str="@-ms-keyframes "+u.keyframe_name+" {",e=0,f=0;f<t.length;f++)o=t[f].duration,e+=o;for(s=0,f=0;f<t.length;f++)o=t[f].duration,s+=o,h=s/e*100+"%",c=t[f].properties,u.keyframe_style_str+=h+"{"+c+"}";u.keyframe_style_str+="}";u.delay=i;u.duration=e+"s";u.fill_mode=r\|\|"both";this._sequences.push(u)};Key

	#include <filesystem>
	#include <string>
	#include <iostream>
	#include <regex>

	namespace fs = std::filesystem;

	int main() {
	fs::path p = "e:\\abc\\xyz.txt";
	std::string s = p.string();