tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

quiet noise from llama tokenizer by setting pad token earlier

Browse Source
This commit is contained in:
Aman Karmani
2023-08-13 01:30:54 +00:00
committed by Aman Gupta Karmani
parent 8cec513447
commit e029ab34ea
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/axolotl/utils/models.py
View File

@@ -59,17 +59,17 @@ def load_tokenizer(
**tokenizer_kwargs,
)
LOG.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
LOG.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
LOG.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
LOG.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")
if tokenizer.__class__.__name__ in [
"LlamaTokenizer",
"LlamaTokenizerFast",
]:
tokenizer.pad_token = LLAMA_DEFAULT_PAD_TOKEN
LOG.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
LOG.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
LOG.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
LOG.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")
if tokenizer.__class__.__name__ == "GPTNeoXTokenizerFast":
tokenizer.add_special_tokens({"pad_token": "[PAD]"})
os.environ["TOKENIZERS_PARALLELISM"] = "false"