cedrickchee

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.

rajkrrsingh

Prerequisite hive settings:

set hive.server2.logging.operation.level=execution;
set hive.metastore.transactional.event.listeners=org.apache.hive.hcatalog.listener.DbNotificationListener;
set hive.metastore.dml.events=true;

Setup database and tables

vvalorous

package main

import (
	"fmt"
	"sort"

	"github.com/aws/aws-sdk-go/aws"
	"github.com/aws/aws-sdk-go/aws/session"
	"github.com/aws/aws-sdk-go/service/ec2"
	"github.com/aws/aws-sdk-go/service/ec2/ec2iface"

brbarnett

{
   "Name":"AKS Cluster Configuration Reader",
   "Id":"{{ create a unique guid }}",
   "IsCustom":true,
   "Description":"Can get AKS configuration.",
   "Actions":[
      "Microsoft.ContainerService/managedClusters/accessProfiles/listCredential/action",
      "Microsoft.ContainerService/managedClusters/listClusterUserCredential/action"
   ],
   "NotActions":[

stavxyz

package main

import (
	"fmt"
	"sort"

	"github.com/aws/aws-sdk-go/aws"
	"github.com/aws/aws-sdk-go/aws/session"
	"github.com/aws/aws-sdk-go/service/ec2"
	"github.com/aws/aws-sdk-go/service/ec2/ec2iface"

prasanthj

Notes to make IR shield (made by LinkSprite) work in Raspberry Pi 3 (bought from Amazon [1]). 
The vendor has some documentation [2] but that is not complete and sufficient for Raspbian Stretch. 
Following are the changes that I made to make it work.

$ sudo apt-get update
$ sudo apt-get install lirc

# Add the following lines to /etc/modules file
lirc_dev
lirc_rpi gpio_in_pin=18 gpio_out_pin=17

t3rmin4t0r

import sys, re, math, os
from xml.dom.minidom import parse
from collections import namedtuple

Sample = namedtuple("Sample", ['query', 'duration', 'success', 'end', 'start', 'user']) 

RUN_NUM = re.compile(r'(?P<query>.*\.sql)(_(?P<run>[0-9]*))?')
def runid(q):
	m = RUN_NUM.match(q)
	return (m.group('query'), int(m.group('run')))

timvlaer

brew unlink thrift
brew install https://raw.githubusercontent.com/Homebrew/homebrew-core/9d524e4850651cfedd64bc0740f1379b533f607d/Formula/thrift.rb

t3rmin4t0r

import re, sys
NX = True
try:
	import networkx as nx
except:
	NX = False 
	sys.stderr.write("Could not import nx\npip install networkx, please\n")

plan39 = """
        Map 1 <- Map 5 (BROADCAST_EDGE), Map 6 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE)

Lazin

from __future__ import print_function

import ctypes
import random
import itertools

class Bits:

    @staticmethod
    def float2bin(f):