Upload 8 files

Ruttoni_AI/pytorch_model.txt

@@ -0,0 +1 @@
+The model is avalable at: https://huggingface.co/lu2000luk/RuttoniAI/resolve/main/pytorch_model.bin

aka.py

@@ -0,0 +1,22 @@
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+import torch
+import colorama
+from colorama import Fore, Back, Style
+
+colorama.init()
+
+# Load the trained model for inference
+model = T5ForConditionalGeneration.from_pretrained("./Ruttoni_AI")
+tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
+
+# Generate a summary using the trained model
+def generate_summary(input_text):
+    input_ids = tokenizer.encode(input_text, return_tensors='pt')
+    outputs = model.generate(input_ids)
+    summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return summary
+
+# Example usage
+input_text = "Who is pesce beddo?"
+summary = generate_summary(input_text)
+print(Back.GREEN + "Answer: " + summary)

csv_preprocess.py

@@ -0,0 +1,10 @@
+import pandas as pd
+
+# Read the CSV file
+data = pd.read_csv('ruttoniaitrain1.csv')
+
+# Rename columns
+data = data.rename(columns={'Quest': 'text', 'Answer': 'target'})
+
+# Save the preprocessed data
+data.to_csv('ruttoniaitrain_preprocessed.csv', index=False)

train.py

@@ -0,0 +1,84 @@
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+from transformers import DataCollatorWithPadding
+from datasets import Dataset
+import pandas as pd
+import torch
+from sklearn.model_selection import train_test_split
+
+# Load the CSV file
+df = pd.read_csv("ruttoniaitrain1.csv")
+
+# Rename the columns
+df = df.rename(columns={"Quest": "text", "Answer": "target"})
+
+# Convert the DataFrame to a Hugging Face Dataset
+train_df, val_df = train_test_split(df, test_size=0.2, random_state=42)
+train_dataset = Dataset.from_pandas(train_df)
+val_dataset = Dataset.from_pandas(val_df)
+
+print("CSV Processed and loaded!")
+# Initialize the tokenizer and model
+tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
+model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-base")
+
+print("Model Loaded!")
+# Tokenize and format the data
+def preprocess_function(examples):
+    inputs = tokenizer(
+        examples['text'],
+        truncation=True,
+        padding='longest',
+        max_length=512
+    )
+    targets = tokenizer(
+        examples['target'],
+        truncation=True,
+        padding='longest',
+        max_length=32
+    )
+    
+    examples['input_ids'] = inputs['input_ids']
+    examples['attention_mask'] = inputs['attention_mask']
+    examples['labels'] = targets['input_ids']
+    
+    return examples
+
+train_dataset = train_dataset.map(preprocess_function, batched=True)
+
+training_args = {
+    'output_dir': './Ruttoni_AI',
+    'num_train_epochs': 3,
+    'per_device_train_batch_size': 4,
+    'save_steps': 500,
+    'save_total_limit': 2,
+    'logging_steps': 100,
+    'evaluation_strategy': 'steps',
+    'eval_steps': 500,
+    'logging_dir': './logs',
+    'overwrite_output_dir': True,
+    'warmup_steps': 500,
+    'learning_rate': 1e-4,
+    'report_to': 'none'
+}
+
+print("Arguments and functions initialized!")
+
+data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+from transformers import Trainer, TrainingArguments
+
+trainer = Trainer(
+    model=model,
+    args=TrainingArguments(**training_args),
+    data_collator=data_collator,
+    train_dataset=train_dataset,
+    eval_dataset=val_dataset,
+)
+
+print("Training...")
+
+trainer.train()
+
+print("Saving...")
+
+trainer.save_model("./Ruttoni_AI")