jph00

conda install cuda -c nvidia/label/cuda-12.1.0
conda install 'pytorch>2.0.1' torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
conda install scipy matplotlib pandas notebook

jph00

import torch, time, os, safetensors
from torch import nn

from peft import get_peft_model, LoraConfig, TaskType
from bitsandbytes.nn import Linear4bit, Linear8bitLt

from transformers import AutoTokenizer, LlamaForCausalLM, AutoConfig, LlamaPreTrainedModel, BitsAndBytesConfig
from transformers.utils import hub, WEIGHTS_INDEX_NAME, SAFE_WEIGHTS_INDEX_NAME

from transformers.integrations.bitsandbytes import replace_with_bnb_linear

jph00

from bitsandbytes.nn.modules import Linear8bitLt, Linear4bit
from contextlib import contextmanager

def noop (x=None, *args, **kwargs):
    "Do nothing"
    return x

@contextmanager
def no_kaiming():
    old_iku = init.kaiming_uniform_

jph00

import torch
from datasets import load_dataset
import argparse
import os
import math
from itertools import chain
from datetime import timedelta
from torch.utils.data import DataLoader
from accelerate import Accelerator
from accelerate.utils import (DummyOptim, DummyScheduler,

jph00

Bing Chat at 2023-3-26 13:47:19

1

Q: Bing AI

2

Q: Some philosophers and AI researchers have claimed that AI can not be sentient, or be AGI, due to lack of "embodiment" or "grounding". Could you please summarize these claims, and points for and against? Who are the main people on each side of this debate?

jph00

from datasets.tasks import ImageClassification
t = train.rename_columns({'image':'a', 'label':'b'})
t2 = t.prepare_for_task(ImageClassification(image_column='a', label_column='b'))
t2.features

jph00

#!/usr/bin/env bash
for f in $(<~/git/repos); do
  cd ~/git/$f
  git pull > /dev/null &
  cd - > /dev/null
done

wait < <(jobs -p)

for f in $(<~/git/repos); do

jph00

name: Quarto Publish
on:
  workflow_dispatch:
  push: { branches: master }
jobs:
  build-deploy:
    runs-on: ubuntu-latest
    permissions: {contents: write}
    steps:
      - uses: actions/checkout@v2

jph00

jph00

model_name,learning_rate,pool,dataset,GPU_mem,error_rate,valid_loss,train_loss,fit_time
efficientnetv2_rw_t,0.0001,concat,pets,2.3203125,0.18335586786270142,0.5982086062431335,0.99508398771286,135.1381552380044
efficientnetv2_rw_s,0.0001,concat,pets,3.146484375,0.1779431700706482,0.5593751072883606,0.8270677328109741,145.79841202299576
efficientnetv2_rw_m,0.0001,concat,pets,5.56640625,0.15899866819381714,0.5119925141334534,0.7437679171562195,214.4970937330509
efficientnet_lite0,0.0001,concat,pets,1.51953125,0.19418132305145264,0.6388306021690369,1.144728422164917,67.13226824696176
efficientnet_es_pruned,0.0001,concat,pets,1.53515625,0.1637347936630249,0.5296803712844849,0.9239290952682496,69.60124204796739
efficientnet_es,0.0001,concat,pets,1.53515625,0.1400541067123413,0.44839274883270264,0.8084487915039062,72.84359885391314
efficientnet_b0,0.0001,concat,pets,1.666015625,0.19418132305145264,0.65826016664505,1.157211184501648,85.95306042104494
efficientnetv2_rw_t,0.0004,concat,pets,2.3203125,0.114343702793121