Gavin Schulz gsmaverick

## chat
#!/bin/bash
TOKEN=< OpenAI token from https://platform.openai.com/account/api-keys >
PROMPT="You are the best at writing shell commands. Assume the OS is Ubuntu. I want you to respond with only the shell commands separated by semicolons and no commentary. Here is what I want to do: $@"
RESULT=`curl -s https://api.openai.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $TOKEN" \
  -d "{
  \"model\": \"gpt-3.5-turbo\",
  \"messages\": [{\"role\": \"user\", \"content\": \"$PROMPT\"}]
}" | jq '.choices[] | .message.content' -r`

## llama-7b-m1.md

      
              1 file
            
          
              20 forks
            
          
              15 comments
            
          
              117 stars
            
          
                cedrickchee
                / llama-7b-m1.md
            
            
              Last active
              April 25, 2024 04:54
            
              
                4 Steps in Running LLaMA-7B on a M1 MacBook with `llama.cpp`
              
          
    4 Steps in Running LLaMA-7B on a M1 MacBook

The large language models usability

The problem with large language models is that you can’t run these locally on your laptop. Thanks to Georgi Gerganov and his llama.cpp project, it is now possible to run Meta’s LLaMA on a single computer without a dedicated GPU.
Running LLaMA

There are multiple steps involved in running LLaMA locally on a M1 Mac after downloading the model weights.

  
## register_social_accounts.py
# This is based on https://gist.github.com/getup8/7862fd86f8e48781587490f25417d7b9

from allauth.socialaccount.models import SocialApp
from django.conf import settings
from django.core.management.base import BaseCommand


class Command(BaseCommand):
    help = 'Updates the allauth SocialApps registered in the database based on the ' \
           'SOCIALACCOUNT_PROVIDERS setting'

## load_social_accounts.py
from django.conf import settings
from django.core.management.base import BaseCommand, CommandError

from allauth.socialaccount.models import SocialApp


class Command(BaseCommand):
    help = 'Loads allauth SocialApp settings into database'

    def handle(self, *args, **options):

## gist:4247000
<!DOCTYPE html>
<html>
<head>
  <title>iOS6 Safari Photo Capture Demo</title>

  <script type="text/javascript">
    window.onload = function() {
      var input = document.getElementById("input");
      input.addEventListener("change", handleFile);
    }

## middleware.py
from django import http

try:
    from django.conf import settings
    XS_SHARING_ALLOWED_ORIGINS = settings.XS_SHARING_ALLOWED_ORIGINS
    XS_SHARING_ALLOWED_METHODS = settings.XS_SHARING_ALLOWED_METHODS
    XS_SHARING_ALLOWED_HEADERS = settings.XS_SHARING_ALLOWED_HEADERS
    XS_SHARING_ALLOWED_CREDENTIALS = settings.XS_SHARING_ALLOWED_CREDENTIALS
except AttributeError:
    XS_SHARING_ALLOWED_ORIGINS = '*'
	#!/bin/bash
	TOKEN=< OpenAI token from https://platform.openai.com/account/api-keys >
	PROMPT="You are the best at writing shell commands. Assume the OS is Ubuntu. I want you to respond with only the shell commands separated by semicolons and no commentary. Here is what I want to do: $@"
	RESULT=`curl -s https://api.openai.com/v1/chat/completions \
	-H 'Content-Type: application/json' \
	-H "Authorization: Bearer $TOKEN" \
	-d "{
	\"model\": \"gpt-3.5-turbo\",
	\"messages\": [{\"role\": \"user\", \"content\": \"$PROMPT\"}]
	}" \| jq '.choices[] \| .message.content' -r`
	# This is based on https://gist.github.com/getup8/7862fd86f8e48781587490f25417d7b9

	from allauth.socialaccount.models import SocialApp
	from django.conf import settings
	from django.core.management.base import BaseCommand


	class Command(BaseCommand):
	help = 'Updates the allauth SocialApps registered in the database based on the ' \
	'SOCIALACCOUNT_PROVIDERS setting'
	<!DOCTYPE html>
	<html>
	<head>
	<title>iOS6 Safari Photo Capture Demo</title>

	<script type="text/javascript">
	window.onload = function() {
	var input = document.getElementById("input");
	input.addEventListener("change", handleFile);
	}
	from django import http

	try:
	from django.conf import settings
	XS_SHARING_ALLOWED_ORIGINS = settings.XS_SHARING_ALLOWED_ORIGINS
	XS_SHARING_ALLOWED_METHODS = settings.XS_SHARING_ALLOWED_METHODS
	XS_SHARING_ALLOWED_HEADERS = settings.XS_SHARING_ALLOWED_HEADERS
	XS_SHARING_ALLOWED_CREDENTIALS = settings.XS_SHARING_ALLOWED_CREDENTIALS
	except AttributeError:
	XS_SHARING_ALLOWED_ORIGINS = '*'