#!/usr/bin/env python
# coding: utf-8

# # Quantizing a model during fine-tuning with Intel Neural Compressor (INC) for text classification tasks

# This notebook shows how to apply quantization aware training, using the [Intel Neural Compressor](https://github.com/intel/neural-compressor) (INC) library, for any tasks of the GLUE benchmark. This is made possible thanks to 🤗 [Optimum Intel](https://github.com/huggingface/optimum-intel), an extension of 🤗 [Transformers](https://github.com/huggingface/transformers), providing a set of performance optimization tools enabling maximum efficiency to accelerate end-to-end pipelines on a variety of Intel processors.

# If you're opening this Notebook on colab, you will probably need to install 🤗 Transformers, 🤗 Datasets and 🤗 Optimum. Uncomment the following cell and run it.

# In[1]:


#! pip install datasets transformers optimum[neural-compressor]


# Make sure your version of 🤗 Optimum is at least 1.6.0 since the functionality was introduced in that version:

# In[2]:


from optimum.intel.version import __version__

print(__version__)


# The GLUE Benchmark is a group of nine classification tasks on sentences or pairs of sentences which are:
# 
# - [CoLA](https://nyu-mll.github.io/CoLA/) (Corpus of Linguistic Acceptability) Determine if a sentence is grammatically correct or not.
# - [MNLI](https://arxiv.org/abs/1704.05426) (Multi-Genre Natural Language Inference) Determine if a sentence entails, contradicts or is unrelated to a given hypothesis. This dataset has two versions, one with the validation and test set coming from the same distribution, another called mismatched where the validation and test use out-of-domain data.
# - [MRPC](https://www.microsoft.com/en-us/download/details.aspx?id=52398) (Microsoft Research Paraphrase Corpus) Determine if two sentences are paraphrases from one another or not.
# - [QNLI](https://rajpurkar.github.io/SQuAD-explorer/) (Question-answering Natural Language Inference) Determine if the answer to a question is in the second sentence or not. This dataset is built from the SQuAD dataset.
# - [QQP](https://data.quora.com/First-Quora-Dataset-Release-Question-Pairs) (Quora Question Pairs2) Determine if two questions are semantically equivalent or not.
# - [RTE](https://aclweb.org/aclwiki/Recognizing_Textual_Entailment) (Recognizing Textual Entailment) Determine if a sentence entails a given hypothesis or not.
# - [SST-2](https://nlp.stanford.edu/sentiment/index.html) (Stanford Sentiment Treebank) Determine if the sentence has a positive or negative sentiment.
# - [STS-B](http://ixa2.si.ehu.es/stswiki/index.php/STSbenchmark) (Semantic Textual Similarity Benchmark) Determine the similarity of two sentences with a score from 1 to 5.
# - [WNLI](https://cs.nyu.edu/faculty/davise/papers/WinogradSchemas/WS.html) (Winograd Natural Language Inference) Determine if a sentence with an anonymous pronoun and a sentence with this pronoun replaced are entailed or not. This dataset is built from the Winograd Schema Challenge dataset.
# 
# We will see how to apply post-training static quantization on a DistilBERT model fine-tuned on the SST-2 task:

# In[3]:


GLUE_TASKS = ["cola", "mnli", "mnli-mm", "mrpc", "qnli", "qqp", "rte", "sst2", "stsb", "wnli"]
task = "sst2"
model_checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
batch_size = 16
max_train_samples = 200
max_eval_samples = 200


# ## Loading the dataset

# We will use the [🤗 Datasets](https://github.com/huggingface/datasets) and [🤗 Evaluate](https://github.com/huggingface/evaluate) libraries to download the data and get the metric we need to use for evaluation. This can be easily done with the functions `load_dataset` and `load`.
# 
# Apart from `mnli-mm` being a special code, we can directly pass our task name to those functions. `load_dataset` will cache the dataset to avoid downloading it again the next time you run this cell.

# In[4]:


import evaluate
from datasets import load_dataset

actual_task = "mnli" if task == "mnli-mm" else task
dataset = load_dataset("glue", actual_task)
metric = evaluate.load("glue", actual_task)


# Note that `load` has loaded the proper metric associated to your task, which is:
# 
# - for CoLA: [Matthews Correlation Coefficient](https://en.wikipedia.org/wiki/Matthews_correlation_coefficient)
# - for MNLI (matched or mismatched): Accuracy
# - for MRPC: Accuracy and [F1 score](https://en.wikipedia.org/wiki/F1_score)
# - for QNLI: Accuracy
# - for QQP: Accuracy and [F1 score](https://en.wikipedia.org/wiki/F1_score)
# - for RTE: Accuracy
# - for SST-2: Accuracy
# - for STS-B: [Pearson Correlation Coefficient](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient) and [Spearman's_Rank_Correlation_Coefficient](https://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient)
# - for WNLI: Accuracy
# 
# so the metric object only computes the one(s) needed for your task.

# We also quickly upload some telemetry - this tells us which examples and software versions are getting used so we know where to prioritize our maintenance efforts. We don't collect (or care about) any personally identifiable information, but if you'd prefer not to be counted, feel free to skip this step or delete this cell entirely.

# In[ ]:


from transformers.utils import send_example_telemetry

send_example_telemetry("text_classification_quantization_inc_notebook", framework="none")


# ## Preprocessing the data

# Before we can feed those texts to our model, we need to preprocess them. This is done by a 🤗 Transformers `Tokenizer` which will (as the name indicates) tokenize the inputs (including converting the tokens to their corresponding IDs in the pretrained vocabulary) and put it in a format the model expects, as well as generate the other inputs that model requires.
# 
# To do all of this, we instantiate our tokenizer with the `AutoTokenizer.from_pretrained` method, which will ensure that:
# 
# - we get a tokenizer that corresponds to the model architecture we want to use
# - we download the vocabulary used when pretraining this specific checkpoint
# 
# That vocabulary will be cached, so it's not downloaded again the next time we run the cell.

# In[5]:


from transformers import AutoTokenizer
    
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)


# To preprocess our dataset, we will thus need the names of the columns containing the sentence(s). The following dictionary keeps track of the correspondence task to column names:

# In[6]:


task_to_keys = {
    "cola": ("sentence", None),
    "mnli": ("premise", "hypothesis"),
    "mnli-mm": ("premise", "hypothesis"),
    "mrpc": ("sentence1", "sentence2"),
    "qnli": ("question", "sentence"),
    "qqp": ("question1", "question2"),
    "rte": ("sentence1", "sentence2"),
    "sst2": ("sentence", None),
    "stsb": ("sentence1", "sentence2"),
    "wnli": ("sentence1", "sentence2"),
}


# We can double check it does work on our current dataset:

# In[7]:


sentence1_key, sentence2_key = task_to_keys[task]
if sentence2_key is None:
    print(f"Sentence: {dataset['train'][0][sentence1_key]}")
else:
    print(f"Sentence 1: {dataset['train'][0][sentence1_key]}")
    print(f"Sentence 2: {dataset['train'][0][sentence2_key]}")


# We can then write the function that will preprocess our samples. We just feed them to the `tokenizer` with the argument `truncation=True`. This will ensure that an input longer than what the model selected can handle will be truncated to the maximum length accepted by the model.

# In[8]:


max_seq_length = min(128, tokenizer.model_max_length)
padding = "max_length"

def preprocess_function(examples):
    args = (
        (examples[sentence1_key],) if sentence2_key is None else (examples[sentence1_key], examples[sentence2_key])
    )
    return tokenizer(*args, padding=padding, max_length=max_seq_length, truncation=True)


# To apply this function on all the sentences (or pairs of sentences) in our dataset, we just use the `map` method of our `dataset` object we created earlier. This will apply the function on all the elements of all the splits in `dataset`, so our training, validation and testing data will be preprocessed in one single command.

# In[9]:


encoded_dataset = dataset.map(preprocess_function, batched=True)


# Even better, the results are automatically cached by the 🤗 Datasets library to avoid spending time on this step the next time you run your notebook. The 🤗 Datasets library is normally smart enough to detect when the function you pass to map has changed (and thus requires to not use the cache data). For instance, it will properly detect if you change the task in the first cell and rerun the notebook. 🤗 Datasets warns you when it uses cached files, you can pass `load_from_cache_file=False` in the call to `map` to not use the cached files and force the preprocessing to be applied again.
# 
# Note that we passed `batched=True` to encode the texts by batches together. This is to leverage the full benefit of the fast tokenizer we loaded earlier, which will use multi-threading to treat the texts in a batch concurrently.

# ## Applying quantization on the model

# Quantization aware training simulates the effects of quantization during training in order to alleviate its effects on the model's performance.
# 
# Now that our data is ready, we can download the pretrained model and fine-tune it. Since all our tasks are about sentence classification, we use the `AutoModelForSequenceClassification` class. Like with the tokenizer, the `from_pretrained` method will download and cache the model for us. The only thing we have to specify is the number of labels for our problem (which is always 2, except for STS-B which is a regression problem and MNLI where we have 3 labels):

# In[10]:


from transformers import AutoModelForSequenceClassification, TrainingArguments, default_data_collator

model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint)


# The `INCTrainer` class provides an API to train your model while combining different compression techniques such as knowledge distillation, pruning and quantization. The `INCTrainer` is very similar to the 🤗 Transformers `Trainer`, which can be replaced with minimal changes in your code. In addition to the usual 
# 
# To instantiate an `INCTrainer`, we will need to define three more things. First, we need to create the quantization configuration describing the quantization proccess we wish to apply. Quantization will be applied on the embeddings, on the linear layers as well as on their corresponding input activations.

# In[11]:


from neural_compressor import QuantizationAwareTrainingConfig

quantization_config = QuantizationAwareTrainingConfig()


# [`TrainingArguments`](https://huggingface.co/transformers/main_classes/trainer.html#transformers.TrainingArguments) is a class that contains all the attributes to customize the training. It requires one folder name, which will be used to save the checkpoints of the model, and all other arguments are optional:

# In[12]:


metric_name = "pearson" if task == "stsb" else "matthews_correlation" if task == "cola" else "accuracy"
save_directory = f"{model_checkpoint.split('/')[-1]}-finetuned-{task}"

args = TrainingArguments(
    output_dir = save_directory,
    do_train=True,
    do_eval=False,
    evaluation_strategy = "epoch",
    save_strategy = "epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=batch_size,
    per_device_eval_batch_size=batch_size,
    num_train_epochs=1,
    weight_decay=0.01,
    load_best_model_at_end=True,
    metric_for_best_model=metric_name,
)


# The last thing to define for our `INCTrainer` is how to compute the metrics from the predictions. We need to define a function for this, which will just use the `metric` we loaded earlier, the only preprocessing we have to do is to take the argmax of our predicted logits (our just squeeze the last axis in the case of STS-B):

# In[13]:


import numpy as np

def compute_metrics(eval_pred):
    predictions, labels = eval_pred
    if task != "stsb":
        predictions = np.argmax(predictions, axis=1)
    else:
        predictions = predictions[:, 0]
    return metric.compute(predictions=predictions, references=labels)


# Then we just need to pass all of this along with our datasets to the `INCTrainer`:

# In[14]:


import copy
from optimum.intel.neural_compressor import INCTrainer

validation_key = "validation_mismatched" if task == "mnli-mm" else "validation_matched" if task == "mnli" else "validation"
trainer = INCTrainer(
    model=model,
    quantization_config=quantization_config,
    task="sequence-classification", # optional : only needed to export the model to the ONNX format
    args=args,
    train_dataset=encoded_dataset["train"].select(range(max_train_samples)),
    eval_dataset=encoded_dataset[validation_key].select(range(max_eval_samples)),
    compute_metrics=compute_metrics,
    tokenizer=tokenizer,
    data_collator=default_data_collator,
)
fp_model = copy.deepcopy(model)


# We can now finetune our model by just calling the `train` method:

# In[15]:


trainer.train()


# We can run evaluation by just calling the `evaluate` method:

# In[16]:


trainer.evaluate()


# In[17]:


import os
import torch

def get_model_size(model):
    torch.save(model.state_dict(), "tmp.pt")
    model_size = os.path.getsize("tmp.pt") / (1024*1024)
    os.remove("tmp.pt")
    return round(model_size, 2)

fp_model_size = get_model_size(fp_model)
q_model_size = get_model_size(trainer.model)

print(f"The full-precision model size is {round(fp_model_size)} MB while the quantized model one is {round(q_model_size)} MB.")
print(f"The quantized model is {round(fp_model_size / q_model_size, 2)}x smaller than the full-precision one.")


# To save the resulting quantized model, you can use the `save_model` method. By setting `save_onnx_model` to `True`, the model will be additionnaly exported to the ONNX format.
# 

# In[18]:


trainer.save_model(save_onnx_model=True)


# ## Loading the quantized model

# You must instantiate you model using our `INCModelForXxx`[https://huggingface.co/docs/optimum/main/intel/reference_inc#optimum.intel.neural_compressor.INCModel] or `ORTModelForXxx`[https://huggingface.co/docs/optimum/onnxruntime/package_reference/modeling_ort] classes to load respectively your quantized PyTorch or ONNX model hosted locally or on the 🤗 hub :

# In[19]:


from optimum.intel.neural_compressor import INCModelForSequenceClassification
from optimum.onnxruntime import ORTModelForSequenceClassification

pytorch_model = INCModelForSequenceClassification.from_pretrained(save_directory)
onnx_model = ORTModelForSequenceClassification.from_pretrained(save_directory)