andrewyu0

obsidian copilot

your notes = your lifelong ai companion + intelligence augmentation

COMMENTS VERY WELCOME! this is a first pass to put these ideas in one place

tldr - combine obsidian + openinterpreter to create a bespoke pkm copilot experience. if you follow the "file over app" philosophy, this combination can be your lifetime AI companion

chuyqa

truebit

local spaces = require("hs.spaces") -- https://github.com/asmagill/hs._asm.spaces

-- Switch kitty
hs.hotkey.bind({'command'}, 'escape', function () -- change your own hotkey combo here, available keys could be found here:https://www.hammerspoon.org/docs/hs.hotkey.html#bind
  local BUNDLE_ID = 'net.kovidgoyal.kitty' -- more accurate to avoid mismatching on browser titles

  function getMainWindow(app)
    -- get main window from app
    local win = nil
    while win == nil do

lewtun

# This is a modified version of TRL's `SFTTrainer` example (https://github.com/huggingface/trl/blob/main/examples/scripts/sft_trainer.py), 
# adapted to run with DeepSpeed ZeRO-3 and Mistral-7B-V1.0. The settings below were run on 1 node of 8 x A100 (80GB) GPUs.
#
# Usage:
#   - Install the latest transformers & accelerate versions: `pip install -U transformers accelerate`
#   - Install deepspeed: `pip install deepspeed==0.9.5`
#   - Install TRL from main: pip install git+https://github.com/huggingface/trl.git
#   - Clone the repo: git clone github.com/huggingface/trl.git
#   - Copy this Gist into trl/examples/scripts
#   - Run from root of trl repo with: accelerate launch --config_file=examples/accelerate_configs/deepspeed_zero3.yaml --gradient_accumulation_steps 8 examples/scripts/sft_trainer.py  

Birch-san

Install HF Code Autocomplete VSCode plugin.

We are not going to set an API token. We are going to specify an API endpoint.
We will try to deploy that API ourselves, to use our own GPU to provide the code assistance.

We will use bigcode/starcoder, a 15.5B param model.
We will use NF4 4-bit quantization to fit this into 10787MiB VRAM.
It would require 23767MiB VRAM unquantized. (still fits on a 4090, which has 24564MiB)!

Setup API

perkinsjr

import { getAuth, withClerkMiddleware } from "@clerk/nextjs/server";
import { NextResponse, NextFetchEvent } from "next/server";
import type { NextRequest } from "next/server";
import { Ratelimit } from "@upstash/ratelimit";
import { Redis } from "@upstash/redis";

// Add public paths for Clerk to handle.
const publicPaths = ["/", "/sign-in*", "/sign-up*", "/api/blocked"];

// set your rate limit.

virattt

RafalWilinski

const awsTool = new DynamicTool({
  name: "aws-cli",
  description:
    "This is AWS CLI. You can call this to send commands to the AWS Cloud. Use AWS CLI format like `aws s3api list-buckets`",
  async func(command) {
    const args = command.split(" ").filter((x) => x !== "aws");
    const result = spawnSync("aws", args, {
      env: {
        ...process.env,
        AWS_REGION: "eu-central-1",

rain-1

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

coolaj86

Chat GPT "DAN" (and other "Jailbreaks")

• https://chat.openai.com/
• Is ChatGPT "DAN" Real? Gonna find out [Part 1]
  (https://www.youtube.com/watch?v=-q8woRG9FrI)
• Part 2: I thought ChatGPT DAN was a hoax, but...
  (https://www.youtube.com/watch?v=rHZRrDu3A2U&lc=UgxfrxX8aK7gnCzkend4AaABAg)