提示模板¶
提示模板是结构化文本模板,用于设置用户提示的格式 以优化特定任务上的模型性能。它们可以用于多种用途:
每当提示模型时都需要的特定于模型的模板,例如 [INST] 标记中。这些模型使用这些标签进行了预训练,并使用它们 在推理中可以帮助确保最佳性能。
例如,如果我想微调模型以执行语法更正任务,我可以使用 将文本 “Correct this to standard English: {prompt} — Corrected: {response}” 添加到我的所有数据样本中。
from torchtune.data import GrammarErrorCorrectionTemplate, Message
sample = {
"incorrect": "This are a cat",
"correct": "This is a cat.",
}
msgs = [
Message(role="user", content=sample["incorrect"]),
Message(role="assistant", content=sample["correct"]),
]
gec_template = GrammarErrorCorrectionTemplate()
templated_msgs = gec_template(msgs)
for msg in templated_msgs:
print(msg.text_content)
# Correct this to standard English: This are a cat
# ---
# Corrected:
# This is a cat.
添加的文本与模型分词器添加的特殊标记不同。对于扩展的 关于提示模板和特殊令牌之间的区别的讨论,参见令牌化提示模板和特殊令牌。
使用提示模板¶
提示模板将传递到分词器中,并将自动应用于您正在微调的数据集。您可以通过两种方式传递它:
提示模板类的字符串点路径,即 “torchtune.models.mistral.MistralChatTemplate” 或 “path.to.my.CustomPromptTemplate”
一个字典,用于将 role 映射到字符串元组,指示要在消息内容之前和之后添加的文本
通过 dotpath 字符串定义¶
# In code
from torchtune.models.mistral import mistral_tokenizer
m_tokenizer = mistral_tokenizer(
path="/tmp/Mistral-7B-v0.1/tokenizer.model"
prompt_template="torchtune.models.mistral.MistralChatTemplate"
)
# In config
tokenizer:
_component_: torchtune.models.mistral.mistral_tokenizer
path: /tmp/Mistral-7B-v0.1/tokenizer.model
prompt_template: torchtune.models.mistral.MistralChatTemplate
通过字典定义¶
例如,要实现以下提示模板:
System: {content}\\n
User: {content}\\n
Assistant: {content}\\n
Tool: {content}\\n
您需要为每个角色传入一个元组,其中 是字符串
added before the text 内容 和 是 之后添加的字符串。PREPEND_TAG
APPEND_TAG
template = {role: (PREPEND_TAG, APPEND_TAG)}
因此,模板将定义如下:
template = {
"system": ("System: ", "\\n"),
"user": ("User: ", "\\n"),
"assistant": ("Assistant: ", "\\n"),
"ipython": ("Tool: ", "\\n"),
}
现在我们可以将其作为字典传递到分词器中:
# In code
from torchtune.models.mistral import mistral_tokenizer
template = {
"system": ("System: ", "\\n"),
"user": ("User: ", "\\n"),
"assistant": ("Assistant: ", "\\n"),
"ipython": ("Tool: ", "\\n"),
}
m_tokenizer = mistral_tokenizer(
path="/tmp/Mistral-7B-v0.1/tokenizer.model"
prompt_template=template,
)
# In config
tokenizer:
_component_: torchtune.models.mistral.mistral_tokenizer
path: /tmp/Mistral-7B-v0.1/tokenizer.model
prompt_template:
system:
- "System: "
- "\\n"
user:
- "User: "
- "\\n"
assistant:
- "Assistant: "
- "\\n"
ipython:
- "Tool: "
- "\\n"
如果您不想向角色添加 prepend/append 标签,则可以在需要的地方传入一个空字符串 “”。
使用
类¶
还可以传入模板字典,以便您可以将其用作独立的自定义
prompt 模板类。
from torchtune.data import PromptTemplate
def my_custom_template() -> PromptTemplate:
return PromptTemplate(
template={
"user": ("User: ", "\\n"),
"assistant": ("Assistant: ", "\\n"),
},
)
template = my_custom_template()
msgs = [
Message(role="user", content="Hello world!"),
Message(role="assistant", content="Is AI overhyped?"),
]
templated_msgs = template(msgs)
for msg in templated_msgs:
print(msg.role, msg.text_content)
# user, User: Hello world!
#
# assistant, Assistant: Is AI overhyped?
#
自定义提示模板¶
对于不完全属于该模式的更高级的配置,您可以创建一个继承自该方法并实现该方法的新类。
PREPEND_TAG content APPEND_TAG
__call__
from torchtune.data import Message
class PromptTemplateInterface(Protocol):
def __call__(
self,
messages: List[Message],
inference: bool = False,
) -> List[Message]:
"""
Format each role's message(s) according to the prompt template
Args:
messages (List[Message]): a single conversation, structured as a list
of :class:`~torchtune.data.Message` objects
inference (bool): Whether the template is being used for inference or not.
Returns:
The formatted list of messages
"""
pass
# Contrived example - make all assistant prompts say "Eureka!"
class EurekaTemplate(PromptTemplateInterface):
def __call__(
self,
messages: List[Message],
inference: bool = False,
) -> List[Message]:
formatted_dialogue = []
for message in messages:
if message.role == "assistant":
content = "Eureka!"
else:
content = message.content
formatted_dialogue.append(
Message(
role=message.role,
content=content,
masked=message.masked,
ipython=message.ipython,
eot=message.eot,
),
)
return formatted_dialogue
template = EurekaTemplate()
msgs = [
Message(role="user", content="Hello world!"),
Message(role="assistant", content="Is AI overhyped?"),
]
templated_msgs = template(msgs)
for msg in templated_msgs:
print(msg.role, msg.text_content)
# user, Hello world!
# assistant, Eureka!
要在分词器中使用此自定义模板,您可以通过 dotpath 字符串传入它:
# In code
from torchtune.models.mistral import mistral_tokenizer
m_tokenizer = mistral_tokenizer(
path="/tmp/Mistral-7B-v0.1/tokenizer.model",
prompt_template="path.to.template.EurekaTemplate",
)
# In config
tokenizer:
_component_: torchtune.models.mistral.mistral_tokenizer
path: /tmp/Mistral-7B-v0.1/tokenizer.model
prompt_template: path.to.template.EurekaTemplate