| | from dataclasses import dataclass |
| | from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Tuple, Union |
| |
|
| | from ..extras.logging import get_logger |
| | from .formatter import EmptyFormatter, FunctionFormatter, StringFormatter, ToolFormatter |
| | from .utils import Role, infer_max_len |
| |
|
| |
|
| | if TYPE_CHECKING: |
| | from transformers import PreTrainedTokenizer |
| |
|
| | from .formatter import 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] |
| | 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: Optional[int] = 1_000_000, |
| | reserved_label_len: Optional[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: Optional[int] = 1_000_000, |
| | reserved_label_len: Optional[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: 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 = [] |
| | 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: Optional[str] = "", |
| | stop_words: Optional[List[str]] = [], |
| | efficient_eos: Optional[bool] = False, |
| | replace_eos: Optional[bool] = False, |
| | force_system: Optional[bool] = False, |
| | ) -> None: |
| | 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, |
| | 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 |
| | is_oov = eos_token not in tokenizer.get_vocab() |
| | 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 is_oov: |
| | logger.warning("New tokens have been added, make sure `resize_vocab` is True.") |
| |
|
| |
|
| | def get_template_and_fix_tokenizer( |
| | tokenizer: "PreTrainedTokenizer", |
| | name: Optional[str] = None, |
| | ) -> Template: |
| | if name is None: |
| | template = templates["vanilla"] |
| | else: |
| | template = templates.get(name, None) |
| | if templates 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: |
| | 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))) |
| |
|
| | 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." |
| | ), |
| | ) |
| |
|
| |
|
| | _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="baichuan", |
| | format_user=StringFormatter(slots=[{"token": "<reserved_102>"}, "{{content}}", {"token": "<reserved_103>"}]), |
| | efficient_eos=True, |
| | ) |
| |
|
| |
|
| | _register_template( |
| | name="baichuan2", |
| | format_user=StringFormatter(slots=[{"token": "<reserved_106>"}, "{{content}}", {"token": "<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="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"}, {"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_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_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="cpm", |
| | format_user=StringFormatter(slots=["<用户>{{content}}<AI>"]), |
| | format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]), |
| | force_system=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", {"token": "<|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="falcon", |
| | format_user=StringFormatter(slots=["User: {{content}}\nFalcon:"]), |
| | format_separator=EmptyFormatter(slots=["\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_separator=EmptyFormatter(slots=["<end_of_turn>\n"]), |
| | 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, |
| | ) |
| |
|
| |
|
| | _register_template( |
| | name="llama2", |
| | 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, respectful and honest assistant. " |
| | "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." |
| | ), |
| | ) |
| |
|
| |
|
| | _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="mistral", |
| | format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]), |
| | format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]), |
| | force_system=True, |
| | ) |
| |
|
| |
|
| | _register_template( |
| | name="openchat", |
| | format_user=StringFormatter(slots=["GPT4 Correct User: {{content}}", {"eos_token"}, "GPT4 Correct Assistant:"]), |
| | format_assistant=StringFormatter(slots=["{{content}}"]), |
| | format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]), |
| | 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="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_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=[{"token": "<|user|>"}, "\n{{content}}", {"token": "<|end|>"}, "\n", {"token": "<|assistant|>"}] |
| | ), |
| | format_system=StringFormatter(slots=[{"token": "<|system|>"}, "\n{{content}}", {"token": "<|end|>"}, "\n"]), |
| | format_separator=EmptyFormatter(slots=["\n"]), |
| | stop_words=["<|end|>"], |
| | replace_eos=True, |
| | force_system=True, |
| | ) |
| |
|
| |
|
| | _register_template( |
| | name="vanilla", |
| | ) |
| |
|
| |
|
| | _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_separator=EmptyFormatter(slots=["\n"]), |
| | stop_words=["<|im_end|>"], |
| | replace_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_system=StringFormatter(slots=["<|system|>\n{{content}}", {"eos_token"}]), |
| | default_system="You are a friendly chatbot who always responds in the style of a pirate", |
| | ) |
| |
|
| |
|
| | _register_template( |
| | name="ziya", |
| | format_user=StringFormatter(slots=[{"token": "<human>"}, ":{{content}}\n", {"token": "<bot>"}, ":"]), |
| | format_separator=EmptyFormatter(slots=["\n"]), |
| | ) |
| |
|
