SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Generate] Facilitate PyTorch generate using ModelOutputs (#6735)

Browse Source 
* fix generate for GPT2 Double Head

* fix gpt2 double head model

* fix  bart / t5

* also add for no beam search

* fix no beam search

* fix encoder decoder

* simplify t5

* simplify t5

* fix t5 tests

* fix BART

* fix transfo-xl

* fix conflict

* integrating sylvains and sams comments

* fix tf past_decoder_key_values

* fix enc dec test
This commit is contained in:
Patrick von Platen
2020-09-01 12:38:25 +02:00
committed by GitHub
parent 397f819615
commit afc4ece462
20 changed files with 393 additions and 259 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/test_modeling_tf_t5.py
View File

@@ -96,7 +96,7 @@ class TFT5ModelTester:
result = model(input_ids, decoder_attention_mask=input_mask, decoder_input_ids=input_ids)
decoder_output = result.last_hidden_state
decoder_past = result.decoder_past_key_values
decoder_past = result.past_key_values
encoder_output = result.encoder_last_hidden_state
self.parent.assertListEqual(list(encoder_output.shape), [self.batch_size, self.seq_length, self.hidden_size])
self.parent.assertListEqual(list(decoder_output.shape), [self.batch_size, self.seq_length, self.hidden_size])