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

[FLAX] Minor fixes in CLM example (#12914)

Browse Source 
* readme: fix retrieval of vocab size for flax clm example

* examples: fix flax clm example when using training/evaluation files
This commit is contained in:
Stefan Schweter
2021-07-27 16:18:04 +02:00
committed by GitHub
parent 12e02e339f
commit d3c3e722d6
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/flax/language-modeling/README.md
View File

@@ -211,7 +211,7 @@ from transformers import GPT2Config
model_dir = "./norwegian-gpt2" # ${MODEL_DIR}
config = GPT2Config.from_pretrained("gpt2", resid_pdrop=0.0, embd_pdrop=0.0, attn_pdrop=0.0, vocab_size=tokenizer.vocab_size)
config = GPT2Config.from_pretrained("gpt2", resid_pdrop=0.0, embd_pdrop=0.0, attn_pdrop=0.0, vocab_size=tokenizer.get_vocab_size())
config.save_pretrained(model_dir)
```

6
examples/flax/language-modeling/run_clm_flax.py
View File

@@ -308,14 +308,14 @@ def main():
extension = "text"
dataset = load_dataset(extension, data_files=data_files, cache_dir=model_args.cache_dir)
if "validation" not in datasets.keys():
datasets["validation"] = load_dataset(
if "validation" not in dataset.keys():
dataset["validation"] = load_dataset(
extension,
data_files=data_files,
split=f"train[:{data_args.validation_split_percentage}%]",
cache_dir=model_args.cache_dir,
)
datasets["train"] = load_dataset(
dataset["train"] = load_dataset(
extension,
data_files=data_files,
split=f"train[{data_args.validation_split_percentage}%:]",