Add generate() functionality to TF 2.0 (#3063)

* add first copy past test to tf 2 generate

* add tf top_k_top_p_filter fn

* add generate function for TF

* add generate function for TF

* implemented generate for all models expect transfoXL

* implemented generate for all models expect transfoXL

* implemented generate for all models expect transfoXL

* make style

* change permission of test file to correct ones

* delete ipdb

* delete ipdb

* fix bug and finish simple gpt2 integration test

* clean test file

* clean test file

* make style

* make style

* make style

* make style

* change import style

* change import style

* make style

* make style

* add decorators

* add decorators

* fix tf ctrl bug dim => axis in TF

* make style

* make style

* refactored test file

* refactored test file

* take out test_torch_tf_conversion if nothing is defined

* take out test_torch_tf_conversion if nothing is defined

* remove useless files

* remove useless files

* fix conflicts

* fix conflicts

* fix conflicts

* fix conflicts

* fix conflicts

* solve conflicts

* solve conflicts

* fix conflicts

* fix conflicts

* merge conflicts

* delete ipdb

* exposed top_k_top_p_filtering fns

* delete weirdly created w! file

* add comment to test tf common modeling

* fix conflicts

* fix conflicts

* make style

* merge conflicts

* make style

* change tf.tensor.shape to shape_list(tensor)
This commit is contained in:
Patrick von Platen
2020-03-03 15:42:15 +01:00
committed by GitHub
parent b31f715019
commit 4134100363
20 changed files with 892 additions and 62 deletions

View File

@@ -386,33 +386,33 @@ class GPT2ModelLanguageGenerationTest(unittest.TestCase):
@slow
def test_lm_generate_distilgpt2(self):
model = GPT2LMHeadModel.from_pretrained("distilgpt2")
input_ids = torch.Tensor([[464, 3290, 318, 13779]]).long() # The dog is cute
input_ids = torch.Tensor([[464, 1893]]).long() # The president
expected_output_ids = [
464,
3290,
318,
13779,
996,
339,
460,
3360,
655,
2513,
1893,
286,
262,
1578,
1829,
11,
290,
262,
1893,
286,
262,
1578,
7526,
11,
423,
587,
287,
262,
3952,
13,
632,
318,
407,
845,
3621,
284,
] # The dog is cute though he can sometimes just walk in the park. It is not very nice to
torch.manual_seed(0)
2635,
] # The president of the United States, and the president of the United Kingdom, have been in the White
output_ids = model.generate(
input_ids,
do_sample=False,
bos_token_id=self.special_tokens["bos_token_id"],
eos_token_ids=self.special_tokens["eos_token_id"],
)