thistleknot

import torch
import torch.nn.functional as F
from transformers import GPTNeoForCausalLM, AutoTokenizer
from datasets import load_dataset
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
import random

# Parameters

thistleknot

#https://www.kaggle.com/code/samuelcortinhas/mnist-dataset-distillation
# Core
import numpy as np
np.random.seed(0)
import pandas as pd
import seaborn as sns
sns.set(style='darkgrid', font_scale=1.4)
import matplotlib.pyplot as plt
%matplotlib inline
import time

thistleknot

import pandas as pd

# Step 1: Read and parse the input file
parsed_data = []
with open('output.txt', 'r') as file:  # Replace 'output.txt' with your file path
    for line in file:
        if line.strip():  # Skip empty lines
            first_colon_index = line.find(':')
            if first_colon_index != -1:
                filepath = line[:first_colon_index].strip()

thistleknot

#!/usr/bin/env python
# coding: utf-8

import lade
from transformers import AutoTokenizer, AutoModel
import torch
lade.augment_all()
lade.config_lade(LEVEL=5, WINDOW_SIZE=7, GUESS_SET_SIZE=7, DEBUG=0)
from datasets import load_dataset
from torch.utils.tensorboard import SummaryWriter

thistleknot

# Revised Tree of Thought Template

## Problem Identification
- **Problem:** Clearly define the problem or decision that needs to be addressed.

## Idea Generation and Processing
- **Preparation:**
  - Define the context and constraints of the problem.
  - Generate probable ideas for addressing the problem.
    1. example idea

thistleknot

Problem: 2, 3, 1, 5
EXECUTION
    Prep
    Length of the list: 4
    Number of consecutive pairs: 3
    a=[2 3 1 5]
    set n_swaps=0
    EndPrep
    Iteration:
        set swap_flag=false. The state is:

thistleknot

from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import BitsAndBytesConfig
import torch

nf4_config = BitsAndBytesConfig(
   load_in_4bit=True,
   bnb_4bit_quant_type="nf4",
   bnb_4bit_use_double_quant=True,
   bnb_4bit_compute_dtype=torch.bfloat16
)

thistleknot

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import KFold
from sklearn.model_selection import KFold
from sklearn.metrics import mean_squared_error
import numpy as np
import pandas as pd
from sklearn.metrics import mean_squared_error
from graphviz import Source

thistleknot

from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
from transformers import AutoTokenizer

pretrained_model_dir = "/home/user/text-generation-webui/models/open_llama_3b_v2/"
quantized_model_dir = "/home/user/text-generation-webui/models/open_llama_3b_v2_qptq/"
quantize_config = BaseQuantizeConfig(
bits=4,  # quantize model to 4-bit
group_size=32,  # it is recommended to set the value to 128
desc_act=False,  # set to False can significantly speed up inference but the perplexity may slightly bad
)

thistleknot

# Since we don't have internet access in this environment, I'll replicate a similar workflow.
# Let's assume the 'data' is a pandas DataFrame obtained from the CSV file.

# For the example, let's create a simulated 'Poverty' column with random data

data_ = pd.read_csv("https://raw.githubusercontent.com/thistleknot/Python-Stock/master/data/raw/states.csv?token=GHSAT0AAAAAACIYSECGQETPAPO6K4QYIFV6ZKDCJIQ").set_index('States')
for c in data_.columns:
    print(c)
    data = data_[[c]]