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

Update all references to canonical models (#29001)

Browse Source 
* Script & Manual edition

* Update
This commit is contained in:
Lysandre Debut
2024-02-16 08:16:58 +01:00
committed by GitHub
parent 1e402b957d
commit f497f564bb
561 changed files with 2682 additions and 2687 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/trainer/test_trainer_seq2seq.py
View File

@@ -35,7 +35,7 @@ class Seq2seqTrainerTester(TestCasePlus):
@require_torch
def test_finetune_bert2bert(self):
bert2bert = EncoderDecoderModel.from_encoder_decoder_pretrained("prajjwal1/bert-tiny", "prajjwal1/bert-tiny")
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased")
bert2bert.config.vocab_size = bert2bert.config.encoder.vocab_size
bert2bert.config.eos_token_id = tokenizer.sep_token_id
@@ -144,11 +144,11 @@ class Seq2seqTrainerTester(TestCasePlus):
MAX_TARGET_LENGTH = 256
dataset = datasets.load_dataset("gsm8k", "main", split="train[:38]")
model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-small")
tokenizer = T5Tokenizer.from_pretrained("google-t5/t5-small")
data_collator = DataCollatorForSeq2Seq(tokenizer, model=model, return_tensors="pt", padding="longest")
gen_config = GenerationConfig.from_pretrained(
"t5-small", max_length=None, min_length=None, max_new_tokens=256, min_new_tokens=1, num_beams=5
"google-t5/t5-small", max_length=None, min_length=None, max_new_tokens=256, min_new_tokens=1, num_beams=5
)
training_args = Seq2SeqTrainingArguments(".", predict_with_generate=True)