File size: 15,091 Bytes
fb21b03 4b14016 fb21b03 16b604a fb21b03 4b14016 fb21b03 16b604a fb21b03 4b14016 fb21b03 4b14016 fb21b03 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 |
"""
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()
CHATINTERN = auto()
DOLLY = auto()
RWKV = auto()
PHOENIX = auto()
ROBIN = auto()
FALCON_CHAT = auto()
CHATGLM3 = auto()
INTERNVL_ZH = 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)
if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ': ' + message + self.sep
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
seps = [self.sep, self.sep2]
ret = system_prompt + seps[0]
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + ': ' + message + seps[i % 2]
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ': ' + message + self.sep
else:
ret += role + ': ' # must be end with a space
return ret
elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
ret = '' if system_prompt == '' else system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + '\n' + message + self.sep
else:
ret += role + '\n'
return ret
elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
ret = system_prompt
for role, message in self.messages:
if message:
ret += role + message + self.sep
else:
ret += role
return ret
elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
seps = [self.sep, self.sep2]
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + message + seps[i % 2]
else:
ret += role
return ret
elif self.sep_style == SeparatorStyle.RWKV:
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
if message:
ret += (
role
+ ': '
+ message.replace('\r\n', '\n').replace('\n\n', '\n')
)
ret += '\n\n'
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.LLAMA2:
seps = [self.sep, self.sep2]
if self.system_message:
ret = system_prompt
else:
ret = '[INST] '
for i, (role, message) in enumerate(self.messages):
tag = self.roles[i % 2]
if message:
if i == 0:
ret += message + ' '
else:
ret += tag + ' ' + message + seps[i % 2]
else:
ret += tag
return ret
elif self.sep_style == SeparatorStyle.CHATGLM:
# source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
# source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
round_add_n = 1 if self.name == 'chatglm2' else 0
if system_prompt:
ret = system_prompt + self.sep
else:
ret = ''
for i, (role, message) in enumerate(self.messages):
if i % 2 == 0:
ret += f'[Round {i//2 + round_add_n}]{self.sep}'
if message:
ret += f'{role}:{message}{self.sep}'
else:
ret += f'{role}:'
return ret
elif self.sep_style == SeparatorStyle.CHATML:
ret = '' if system_prompt == '' else system_prompt + self.sep + '\n'
for role, message in self.messages:
if message:
ret += role + '\n' + message + self.sep + '\n'
else:
ret += role + '\n'
return ret
elif self.sep_style == SeparatorStyle.CHATGLM3:
ret = ''
if self.system_message:
ret += system_prompt
for role, message in self.messages:
if message:
ret += role + '\n' + ' ' + message
else:
ret += role
return ret
elif self.sep_style == SeparatorStyle.CHATINTERN:
# source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
seps = [self.sep, self.sep2]
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
# if i % 2 == 0:
# ret += "<s>"
if message:
ret += role + ':' + message + seps[i % 2] + '\n'
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.DOLLY:
seps = [self.sep, self.sep2]
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + ':\n' + message + seps[i % 2]
if i % 2 == 1:
ret += '\n\n'
else:
ret += role + ':\n'
return ret
elif self.sep_style == SeparatorStyle.PHOENIX:
ret = system_prompt
for role, message in self.messages:
if message:
ret += role + ': ' + '<s>' + message + '</s>'
else:
ret += role + ': ' + '<s>'
return ret
elif self.sep_style == SeparatorStyle.ROBIN:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ':\n' + message + self.sep
else:
ret += role + ':\n'
return ret
elif self.sep_style == SeparatorStyle.FALCON_CHAT:
ret = ''
if self.system_message:
ret += system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ': ' + message + self.sep
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.INTERNVL_ZH:
seps = [self.sep, self.sep2]
ret = self.system_message + seps[0]
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + ': ' + message + seps[i % 2]
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.MPT:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + message + self.sep
else:
ret += role
return ret
else:
raise ValueError(f'Invalid style: {self.sep_style}')
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()
# Note that for inference, using the Hermes-2 and internlm2-chat templates is equivalent.
register_conv_template(
Conversation(
name='Hermes-2',
system_template='<|im_start|>system\n{system_message}',
# note: The new system prompt was not used here to avoid changes in benchmark performance.
# system_message='我是书生·万象,英文名是InternVL,是由上海人工智能实验室及多家合作单位联合开发的多模态基础模型。人工智能实验室致力于原始技术创新,开源开放,共享共创,推动科技进步和产业发展。',
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型,英文名叫InternVL, 是一个有用无害的人工智能助手。',
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
sep_style=SeparatorStyle.MPT,
sep='<|im_end|>',
stop_token_ids=[
2,
6,
7,
8,
],
stop_str='<|endoftext|>',
)
)
register_conv_template(
Conversation(
name='internlm2-chat',
system_template='<|im_start|>system\n{system_message}',
# note: The new system prompt was not used here to avoid changes in benchmark performance.
# system_message='我是书生·万象,英文名是InternVL,是由上海人工智能实验室及多家合作单位联合开发的多模态基础模型。人工智能实验室致力于原始技术创新,开源开放,共享共创,推动科技进步和产业发展。',
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型,英文名叫InternVL, 是一个有用无害的人工智能助手。',
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
sep_style=SeparatorStyle.MPT,
sep='<|im_end|>',
stop_token_ids=[
2,
92543,
92542
]
)
)
register_conv_template(
Conversation(
name='phi3-chat',
system_template='<|system|>\n{system_message}',
# note: The new system prompt was not used here to avoid changes in benchmark performance.
# system_message='我是书生·万象,英文名是InternVL,是由上海人工智能实验室及多家合作单位联合开发的多模态基础模型。人工智能实验室致力于原始技术创新,开源开放,共享共创,推动科技进步和产业发展。',
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型,英文名叫InternVL, 是一个有用无害的人工智能助手。',
roles=('<|user|>\n', '<|assistant|>\n'),
sep_style=SeparatorStyle.MPT,
sep='<|end|>',
stop_token_ids=[
2,
32000,
32007
]
)
)
|