Additional BERT/ALBERT examples

[hanneshapke]

Two additional notebooks explaining:

• the export of the BERT model using raw input data during deployment
• the use of ALBERT instead of BERT for even easier deployments (smaller model size, faster inferences)

[googlebot]

All (the pull request submitter and all commit authors) CLAs are signed, but one or more commits were authored or co-authored by someone other than the pull request submitter.

We need to confirm that all authors are ok with their commits being contributed to this project. Please have them confirm that by leaving a comment that contains only @googlebot I consent. in this pull request.

Note to project maintainer: There may be cases where the author cannot leave a comment, or the comment is not properly detected as consent. In those cases, you can manually confirm consent of the commit author(s), and set the cla label to yes (if enabled on your project).

ℹ️ Googlers: Go here for more info.

[review-notebook-app]

Check out this pull request on 

Review Jupyter notebook visual diffs & provide feedback on notebooks.

---

Powered by ReviewNB

[tcmetzger]

@googlebot I consent.

[googlebot]

CLAs look good, thanks!

ℹ️ Googlers: Go here for more info.

[rcrowe-google]

I would suggest replacing this:

try:
    # %tensorflow_version only exists in Colab.
    %tensorflow_version 2.x
except Exception:
    pass

with this:

try:
  import colab
  !pip install --upgrade pip
except:
  pass

[hanneshapke]

@rcrowe-google Very similar to #69 The notebooks are updated now with the requested change, increased the TFX version to 0.25, and updated the BERT/ALBERT version and model data structure. If it is ok with you, let's merge the updates or close the PR. Thank you for your review.