transformers/examples/pytorch/text-generation
GMFTBY 71786b10c5
Adding the state-of-the-art contrastive search decoding methods for the codebase of generation_utils.py (#19477)
* add: the contrastive search for generaton_utils

* add: testing scripts for contrastive search under examples/text-generation

* update the quality of codes

* revise the docstring; make the generation_contrastive_search.py scripts;

* revise the examples/pytorch/text-generation/run_generation_contrastive_search.py to the auto-APIs format

* revise the necessary documents

* fix: revise the docstring of generation_contrastive_search.py

* Fix the code indentation

* fix: revise the nits and examples in contrastive_search docstring.

* fix the copyright

* delete generation_contrastive_search.py

* revise the logic in contrastive_search

* update the intergration test and the docstring

* run the tests over

* add the slow decorate to the contrastive_search intergrate test

* add more test

* do the style, quality, consistency checks
2022-10-19 10:17:46 +01:00
..
README.md Updates the default branch from master to main (#16326) 2022-03-23 03:46:59 -04:00
requirements.txt Examples reorg (#11350) 2021-04-21 11:11:20 -04:00
run_generation_contrastive_search.py Adding the state-of-the-art contrastive search decoding methods for the codebase of generation_utils.py (#19477) 2022-10-19 10:17:46 +01:00
run_generation.py remove extra white space from log format (#12360) 2021-06-25 13:20:14 -07:00

Language generation

Based on the script run_generation.py.

Conditional text generation using the auto-regressive models of the library: GPT, GPT-2, Transformer-XL, XLNet, CTRL. A similar script is used for our official demo Write With Transfomer, where you can try out the different models available in the library.

Example usage:

python run_generation.py \
    --model_type=gpt2 \
    --model_name_or_path=gpt2