karpathy

"""
stable diffusion dreaming
creates hypnotic moving videos by smoothly walking randomly through the sample space

example way to run this script:

$ python stablediffusionwalk.py --prompt "blueberry spaghetti" --name blueberry

to stitch together the images, e.g.:
$ ffmpeg -r 10 -f image2 -s 512x512 -i blueberry/frame%06d.jpg -vcodec libx264 -crf 10 -pix_fmt yuv420p blueberry.mp4

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)

wiseman

from io import StringIO
import sys
from typing import Dict, Optional

from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents.tools import Tool
from langchain.llms import OpenAI

danielgross

import requests
import time
import os
import sys
import openai
import tiktoken
from termcolor import colored

openai.api_key = open(os.path.expanduser('~/.openai')).read().strip()

rain-1

This worked on 14/May/23. The instructions will probably require updating in the future.

llama is a text prediction model similar to GPT-2, and the version of GPT-3 that has not been fine tuned yet. It is also possible to run fine tuned versions (like alpaca or vicuna with this. I think. Those versions are more focused on answering questions)

Note: I have been told that this does not support multiple GPUs. It can only use a single GPU.

It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.

• Clone llama.cpp from git, I am on commit 08737ef720f0510c7ec2aa84d7f70c691073c35d.

adrienbrault

# Clone llama.cpp
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp

# Build it
make clean
LLAMA_METAL=1 make

# Download model
export MODEL=llama-2-13b-chat.ggmlv3.q4_0.bin

jondurbin

Details on how the airoboros-gpt4-2.0 dataset was created.

Script

https://github.com/jondurbin/airoboros

pip install --upgrade airoboros==2.0.13

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

Birch-san

from transformers import (
  AutoConfig,
  AutoTokenizer,
  BitsAndBytesConfig,
  GenerationConfig,
  AutoModelForCausalLM,
  LlamaTokenizerFast,
  PreTrainedModel,
  TextIteratorStreamer,
  StoppingCriteria,

atiorh

# !pip install transformers sentencepiece

import torch
import torch.nn as nn
torch.set_grad_enabled(False)

from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.activations import ReLUSquaredActivation

from collections import defaultdict, OrderedDict