search

microsoft / TransformerCompression

For releasing code related to compression methods for transformers, accompanying our publications
MIT License
354 stars 31 forks source link

Add Phi3 #162

Closed nailimixaM closed 2 months ago

nailimixaM commented 3 months ago

Added tests: pytest -m quarot for unit tests, pytest -m quarot_experiment for longer e2e tests. All require gpu.

Includes changes of #154 and #152.

Co-authored with @pashminacameron @jameshensman.