ML Pipeline
February 1, 2026

My vision for this design, is that it would be used by teams for discussing the model design, code reviews and critique, and planning project needs.
This design could potentially assist Project managers, Data Scientists and any involved team members` `

December 18, 2025
Install

!pip install
-transformers
-torch
-peft
-accelerate
-bitsandbytes

Import

from transformers import pipeline

pipe = pipeline(“sentiment-analysis”)
print(pipe(“Using transformers”))

import pandas as pd
from datasets import Dataset

Data Prep

# Mount the drive to CSV
from google.colab import drive
drive.mount(‘/content/drive’)

# Create a pandas DataFrame from the dictionary
df = pd.read_csv(“/content/drive/MyDrive/Flan_Read/guitarhistory.csv”)

# Convert the pandas DataFrame to a Hugging Face Dataset object
dataset = Dataset.from_pandas(df)

# Print the dataset to confirm it’s been created correctly
print(dataset)

# View dataframe
df# Print the dataset to confirm it’s been created correctly
print(dataset)

# View dataframe
df

Load Model

PEFT

Preprocessing

Training

Evaluation

Inference

December 10 2025

Draft One of the Reading Activity Language Model
This is a screenshot of the Process Map in production.
Here you’ll see I’m refining some the major steps in visual representation of key steps in producing this LLM

LLM Process Sample 1

Here is a close up of one of the steps for defining the type of additional model to load into the current model I’m building. This is called T5 Flan, like the flan cake, hence, the green short cylinder icon

LLM Process Map Closeup


On the image below, Left side we see the parameters for what is known as Parameter-Efficient Fine-Tuning (PEFT) . A step used in building a more energy and cost efficient Language Model. This block of code will be used every time a new set of data is brought in to retrain the model. This is in a .csv format. For example: building this knowledge base on guitar history. The first build was run and tested and now will be updated with new historical information and a new .csv file from the collaboration of a historian, a musician, and a programmer or tech savvy individual.

PEFT Closeup