423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

support ORPO

Browse Source
This commit is contained in:
hiyouga
2024-03-31 18:29:50 +08:00
parent 27776c3474
commit 17bf8a2c3a
22 changed files with 395 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
src/llmtuner/data/preprocess.py
View File

@@ -23,23 +23,25 @@ def preprocess_pretrain_dataset(
) -> Dict[str, List[List[int]]]:
# build grouped texts with format `X1 X2 X3 ...` if packing is enabled
text_examples = [messages[0]["content"] + tokenizer.eos_token for messages in examples["prompt"]]
if not data_args.packing:
return tokenizer(text_examples, add_special_tokens=False, max_length=data_args.cutoff_len)
tokenized_examples = tokenizer(text_examples, add_special_tokens=False)
concatenated_examples = {k: list(chain(*tokenized_examples[k])) for k in tokenized_examples.keys()}
total_length = len(concatenated_examples[list(concatenated_examples.keys())[0]])
block_size = data_args.cutoff_len
# we drop the small remainder, and if the total_length < block_size, we exclude this batch
total_length = (total_length // block_size) * block_size
# split by chunks of cutoff_len
result = {
k: [t[i : i + block_size] for i in range(0, total_length, block_size)]
for k, t in concatenated_examples.items()
}
if data_args.template == "gemma":
for i in range(len(result["input_ids"])):
result["input_ids"][i][0] = tokenizer.bos_token_id
if not data_args.packing:
if data_args.template == "gemma":
text_examples = [tokenizer.bos_token + example for example in text_examples]
result = tokenizer(text_examples, add_special_tokens=False, max_length=data_args.cutoff_len)
else:
tokenized_examples = tokenizer(text_examples, add_special_tokens=False)
concatenated_examples = {k: list(chain(*tokenized_examples[k])) for k in tokenized_examples.keys()}
total_length = len(concatenated_examples[list(concatenated_examples.keys())[0]])
block_size = data_args.cutoff_len
total_length = (total_length // block_size) * block_size
result = {
k: [t[i : i + block_size] for i in range(0, total_length, block_size)]
for k, t in concatenated_examples.items()
}
if data_args.template == "gemma":
for i in range(len(result["input_ids"])):
result["input_ids"][i][0] = tokenizer.bos_token_id
return result