423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-04 18:02:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

Slim Orca data parsing

Browse Source 
Former-commit-id: f2d8efede7e20edafed0d5446eb64f2d419949b1
This commit is contained in:
Mark Mueller 2024-02-08 19:32:20 +01:00
parent 4d473894fd
commit 1ce82f391a
3 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
data/README.md
View File

@ -26,7 +26,8 @@ If you are using a custom dataset, please provide your dataset definition in the
"user_tag": "the value of the role_tag represents the user. (default: human)",
"assistant_tag": "the value of the role_tag represents the assistant. (default: gpt)",
"observation_tag": "the value of the role_tag represents the tool results. (default: observation)",
"function_tag": "the value of the role_tag represents the function call. (default: function_call)"
"function_tag": "the value of the role_tag represents the function call. (default: function_call)",
"system_tag": "the value of the role_tag represents the system prompt. (default: None) incompatible with system column"
}
}
```

7
src/llmtuner/data/aligner.py
View File

@ -47,10 +47,10 @@ def convert_sharegpt(examples: Dict[str, List[Any]], dataset_attr: "DatasetAttr"
dataset_attr.assistant_tag: Role.ASSISTANT,
dataset_attr.observation_tag: Role.OBSERVATION,
dataset_attr.function_tag: Role.FUNCTION,
dataset_attr.system_tag: Role.SYSTEM,
}
for i, messages in enumerate(examples[dataset_attr.messages]):
messages = messages[: len(messages) // 2 * 2] # should be multiples of 2
if len(messages) == 0:
if len(messages) <= 1:
continue
prompt = []
@ -74,6 +74,9 @@ def convert_sharegpt(examples: Dict[str, List[Any]], dataset_attr: "DatasetAttr"
{"role": tag_mapping[message[dataset_attr.role_tag]], "content": message[dataset_attr.content_tag]}
)
if len(prompt) % 2 == 1:
# Last message was neither from assistant nor function
prompt.pop(-1)
last_message = prompt.pop(-1)
response.append(last_message)
outputs["prompt"].append(prompt)

1
src/llmtuner/data/utils.py
View File

@ -21,6 +21,7 @@ class Role(str, Enum):
ASSISTANT = "assistant"
OBSERVATION = "observation"
FUNCTION = "function"
SYSTEM = "system"
def checksum(data_files: List[str], file_sha1: Optional[str] = None) -> None: