Spaces:
Running
Running
File size: 35,387 Bytes
2852136 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 |
# Copyright 2024 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from dataclasses import dataclass
from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Tuple, Union
from ..extras.logging import get_logger
from .data_utils import Role, infer_max_len
from .formatter import EmptyFormatter, FunctionFormatter, StringFormatter, ToolFormatter
if TYPE_CHECKING:
from transformers import PreTrainedTokenizer
from .formatter import SLOTS, Formatter
logger = get_logger(__name__)
@dataclass
class Template:
format_user: "Formatter"
format_assistant: "Formatter"
format_system: "Formatter"
format_function: "Formatter"
format_observation: "Formatter"
format_tools: "Formatter"
format_separator: "Formatter"
default_system: str
stop_words: List[str]
image_token: str
efficient_eos: bool
replace_eos: bool
force_system: bool
def encode_oneturn(
self,
tokenizer: "PreTrainedTokenizer",
messages: List[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
cutoff_len: int = 1_000_000,
reserved_label_len: int = 1,
) -> Tuple[List[int], List[int]]:
r"""
Returns a single pair of token ids representing prompt and response respectively.
"""
encoded_pairs = self._encode(tokenizer, messages, system, tools, cutoff_len, reserved_label_len)
prompt_ids = []
for query_ids, resp_ids in encoded_pairs[:-1]:
prompt_ids += query_ids + resp_ids
prompt_ids = prompt_ids + encoded_pairs[-1][0]
answer_ids = encoded_pairs[-1][1]
return prompt_ids, answer_ids
def encode_multiturn(
self,
tokenizer: "PreTrainedTokenizer",
messages: List[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
cutoff_len: int = 1_000_000,
reserved_label_len: int = 1,
) -> Sequence[Tuple[List[int], List[int]]]:
r"""
Returns multiple pairs of token ids representing prompts and responses respectively.
"""
return self._encode(tokenizer, messages, system, tools, cutoff_len, reserved_label_len)
def _encode(
self,
tokenizer: "PreTrainedTokenizer",
messages: List[Dict[str, str]],
system: Optional[str],
tools: Optional[str],
cutoff_len: int,
reserved_label_len: int,
) -> Sequence[Tuple[List[int], List[int]]]:
r"""
Encodes formatted inputs to pairs of token ids.
Turn 0: system + query resp
Turn t: sep + query resp
"""
system = system or self.default_system
encoded_messages = []
for i, message in enumerate(messages):
elements = []
if i == 0 and (system or tools or self.force_system):
tool_text = self.format_tools.apply(content=tools)[0] if tools else ""
elements += self.format_system.apply(content=(system + tool_text))
elif i > 0 and i % 2 == 0:
elements += self.format_separator.apply()
if message["role"] == Role.USER.value:
elements += self.format_user.apply(content=message["content"], idx=str(i // 2))
elif message["role"] == Role.ASSISTANT.value:
elements += self.format_assistant.apply(content=message["content"])
elif message["role"] == Role.OBSERVATION.value:
elements += self.format_observation.apply(content=message["content"])
elif message["role"] == Role.FUNCTION.value:
elements += self.format_function.apply(content=message["content"])
else:
raise NotImplementedError("Unexpected role: {}".format(message["role"]))
encoded_messages.append(self._convert_elements_to_ids(tokenizer, elements))
return self._make_pairs(encoded_messages, cutoff_len, reserved_label_len)
def _convert_elements_to_ids(
self, tokenizer: "PreTrainedTokenizer", elements: List[Union[str, Dict[str, str]]]
) -> List[int]:
r"""
Converts elements to token ids.
"""
token_ids = []
for elem in elements:
if isinstance(elem, str):
if len(elem) != 0:
token_ids += tokenizer.encode(elem, add_special_tokens=False)
elif isinstance(elem, dict):
token_ids += [tokenizer.convert_tokens_to_ids(elem.get("token"))]
elif isinstance(elem, set):
if "bos_token" in elem and tokenizer.bos_token_id is not None:
token_ids += [tokenizer.bos_token_id]
elif "eos_token" in elem and tokenizer.eos_token_id is not None:
token_ids += [tokenizer.eos_token_id]
else:
raise ValueError("Input must be string, set[str] or dict[str, str], got {}".format(type(elem)))
return token_ids
def _make_pairs(
self,
encoded_messages: Sequence[List[int]],
cutoff_len: int,
reserved_label_len: int,
) -> Sequence[Tuple[List[int], List[int]]]:
encoded_pairs = []
total_length = 0
for i in range(0, len(encoded_messages), 2):
if total_length >= cutoff_len:
break
max_source_len, max_target_len = infer_max_len(
source_len=len(encoded_messages[i]),
target_len=len(encoded_messages[i + 1]),
max_len=(cutoff_len - total_length),
reserved_label_len=reserved_label_len,
)
source_ids = encoded_messages[i][:max_source_len]
target_ids = encoded_messages[i + 1][:max_target_len]
total_length += len(source_ids) + len(target_ids)
encoded_pairs.append((source_ids, target_ids))
return encoded_pairs
@dataclass
class Llama2Template(Template):
def _encode(
self,
tokenizer: "PreTrainedTokenizer",
messages: List[Dict[str, str]],
system: str,
tools: str,
cutoff_len: int,
reserved_label_len: int,
) -> Sequence[Tuple[List[int], List[int]]]:
r"""
Encodes formatted inputs to pairs of token ids.
Turn 0: system + query resp
Turn t: sep + query resp
"""
system = system or self.default_system
encoded_messages = []
for i, message in enumerate(messages):
elements = []
system_text = ""
if i == 0 and (system or tools or self.force_system):
tool_text = self.format_tools.apply(content=tools)[0] if tools else ""
system_text = self.format_system.apply(content=(system + tool_text))[0]
elif i > 0 and i % 2 == 0:
elements += self.format_separator.apply()
if message["role"] == Role.USER.value:
elements += self.format_user.apply(content=system_text + message["content"])
elif message["role"] == Role.ASSISTANT.value:
elements += self.format_assistant.apply(content=message["content"])
elif message["role"] == Role.OBSERVATION.value:
elements += self.format_observation.apply(content=message["content"])
elif message["role"] == Role.FUNCTION.value:
elements += self.format_function.apply(content=message["content"])
else:
raise NotImplementedError("Unexpected role: {}".format(message["role"]))
encoded_messages.append(self._convert_elements_to_ids(tokenizer, elements))
return self._make_pairs(encoded_messages, cutoff_len, reserved_label_len)
TEMPLATES: Dict[str, Template] = {}
def _register_template(
name: str,
format_user: Optional["Formatter"] = None,
format_assistant: Optional["Formatter"] = None,
format_system: Optional["Formatter"] = None,
format_function: Optional["Formatter"] = None,
format_observation: Optional["Formatter"] = None,
format_tools: Optional["Formatter"] = None,
format_separator: Optional["Formatter"] = None,
default_system: str = "",
stop_words: List[str] = [],
image_token: str = "<image>",
efficient_eos: bool = False,
replace_eos: bool = False,
force_system: bool = False,
) -> None:
r"""
Registers a chat template.
To add the following chat template:
```
[HUMAN]:
user prompt here
[AI]:
model response here
[HUMAN]:
user prompt here
[AI]:
model response here
```
The corresponding code should be:
```
_register_template(
name="custom",
format_user=StringFormatter(slots=["[HUMAN]:\n{{content}}\n[AI]:\n"]),
format_separator=EmptyFormatter(slots=["\n\n"]),
efficient_eos=True,
)
```
"""
eos_slots = [] if efficient_eos else [{"eos_token"}]
template_class = Llama2Template if name.startswith("llama2") else Template
default_user_formatter = StringFormatter(slots=["{{content}}"])
default_assistant_formatter = StringFormatter(slots=["{{content}}"] + eos_slots)
default_function_formatter = FunctionFormatter(slots=["Action: {{name}}\nAction Input: {{arguments}}"] + eos_slots)
default_tool_formatter = ToolFormatter(tool_format="default")
default_separator_formatter = EmptyFormatter()
TEMPLATES[name] = template_class(
format_user=format_user or default_user_formatter,
format_assistant=format_assistant or default_assistant_formatter,
format_system=format_system or default_user_formatter,
format_function=format_function or default_function_formatter,
format_observation=format_observation or format_user or default_user_formatter,
format_tools=format_tools or default_tool_formatter,
format_separator=format_separator or default_separator_formatter,
default_system=default_system,
stop_words=stop_words,
image_token=image_token,
efficient_eos=efficient_eos,
replace_eos=replace_eos,
force_system=force_system,
)
def _add_or_replace_eos_token(tokenizer: "PreTrainedTokenizer", eos_token: str) -> None:
is_added = tokenizer.eos_token_id is None
num_added_tokens = tokenizer.add_special_tokens({"eos_token": eos_token})
if is_added:
logger.info("Add eos token: {}".format(tokenizer.eos_token))
else:
logger.info("Replace eos token: {}".format(tokenizer.eos_token))
if num_added_tokens > 0:
logger.warning("New tokens have been added, make sure `resize_vocab` is True.")
def _jinja_escape(content: str) -> str:
return content.replace("'", r"\'")
def _convert_slots_to_jinja(slots: "SLOTS", tokenizer: "PreTrainedTokenizer", placeholder: str = "content") -> str:
slot_items = []
for slot in slots:
if isinstance(slot, str):
slot_pieces = slot.split("{{content}}")
if slot_pieces[0]:
slot_items.append("'" + _jinja_escape(slot_pieces[0]) + "'")
if len(slot_pieces) > 1:
slot_items.append(placeholder)
if slot_pieces[1]:
slot_items.append("'" + _jinja_escape(slot_pieces[1]) + "'")
elif isinstance(slot, set): # do not use {{ eos_token }} since it may be replaced
if "bos_token" in slot and tokenizer.bos_token_id is not None:
slot_items.append("'" + tokenizer.bos_token + "'")
elif "eos_token" in slot and tokenizer.eos_token_id is not None:
slot_items.append("'" + tokenizer.eos_token + "'")
elif isinstance(slot, dict):
raise ValueError("Dict is not supported.")
return " + ".join(slot_items)
def _get_jinja_template(template: "Template", tokenizer: "PreTrainedTokenizer") -> str:
jinja_template = ""
if template.default_system:
jinja_template += "{% set system_message = '" + _jinja_escape(template.default_system) + "' %}"
jinja_template += (
"{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}"
)
system_message = _convert_slots_to_jinja(template.format_system.apply(), tokenizer, placeholder="system_message")
if isinstance(template, Llama2Template):
pass
elif template.force_system:
jinja_template += "{{ " + system_message + " }}"
else:
jinja_template += "{% if system_message is defined %}{{ " + system_message + " }}{% endif %}"
jinja_template += "{% for message in messages %}"
jinja_template += "{% set content = message['content'] %}"
if isinstance(template, Llama2Template):
jinja_template += "{% if loop.index0 == 0 and system_message is defined %}"
jinja_template += "{% set content = " + system_message + " + message['content'] %}"
jinja_template += "{% endif %}"
jinja_template += "{% if message['role'] == 'user' %}"
user_message = _convert_slots_to_jinja(template.format_user.apply(), tokenizer)
jinja_template += "{{ " + user_message + " }}"
jinja_template += "{% elif message['role'] == 'assistant' %}"
assistant_message = _convert_slots_to_jinja(
template.format_assistant.apply() + template.format_separator.apply(), tokenizer
)
jinja_template += "{{ " + assistant_message + " }}"
jinja_template += "{% endif %}"
jinja_template += "{% endfor %}"
return jinja_template
def get_template_and_fix_tokenizer(
tokenizer: "PreTrainedTokenizer",
name: Optional[str] = None,
) -> Template:
if name is None:
template = TEMPLATES["empty"] # placeholder
else:
template = TEMPLATES.get(name, None)
if template is None:
raise ValueError("Template {} does not exist.".format(name))
stop_words = template.stop_words
if template.replace_eos:
if not stop_words:
raise ValueError("Stop words are required to replace the EOS token.")
_add_or_replace_eos_token(tokenizer, eos_token=stop_words[0])
stop_words = stop_words[1:]
if tokenizer.eos_token_id is None:
_add_or_replace_eos_token(tokenizer, eos_token="<|endoftext|>")
if tokenizer.pad_token_id is None:
tokenizer.pad_token = tokenizer.eos_token
logger.info("Add pad token: {}".format(tokenizer.pad_token))
if stop_words:
num_added_tokens = tokenizer.add_special_tokens(
dict(additional_special_tokens=stop_words), replace_additional_special_tokens=False
)
logger.info("Add {} to stop words.".format(",".join(stop_words)))
if num_added_tokens > 0:
logger.warning("New tokens have been added, make sure `resize_vocab` is True.")
try:
tokenizer.chat_template = _get_jinja_template(template, tokenizer)
except ValueError:
logger.info("Cannot add this chat template to tokenizer.")
return template
_register_template(
name="alpaca",
format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n\n### Response:\n"]),
format_separator=EmptyFormatter(slots=["\n\n"]),
default_system=(
"Below is an instruction that describes a task. "
"Write a response that appropriately completes the request.\n\n"
),
)
_register_template(
name="aquila",
format_user=StringFormatter(slots=["Human: {{content}}###Assistant:"]),
format_separator=EmptyFormatter(slots=["###"]),
default_system=(
"A chat between a curious human and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the human's questions."
),
stop_words=["</s>"],
efficient_eos=True,
)
_register_template(
name="atom",
format_user=StringFormatter(
slots=[{"bos_token"}, "Human: {{content}}\n", {"eos_token"}, {"bos_token"}, "Assistant:"]
),
format_assistant=StringFormatter(slots=["{{content}}\n", {"eos_token"}]),
)
_register_template(
name="baichuan",
format_user=StringFormatter(slots=[{"token": "<reserved_102>"}, "{{content}}", {"token": "<reserved_103>"}]),
efficient_eos=True,
)
_register_template(
name="baichuan2",
format_user=StringFormatter(slots=["<reserved_106>{{content}}<reserved_107>"]),
efficient_eos=True,
)
_register_template(
name="belle",
format_user=StringFormatter(slots=["Human: {{content}}\n\nBelle: "]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
format_separator=EmptyFormatter(slots=["\n\n"]),
force_system=True,
)
_register_template(
name="bluelm",
format_user=StringFormatter(slots=[{"token": "[|Human|]:"}, "{{content}}", {"token": "[|AI|]:"}]),
)
_register_template(
name="breeze",
format_user=StringFormatter(slots=["[INST] {{content}} [/INST] "]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
default_system=(
"You are a helpful AI assistant built by MediaTek Research. "
"The user you are helping speaks Traditional Chinese and comes from Taiwan."
),
efficient_eos=True,
)
_register_template(
name="chatglm2",
format_user=StringFormatter(slots=["[Round {{idx}}]\n\n问:{{content}}\n\n答:"]),
format_system=StringFormatter(slots=[{"token": "[gMASK]"}, {"token": "sop"}, "{{content}}"]),
format_separator=EmptyFormatter(slots=["\n\n"]),
efficient_eos=True,
force_system=True,
)
_register_template(
name="chatglm3",
format_user=StringFormatter(slots=[{"token": "<|user|>"}, "\n", "{{content}}", {"token": "<|assistant|>"}]),
format_assistant=StringFormatter(slots=["\n", "{{content}}"]),
format_system=StringFormatter(slots=[{"token": "[gMASK]"}, {"token": "sop"}, "{{content}}"]),
format_function=FunctionFormatter(slots=["{{name}}\n{{arguments}}"]),
format_observation=StringFormatter(
slots=[{"token": "<|observation|>"}, "\n", "{{content}}", {"token": "<|assistant|>"}]
),
stop_words=["<|user|>", "<|observation|>"],
efficient_eos=True,
force_system=True,
)
_register_template(
name="chatglm3_system",
format_user=StringFormatter(slots=[{"token": "<|user|>"}, "\n", "{{content}}", {"token": "<|assistant|>"}]),
format_assistant=StringFormatter(slots=["\n", "{{content}}"]),
format_system=StringFormatter(
slots=[{"token": "[gMASK]"}, {"token": "sop"}, {"token": "<|system|>"}, "\n", "{{content}}"]
),
format_function=FunctionFormatter(slots=["{{name}}\n{{arguments}}"]),
format_observation=StringFormatter(
slots=[{"token": "<|observation|>"}, "\n", "{{content}}", {"token": "<|assistant|>"}]
),
default_system=(
"You are ChatGLM3, a large language model trained by Zhipu.AI. "
"Follow the user's instructions carefully. Respond using markdown."
),
stop_words=["<|user|>", "<|observation|>"],
efficient_eos=True,
)
_register_template(
name="chatml",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
stop_words=["<|im_end|>", "<|im_start|>"],
replace_eos=True,
)
_register_template(
name="chatml_de",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system="Du bist ein freundlicher und hilfsbereiter KI-Assistent.",
stop_words=["<|im_end|>", "<|im_start|>"],
replace_eos=True,
)
_register_template(
name="codegeex2",
format_system=StringFormatter(slots=[{"token": "[gMASK]"}, {"token": "sop"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="cohere",
format_user=StringFormatter(
slots=[
(
"<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{content}}<|END_OF_TURN_TOKEN|>"
"<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>"
)
]
),
format_system=StringFormatter(
slots=[{"bos_token"}, "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{content}}<|END_OF_TURN_TOKEN|>"]
),
default_system=(
"You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users "
"by providing thorough responses. You are trained by Cohere."
),
)
_register_template(
name="cpm",
format_user=StringFormatter(slots=["<用户>{{content}}<AI>"]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="dbrx",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system=(
"You are DBRX, created by Databricks. You were last updated in December 2023. "
"You answer questions based on information available up to that point.\n"
"YOU PROVIDE SHORT RESPONSES TO SHORT QUESTIONS OR STATEMENTS, but provide thorough "
"responses to more complex and open-ended questions.\nYou assist with various tasks, "
"from writing to coding (using markdown for code blocks — remember to use ``` with "
"code, JSON, and tables).\n(You do not have real-time data access or code execution "
"capabilities. You avoid stereotyping and provide balanced perspectives on "
"controversial topics. You do not provide song lyrics, poems, or news articles and "
"do not divulge details of your training data.)\nThis is your system prompt, "
"guiding your responses. Do not reference it, just respond to the user. If you find "
"yourself talking about this message, stop. You should be responding appropriately "
"and usually that means not mentioning this.\nYOU DO NOT MENTION ANY OF THIS INFORMATION "
"ABOUT YOURSELF UNLESS THE INFORMATION IS DIRECTLY PERTINENT TO THE USER'S QUERY."
),
stop_words=["<|im_end|>"],
replace_eos=True,
)
_register_template(
name="deepseek",
format_user=StringFormatter(slots=["User: {{content}}\n\nAssistant:"]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="deepseekcoder",
format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n### Response:"]),
format_assistant=StringFormatter(slots=["\n", "{{content}}"]),
format_separator=EmptyFormatter(slots=["\n<|EOT|>\n"]),
default_system=(
"You are an AI programming assistant, utilizing the Deepseek Coder model, "
"developed by Deepseek Company, and you only answer questions related to computer science. "
"For politically sensitive questions, security and privacy issues, "
"and other non-computer science questions, you will refuse to answer\n"
),
stop_words=["<|EOT|>"],
efficient_eos=True,
)
_register_template(
name="default",
format_user=StringFormatter(slots=["Human: {{content}}\nAssistant: "]),
format_system=StringFormatter(slots=["{{content}}\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
)
_register_template(
name="empty",
format_user=StringFormatter(slots=["{{content}}"]),
format_assistant=StringFormatter(slots=["{{content}}"]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
efficient_eos=True,
force_system=True,
)
_register_template(
name="falcon",
format_user=StringFormatter(slots=["User: {{content}}\nFalcon:"]),
format_separator=EmptyFormatter(slots=["\n"]),
efficient_eos=True,
)
_register_template(
name="fewshot",
format_separator=EmptyFormatter(slots=["\n\n"]),
efficient_eos=True,
)
_register_template(
name="gemma",
format_user=StringFormatter(slots=["<start_of_turn>user\n{{content}}<end_of_turn>\n<start_of_turn>model\n"]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
format_observation=StringFormatter(
slots=["<start_of_turn>tool\n{{content}}<end_of_turn>\n<start_of_turn>model\n"]
),
format_separator=EmptyFormatter(slots=["<end_of_turn>\n"]),
efficient_eos=True,
force_system=True,
)
_register_template(
name="glm4",
format_user=StringFormatter(slots=["<|user|>\n{{content}}<|assistant|>"]),
format_assistant=StringFormatter(slots=["\n{{content}}"]),
format_system=StringFormatter(slots=["[gMASK]<sop>{{content}}"]),
format_function=FunctionFormatter(slots=["{{name}}\n{{arguments}}"]),
format_observation=StringFormatter(slots=["<|observation|>\n{{content}}<|assistant|>"]),
stop_words=["<|user|>", "<|observation|>"],
efficient_eos=True,
force_system=True,
)
_register_template(
name="intern",
format_user=StringFormatter(slots=["<|User|>:{{content}}", {"token": "<eoh>"}, "\n<|Bot|>:"]),
format_separator=EmptyFormatter(slots=[{"token": "<eoa>"}, "\n"]),
stop_words=["<eoa>"],
efficient_eos=True,
)
_register_template(
name="intern2",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=[{"bos_token"}, "<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system=(
"You are an AI assistant whose name is InternLM (书生·浦语).\n"
"- InternLM (书生·浦语) is a conversational language model that is developed "
"by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.\n"
"- InternLM (书生·浦语) can understand and communicate fluently in the language chosen "
"by the user such as English and 中文."
),
stop_words=["<|im_end|>"],
efficient_eos=True, # internlm2 tokenizer cannot set eos_token_id
)
_register_template(
name="llama2",
format_user=StringFormatter(slots=[{"bos_token"}, "[INST] {{content}} [/INST]"]),
format_assistant=StringFormatter(slots=[" {{content}} ", {"eos_token"}]),
format_system=StringFormatter(slots=["<<SYS>>\n{{content}}\n<</SYS>>\n\n"]),
)
_register_template(
name="llama2_zh",
format_user=StringFormatter(slots=[{"bos_token"}, "[INST] {{content}} [/INST]"]),
format_system=StringFormatter(slots=["<<SYS>>\n{{content}}\n<</SYS>>\n\n"]),
default_system="You are a helpful assistant. 你是一个乐于助人的助手。",
)
_register_template(
name="llama3",
format_user=StringFormatter(
slots=[
(
"<|start_header_id|>user<|end_header_id|>\n\n{{content}}<|eot_id|>"
"<|start_header_id|>assistant<|end_header_id|>\n\n"
)
]
),
format_system=StringFormatter(
slots=[{"bos_token"}, "<|start_header_id|>system<|end_header_id|>\n\n{{content}}<|eot_id|>"]
),
format_observation=StringFormatter(
slots=[
(
"<|start_header_id|>tool<|end_header_id|>\n\n{{content}}<|eot_id|>"
"<|start_header_id|>assistant<|end_header_id|>\n\n"
)
]
),
default_system="You are a helpful assistant.",
stop_words=["<|eot_id|>"],
replace_eos=True,
)
_register_template(
name="mistral",
format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="olmo",
format_user=StringFormatter(slots=["<|user|>\n{{content}}<|assistant|>\n"]),
format_system=StringFormatter(slots=[{"eos_token"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="openchat",
format_user=StringFormatter(slots=["GPT4 Correct User: {{content}}", {"eos_token"}, "GPT4 Correct Assistant:"]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="openchat-3.6",
format_user=StringFormatter(
slots=[
(
"<|start_header_id|>GPT4 Correct User<|end_header_id|>\n\n{{content}}<|eot_id|>"
"<|start_header_id|>GPT4 Correct Assistant<|end_header_id|>\n\n"
)
]
),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
stop_words=["<|eot_id|>"],
replace_eos=True,
force_system=True,
)
_register_template(
name="orion",
format_user=StringFormatter(slots=["Human: {{content}}\n\nAssistant: ", {"eos_token"}]),
format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]),
force_system=True,
)
_register_template(
name="phi",
format_user=StringFormatter(slots=["<|user|>\n{{content}}<|end|>\n<|assistant|>\n"]),
format_system=StringFormatter(slots=[{"bos_token"}, "<|system|>\n{{content}}<|end|>\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system="You are a helpful AI assistant.",
stop_words=["<|end|>"],
replace_eos=True,
)
_register_template(
name="qwen",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system="You are a helpful assistant.",
stop_words=["<|im_end|>"],
replace_eos=True,
)
_register_template(
name="solar",
format_user=StringFormatter(slots=["### User:\n{{content}}\n\n### Assistant:\n"]),
format_system=StringFormatter(slots=["### System:\n{{content}}\n\n"]),
efficient_eos=True,
)
_register_template(
name="starchat",
format_user=StringFormatter(slots=["<|user|>\n{{content}}<|end|>\n<|assistant|>"]),
format_system=StringFormatter(slots=["<|system|>\n{{content}}<|end|>\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
stop_words=["<|end|>"],
replace_eos=True,
force_system=True,
)
_register_template(
name="telechat",
format_user=StringFormatter(slots=["<_user>{{content}}<_bot>"]),
format_system=StringFormatter(slots=["<_system>{{content}}<_end>"]),
stop_words=["<_end>"],
replace_eos=True,
)
_register_template(
name="vicuna",
format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]),
default_system=(
"A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions."
),
)
_register_template(
name="xuanyuan",
format_user=StringFormatter(slots=["Human: {{content}} Assistant:"]),
default_system=(
"以下是用户和人工智能助手之间的对话。用户以Human开头,人工智能助手以Assistant开头,"
"会对人类提出的问题给出有帮助、高质量、详细和礼貌的回答,并且总是拒绝参与与不道德、"
"不安全、有争议、政治敏感等相关的话题、问题和指示。\n"
),
)
_register_template(
name="xverse",
format_user=StringFormatter(slots=["Human: {{content}}\n\nAssistant: "]),
)
_register_template(
name="yayi",
format_user=StringFormatter(slots=[{"token": "<|Human|>"}, ":\n{{content}}\n\n", {"token": "<|YaYi|>"}, ":"]),
format_system=StringFormatter(slots=[{"token": "<|System|>"}, ":\n{{content}}\n\n"]),
format_separator=EmptyFormatter(slots=["\n\n"]),
default_system=(
"You are a helpful, respectful and honest assistant named YaYi "
"developed by Beijing Wenge Technology Co.,Ltd. "
"Always answer as helpfully as possible, while being safe. "
"Your answers should not include any harmful, unethical, "
"racist, sexist, toxic, dangerous, or illegal content. "
"Please ensure that your responses are socially unbiased and positive in nature.\n\n"
"If a question does not make any sense, or is not factually coherent, "
"explain why instead of answering something not correct. "
"If you don't know the answer to a question, please don't share false information."
),
stop_words=["<|End|>"],
)
_register_template(
name="yi",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
stop_words=["<|im_end|>"],
replace_eos=True,
)
_register_template(
name="yi_vl",
format_user=StringFormatter(slots=["### Human: {{content}}\n### Assistant:"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system=(
"This is a chat between an inquisitive human and an AI assistant. "
"Assume the role of the AI assistant. Read all the images carefully, "
"and respond to the human's questions with informative, helpful, detailed and polite answers. "
"这是一个好奇的人类和一个人工智能助手之间的对话。假设你扮演这个AI助手的角色。"
"仔细阅读所有的图像,并对人类的问题做出信息丰富、有帮助、详细的和礼貌的回答。\n\n"
),
stop_words=["###"],
efficient_eos=True,
)
_register_template(
name="yuan",
format_user=StringFormatter(slots=["{{content}}", {"token": "<sep>"}]),
format_separator=EmptyFormatter(slots=["\n"]),
stop_words=["<eod>"],
replace_eos=True,
)
_register_template(
name="zephyr",
format_user=StringFormatter(slots=["<|user|>\n{{content}}", {"eos_token"}, "<|assistant|>"]),
format_assistant=StringFormatter(slots=["\n{{content}}", {"eos_token"}]),
format_system=StringFormatter(slots=["<|system|>\n{{content}}", {"eos_token"}]),
default_system="You are Zephyr, a helpful assistant.",
)
_register_template(
name="ziya",
format_user=StringFormatter(slots=["<human>:{{content}}\n<bot>:"]),
format_separator=EmptyFormatter(slots=["\n"]),
)
|