Create app.py

app.py

@@ -0,0 +1,112 @@
+# -*- coding: utf-8 -*-
+"""LLM.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1AbtqagXl-cWKhXqd5z_uxZ2_JiCI4e6q
+"""
+
+#  Step 1: Setup
+# pip install transformers
+# pip install datasets
+
+# !pip install transformers[torch]
+
+# !pip install transformers --upgrade
+# !pip install accelerate --upgrade
+
+import transformers
+import accelerate
+print("Transformers version:", transformers.__version__)
+print("Accelerate version:", accelerate.__version__)
+
+# Step 2: Mount Google Drive to access your data
+from google.colab import drive
+drive.mount('/content/drive')
+
+# Step 2: Import necessary libraries
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments
+from datasets import load_dataset
+from datasets import set_caching_enabled
+set_caching_enabled(False)
+
+from datasets import load_dataset
+
+# Replace 'path_to_your_text_file.txt' with the actual path of your text file in Google Drive
+dataset = load_dataset('text', data_files={'train': '/content/drive/My Drive/Ethics.txt'})
+
+# Split the 'train' dataset into training and validation sets
+train_size = int(len(dataset['train']) * 0.9)
+train_dataset = dataset['train'].select(list(range(train_size)))
+validation_dataset = dataset['train'].select(list(range(train_size, len(dataset['train']))))
+
+print("Train dataset size:", len(train_dataset))
+print("Validation dataset size:", len(validation_dataset))
+
+# Step 4: Tokenization
+from transformers import GPT2Tokenizer
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+
+def tokenize_function(examples):
+    return tokenizer(examples["text"])
+
+# Tokenize the dataset with a reduced number of workers
+tokenized_dataset = dataset.map(
+    tokenize_function,
+    batched=True,
+    num_proc=1  # Set the number of workers to 1
+)
+
+# !pip install gpt-2-simple
+
+import gpt_2_simple as gpt2
+
+# !pip install accelerate>=0.20.1
+# !pip install accelerate -U
+
+# Step 5: Model Preparation
+from transformers import GPT2LMHeadModel
+model = GPT2LMHeadModel.from_pretrained('gpt2')
+
+# Step 6: Training
+from transformers import TrainingArguments,Trainer
+training_args = TrainingArguments(
+    output_dir="./results",
+    overwrite_output_dir=True,
+    num_train_epochs=3,
+    per_device_train_batch_size=1,
+    save_steps=10_000,
+    save_total_limit=2,
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=train_dataset,
+    eval_dataset=validation_dataset,
+)
+
+# Step 9: Save the Model
+model.save_pretrained("fine_tuned_model")
+
+# !pip install xformers
+
+# # Step 7: Testing
+# from transformers import pipeline
+# generator = pipeline('text-generation', model=model)
+# result = generator('My custom model says,')[0]
+# print(result['generated_text'])
+# Step 7: Testing
+from transformers import pipeline, GPT2Tokenizer
+
+# Create a tokenizer for your GPT-2 model
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2')  # You might need to adjust the model name
+
+# Create a text generation pipeline
+generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
+
+# Generate text using the pipeline
+result = generator('My custom model says,')[0]
+print(result['generated_text'])