File size: 1,557 Bytes
61794f8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
# File 1: Model Repo Code (train.py)
# This file contains steps 1 to 4
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForQuestionAnswering, TrainingArguments, Trainer
# Step 1: Load the Dataset
dataset = load_dataset("squad")
# Step 2: Preprocess the Dataset
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
def preprocess_function(examples):
return tokenizer(
examples["question"],
examples["context"],
truncation=True,
max_length=384,
stride=128,
return_overflowing_tokens=True,
padding="max_length"
)
tokenized_dataset = dataset.map(preprocess_function, batched=True)
# Step 3: Train the Model
model = AutoModelForQuestionAnswering.from_pretrained("bert-base-uncased")
training_args = TrainingArguments(
output_dir="./results",
evaluation_strategy="epoch",
learning_rate=3e-5,
per_device_train_batch_size=16,
num_train_epochs=3,
weight_decay=0.01,
push_to_hub=True, # Automatically push to the Hugging Face Hub
hub_model_id="username/qa_model_repo" # Replace with your username and model repo name
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_dataset["train"],
eval_dataset=tokenized_dataset["validation"],
)
trainer.train()
# Step 4: Push the Model and Tokenizer to Hugging Face Hub
model.push_to_hub("username/qa_model_repo")
tokenizer.push_to_hub("username/qa_model_repo")
print("Model and tokenizer pushed to Hugging Face Hub successfully!")
|