fix(model): reduce memory usage while loading in half-precision

[orionji]

Reference:
huggingface/transformers#12062
huggingface/transformers#12316

[codecov-commenter]

Codecov Report

Patch coverage has no change and project coverage change: +0.28 🎉

Comparison is base (506514f) 93.94% compared to head (7428abd) 94.23%.

❗ Current head 7428abd differs from pull request most recent head 1b98035. Consider uploading reports for the commit 1b98035 to get more accurate results

📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more

Additional details and impacted files

@@            Coverage Diff             @@
##           master      #79      +/-   ##
==========================================
+ Coverage   93.94%   94.23%   +0.28%     
==========================================
  Files           7        7              
  Lines         314      312       -2     
==========================================
- Hits          295      294       -1     
+ Misses         19       18       -1     

Impacted Files	Coverage Δ
basaran/model.py	89.03% <0.00%> (+0.49%)	⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.