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

fix system prompt

Browse Source 
Former-commit-id: 411e775aa939bdd154a3f1e92921ede90d989f18
This commit is contained in:
hiyouga
2023-08-16 01:35:52 +08:00
parent ca9a494d0c
commit baa709674f
15 changed files with 170 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/llmtuner/hparams/data_args.py
View File

@@ -10,7 +10,7 @@ class DatasetAttr:
load_from: str
dataset_name: Optional[str] = None
dataset_sha1: Optional[str] = None
source_prefix: Optional[str] = None
system_prompt: Optional[str] = None
def __repr__(self) -> str:
return self.dataset_name
@@ -86,9 +86,9 @@ class DataArguments:
default=True,
metadata={"help": "Whether to ignore the tokens corresponding to padded labels in the loss computation or not."}
)
source_prefix: Optional[str] = field(
system_prompt: Optional[str] = field(
default=None,
metadata={"help": "A prefix to add before every source text. Use `|` to separate multiple prefixes in training."}
metadata={"help": "System prompt to add before the user query. Use `|` to separate multiple prompts in training."}
)
val_size: Optional[float] = field(
default=0,
@@ -100,12 +100,9 @@ class DataArguments:
with open(os.path.join(self.dataset_dir, "dataset_info.json"), "r") as f:
dataset_info = json.load(f)
if self.source_prefix is not None:
prefix_list = self.source_prefix.split("|")
prefix_list = prefix_list * len(dataset_names) if len(prefix_list) == 1 else prefix_list
assert len(prefix_list) == len(dataset_names), "The number of prefixes should be either identical with datasets or 1."
else:
prefix_list = [None] * len(dataset_names)
prompt_list = self.system_prompt.split("|") if self.system_prompt else [None]
prompt_list = prompt_list * (len(dataset_names) // len(prompt_list))
assert len(prompt_list) == len(dataset_names), "Number of system prompts should be equal to datasets or 1."
if self.interleave_probs is not None:
self.interleave_probs = [float(prob.strip()) for prob in self.interleave_probs.split(",")]
@@ -126,12 +123,11 @@ class DataArguments:
dataset_sha1=dataset_info[name].get("file_sha1", None)
)
dataset_attr.source_prefix = prefix_list[i]
if "columns" in dataset_info[name]:
dataset_attr.prompt = dataset_info[name]["columns"].get("prompt", None)
dataset_attr.query = dataset_info[name]["columns"].get("query", None)
dataset_attr.response = dataset_info[name]["columns"].get("response", None)
dataset_attr.history = dataset_info[name]["columns"].get("history", None)
dataset_attr.system_prompt = prompt_list[i]
self.dataset_list.append(dataset_attr)