ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source 
Former-commit-id: 06bcbb901f69265632892a5fcbc956b8be1153da
This commit is contained in:
hiyouga
2023-08-07 15:02:02 +08:00
parent 370f817549
commit 34a2bddfcd
5 changed files with 39 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/chat/stream_chat.py
View File

@@ -30,7 +30,7 @@ class ChatModel:
) -> Tuple[Dict[str, Any], int]:
prefix = prefix or self.source_prefix
prompt, _ = self.template.get_prompt(
prompt, _ = self.template.encode_oneturn(
tokenizer=self.tokenizer, query=query, resp="", history=history, prefix=prefix
)
input_ids = torch.tensor([prompt], device=self.model.device)

11
src/llmtuner/dsets/preprocess.py
View File

@@ -47,15 +47,14 @@ def preprocess_dataset(
def preprocess_supervised_dataset(examples: Dict[str, List[Any]]) -> Dict[str, Any]:
# build inputs with format `<bos> X Y <eos>` and labels with format `<ignore> ... <ignore> Y <eos>`
# for input with history, we build multiple input-label pairs just like:
# https://github.com/lm-sys/FastChat/blob/f17c092f64840fa6354ed52789dccb2daa793d0b/fastchat/train/train.py#L112
# for multiturn examples, we only mask the prompt part in each prompt-response pair.
model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
max_length = data_args.max_source_length + data_args.max_target_length
for query, response, history, prefix in construct_example(examples):
input_ids, labels = [], []
for source_ids, target_ids in template.get_dialog(tokenizer, query, response, history, prefix):
for source_ids, target_ids in template.encode_multiturn(tokenizer, query, response, history, prefix):
if len(source_ids) > data_args.max_source_length:
source_ids = source_ids[:data_args.max_source_length]
if len(target_ids) > data_args.max_target_length:
@@ -78,7 +77,7 @@ def preprocess_dataset(
model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
for query, response, history, prefix in construct_example(examples):
source_ids, target_ids = template.get_prompt(tokenizer, query, response, history, prefix)
source_ids, target_ids = template.encode_oneturn(tokenizer, query, response, history, prefix)
if len(source_ids) > data_args.max_source_length:
source_ids = source_ids[:data_args.max_source_length]
@@ -95,8 +94,8 @@ def preprocess_dataset(
# build input pairs with format `<bos> X Y1 <eos>` and `<bos> X Y2 <eos>`
model_inputs = {"accept_ids": [], "reject_ids": []}
for query, response, history, prefix in construct_example(examples):
source_ids, accept_ids = template.get_prompt(tokenizer, query, response[0], history, prefix)
source_ids, reject_ids = template.get_prompt(tokenizer, query, response[1], history, prefix)
source_ids, accept_ids = template.encode_oneturn(tokenizer, query, response[0], history, prefix)
source_ids, reject_ids = template.encode_oneturn(tokenizer, query, response[1], history, prefix)
if len(source_ids) > data_args.max_source_length:
source_ids = source_ids[:data_args.max_source_length]

6
src/llmtuner/extras/template.py
View File

@@ -14,7 +14,7 @@ class Template:
stop_words: List[str]
use_history: bool
def get_prompt(
def encode_oneturn(
self,
tokenizer: "PreTrainedTokenizer",
query: str,
@@ -33,7 +33,7 @@ class Template:
prompt_ids = prompt_ids + encoded_pairs[-1][0]
return prompt_ids, encoded_pairs[-1][1]
def get_dialog(
def encode_multiturn(
self,
tokenizer: "PreTrainedTokenizer",
query: str,
@@ -73,7 +73,7 @@ class Template:
r"""
Encodes formatted inputs to pairs of token ids.
"""
if tokenizer.bos_token and getattr(tokenizer, "add_bos_token", False): # bos token is optional
if tokenizer.bos_token_id and getattr(tokenizer, "add_bos_token", False): # bos token is optional
bos_token_id = [tokenizer.bos_token_id]
else:
bos_token_id = []