riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-03 03:31:05 +06:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Improve Text Generation doc (#18788)

Browse Source 
* fix args for bram search decoding in generation utils

* fix missing PAD token in gpt2

* add PAD EOS change to TF

* Update src/transformers/generation_tf_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/generation_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/generation_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Ekagra Ranjan 2022-09-01 00:00:29 +05:30 committed by GitHub
parent 86387fe87f
commit 89514f0541
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/generation_tf_utils.py
View File

@ -2113,7 +2113,7 @@ class TFGenerationMixin:
>>> tokenizer = AutoTokenizer.from_pretrained("gpt2")
>>> model = TFAutoModelForCausalLM.from_pretrained("gpt2")
>>> # set pad_token_id to eos_token_id because GPT2 does not have a EOS token
>>> # set pad_token_id to eos_token_id because GPT2 does not have a PAD token
>>> model.config.pad_token_id = model.config.eos_token_id
>>> input_prompt = "Today is a beautiful day, and"

4
src/transformers/generation_utils.py
View File

@ -1139,7 +1139,7 @@ class GenerationMixin:
>>> sentence = "Paris is one of the densest populated areas in Europe."
>>> input_ids = tokenizer(sentence, return_tensors="pt").input_ids
>>> outputs = model.generate(input_ids)
>>> outputs = model.generate(input_ids, num_beams=5)
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Paris ist eines der dichtesten besiedelten Gebiete Europas.']
```"""
@ -1635,7 +1635,7 @@ class GenerationMixin:
>>> tokenizer = AutoTokenizer.from_pretrained("gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("gpt2")
>>> # set pad_token_id to eos_token_id because GPT2 does not have a EOS token
>>> # set pad_token_id to eos_token_id because GPT2 does not have a PAD token
>>> model.config.pad_token_id = model.config.eos_token_id
>>> input_prompt = "It might be possible to"