# Transformers installation
! pip install transformers datasets evaluate accelerate
# To install from source instead of the last release, comment the command above and uncomment the following one.
# ! pip install git+https://github.com/huggingface/transformers.git

from huggingface_hub import notebook_login

notebook_login()

from datasets import load_dataset

swag = load_dataset("swag", "regular")

swag["train"][0]

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")

ending_names = ["ending0", "ending1", "ending2", "ending3"]

def preprocess_function(examples):
    first_sentences = [[context] * 4 for context in examples["sent1"]]
    question_headers = examples["sent2"]
    second_sentences = [
        [f"{header} {examples[end][i]}" for end in ending_names] for i, header in enumerate(question_headers)
    ]

    first_sentences = sum(first_sentences, [])
    second_sentences = sum(second_sentences, [])

    tokenized_examples = tokenizer(first_sentences, second_sentences, truncation=True)
    return {k: [v[i : i + 4] for i in range(0, len(v), 4)] for k, v in tokenized_examples.items()}

tokenized_swag = swag.map(preprocess_function, batched=True)

from dataclasses import dataclass
from transformers.tokenization_utils_base import PreTrainedTokenizerBase, PaddingStrategy
from typing import Optional, Union
import torch

@dataclass
class DataCollatorForMultipleChoice:
    """
    Data collator that will dynamically pad the inputs for multiple choice received.
    """

    tokenizer: PreTrainedTokenizerBase
    padding: Union[bool, str, PaddingStrategy] = True
    max_length: Optional[int] = None
    pad_to_multiple_of: Optional[int] = None

    def __call__(self, features):
        label_name = "label" if "label" in features[0].keys() else "labels"
        labels = [feature.pop(label_name) for feature in features]
        batch_size = len(features)
        num_choices = len(features[0]["input_ids"])
        flattened_features = [
            [{k: v[i] for k, v in feature.items()} for i in range(num_choices)] for feature in features
        ]
        flattened_features = sum(flattened_features, [])

        batch = self.tokenizer.pad(
            flattened_features,
            padding=self.padding,
            max_length=self.max_length,
            pad_to_multiple_of=self.pad_to_multiple_of,
            return_tensors="pt",
        )

        batch = {k: v.view(batch_size, num_choices, -1) for k, v in batch.items()}
        batch["labels"] = torch.tensor(labels, dtype=torch.int64)
        return batch

from dataclasses import dataclass
from transformers.tokenization_utils_base import PreTrainedTokenizerBase, PaddingStrategy
from typing import Optional, Union
import tensorflow as tf

@dataclass
class DataCollatorForMultipleChoice:
    """
    Data collator that will dynamically pad the inputs for multiple choice received.
    """

    tokenizer: PreTrainedTokenizerBase
    padding: Union[bool, str, PaddingStrategy] = True
    max_length: Optional[int] = None
    pad_to_multiple_of: Optional[int] = None

    def __call__(self, features):
        label_name = "label" if "label" in features[0].keys() else "labels"
        labels = [feature.pop(label_name) for feature in features]
        batch_size = len(features)
        num_choices = len(features[0]["input_ids"])
        flattened_features = [
            [{k: v[i] for k, v in feature.items()} for i in range(num_choices)] for feature in features
        ]
        flattened_features = sum(flattened_features, [])

        batch = self.tokenizer.pad(
            flattened_features,
            padding=self.padding,
            max_length=self.max_length,
            pad_to_multiple_of=self.pad_to_multiple_of,
            return_tensors="tf",
        )

        batch = {k: tf.reshape(v, (batch_size, num_choices, -1)) for k, v in batch.items()}
        batch["labels"] = tf.convert_to_tensor(labels, dtype=tf.int64)
        return batch

import evaluate

accuracy = evaluate.load("accuracy")

import numpy as np

def compute_metrics(eval_pred):
    predictions, labels = eval_pred
    predictions = np.argmax(predictions, axis=1)
    return accuracy.compute(predictions=predictions, references=labels)

from transformers import AutoModelForMultipleChoice, TrainingArguments, Trainer

model = AutoModelForMultipleChoice.from_pretrained("google-bert/bert-base-uncased")

training_args = TrainingArguments(
    output_dir="my_awesome_swag_model",
    eval_strategy="epoch",
    save_strategy="epoch",
    load_best_model_at_end=True,
    learning_rate=5e-5,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    num_train_epochs=3,
    weight_decay=0.01,
    push_to_hub=True,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_swag["train"],
    eval_dataset=tokenized_swag["validation"],
    processing_class=tokenizer,
    data_collator=DataCollatorForMultipleChoice(tokenizer=tokenizer),
    compute_metrics=compute_metrics,
)

trainer.train()

trainer.push_to_hub()

from transformers import create_optimizer

batch_size = 16
num_train_epochs = 2
total_train_steps = (len(tokenized_swag["train"]) // batch_size) * num_train_epochs
optimizer, schedule = create_optimizer(init_lr=5e-5, num_warmup_steps=0, num_train_steps=total_train_steps)

from transformers import TFAutoModelForMultipleChoice

model = TFAutoModelForMultipleChoice.from_pretrained("google-bert/bert-base-uncased")

data_collator = DataCollatorForMultipleChoice(tokenizer=tokenizer)
tf_train_set = model.prepare_tf_dataset(
    tokenized_swag["train"],
    shuffle=True,
    batch_size=batch_size,
    collate_fn=data_collator,
)

tf_validation_set = model.prepare_tf_dataset(
    tokenized_swag["validation"],
    shuffle=False,
    batch_size=batch_size,
    collate_fn=data_collator,
)

model.compile(optimizer=optimizer)  # لا توجد وسيطة خسارة!

from transformers.keras_callbacks import KerasMetricCallback

metric_callback = KerasMetricCallback(metric_fn=compute_metrics, eval_dataset=tf_validation_set)

from transformers.keras_callbacks import PushToHubCallback

push_to_hub_callback = PushToHubCallback(
    output_dir="my_awesome_model",
    tokenizer=tokenizer,
)

callbacks = [metric_callback, push_to_hub_callback]

model.fit(x=tf_train_set, validation_data=tf_validation_set, epochs=2, callbacks=callbacks)

prompt = "France has a bread law, Le Décret Pain, with strict rules on what is allowed in a traditional baguette."
candidate1 = "The law does not apply to croissants and brioche."
candidate2 = "The law applies to baguettes."

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("username/my_awesome_swag_model")
inputs = tokenizer([[prompt, candidate1], [prompt, candidate2]], return_tensors="pt", padding=True)
labels = torch.tensor(0).unsqueeze(0)

from transformers import AutoModelForMultipleChoice

model = AutoModelForMultipleChoice.from_pretrained("username/my_awesome_swag_model")
outputs = model(**{k: v.unsqueeze(0) for k, v in inputs.items()}, labels=labels)
logits = outputs.logits

predicted_class = logits.argmax().item()
predicted_class

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("username/my_awesome_swag_model")
inputs = tokenizer([[prompt, candidate1], [prompt, candidate2]], return_tensors="tf", padding=True)

from transformers import TFAutoModelForMultipleChoice

model = TFAutoModelForMultipleChoice.from_pretrained("username/my_awesome_swag_model")
inputs = {k: tf.expand_dims(v, 0) for k, v in inputs.items()}
outputs = model(inputs)
logits = outputs.logits

predicted_class = int(tf.math.argmax(logits, axis=-1)[0])
predicted_class