Skywork-R1V-38B / conversation.py
OrlandoHugBot's picture
Upload folder using huggingface_hub
5b16c4f verified
"""
Conversation prompt templates.
We kindly request that you import fastchat instead of copying this file if you wish to use it.
If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
"""
import dataclasses
from enum import IntEnum, auto
from typing import Any, Dict, List, Tuple, Union
class SeparatorStyle(IntEnum):
"""Separator styles."""
ADD_COLON_SINGLE = auto()
ADD_COLON_TWO = auto()
ADD_COLON_SPACE_SINGLE = auto()
NO_COLON_SINGLE = auto()
NO_COLON_TWO = auto()
ADD_NEW_LINE_SINGLE = auto()
LLAMA2 = auto()
CHATGLM = auto()
CHATML = auto()
DOLLY = auto()
RWKV = auto()
PHOENIX = auto()
ROBIN = auto()
FALCON_CHAT = auto()
CHATGLM3 = auto()
MPT = auto()
@dataclasses.dataclass
class Conversation:
"""A class that manages prompt templates and keeps all conversation history."""
# The name of this template
name: str
# The template of the system prompt
system_template: str = '{system_message}'
# The system message
system_message: str = ''
# The names of two roles
roles: Tuple[str] = ('USER', 'ASSISTANT')
# All messages. Each item is (role, message).
messages: List[List[str]] = ()
# The number of few shot examples
offset: int = 0
# The separator style and configurations
sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
sep: str = '\n'
sep2: str = None
# Stop criteria (the default one is EOS token)
stop_str: Union[str, List[str]] = None
# Stops generation if meeting any token in this list
stop_token_ids: List[int] = None
def get_prompt(self) -> str:
"""Get the prompt for generation."""
system_prompt = self.system_template.format(system_message=self.system_message)
ret = system_prompt
for role, message in self.messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + message
else:
ret += role
return ret
def set_system_message(self, system_message: str):
"""Set the system message."""
self.system_message = system_message
def append_message(self, role: str, message: str):
"""Append a new message."""
self.messages.append([role, message])
def update_last_message(self, message: str):
"""Update the last output.
The last message is typically set to be None when constructing the prompt,
so we need to update it in-place after getting the response from a model.
"""
self.messages[-1][1] = message
def to_gradio_chatbot(self):
"""Convert the conversation to gradio chatbot format."""
ret = []
for i, (role, msg) in enumerate(self.messages[self.offset :]):
if i % 2 == 0:
ret.append([msg, None])
else:
ret[-1][-1] = msg
return ret
def to_openai_api_messages(self):
"""Convert the conversation to OpenAI chat completion format."""
ret = [{'role': 'system', 'content': self.system_message}]
for i, (_, msg) in enumerate(self.messages[self.offset :]):
if i % 2 == 0:
ret.append({'role': 'user', 'content': msg})
else:
if msg is not None:
ret.append({'role': 'assistant', 'content': msg})
return ret
def copy(self):
return Conversation(
name=self.name,
system_template=self.system_template,
system_message=self.system_message,
roles=self.roles,
messages=[[x, y] for x, y in self.messages],
offset=self.offset,
sep_style=self.sep_style,
sep=self.sep,
sep2=self.sep2,
stop_str=self.stop_str,
stop_token_ids=self.stop_token_ids,
)
def dict(self):
return {
'template_name': self.name,
'system_message': self.system_message,
'roles': self.roles,
'messages': self.messages,
'offset': self.offset,
}
# A global registry for all conversation templates
conv_templates: Dict[str, Conversation] = {}
def register_conv_template(template: Conversation, override: bool = False):
"""Register a new conversation template."""
if not override:
assert (
template.name not in conv_templates
), f'{template.name} has been registered.'
conv_templates[template.name] = template
def get_conv_template(name: str) -> Conversation:
"""Get a conversation template."""
return conv_templates[name].copy()
register_conv_template(
Conversation(
name='skywork-r1v-chat',
system_template='<|begin▁of▁sentence|>{system_message}',
system_message='',
roles=('<|User|>\n', '<|Assistant|><think>\n'),
sep_style=SeparatorStyle.MPT,
sep='<|end▁of▁sentence|>',
)
)