Spaces:
Sleeping
Sleeping
| """ | |
| Conversation prompt template. | |
| Now we support | |
| - Vicuna | |
| - Koala | |
| - OpenAssistant/oasst-sft-1-pythia-12b | |
| - StabilityAI/stablelm-tuned-alpha-7b | |
| - databricks/dolly-v2-12b | |
| - THUDM/chatglm-6b | |
| - project-baize/baize-lora-7B | |
| - Alpaca/LLaMa | |
| """ | |
| import dataclasses | |
| from enum import auto, Enum | |
| from typing import List, Tuple, Any | |
| class SeparatorStyle(Enum): | |
| """Different separator style.""" | |
| SINGLE = auto() | |
| TWO = auto() | |
| DOLLY = auto() | |
| OASST_PYTHIA = auto() | |
| BAIZE = auto() | |
| class Conversation: | |
| """A class that keeps all conversation history.""" | |
| system: str | |
| roles: List[str] | |
| messages: List[List[str]] | |
| offset: int | |
| sep_style: SeparatorStyle = SeparatorStyle.SINGLE | |
| sep: str = "###" | |
| sep2: str = None | |
| # Used for the state in the gradio servers. | |
| # TODO(lmzheng): refactor this | |
| conv_id: Any = None | |
| skip_next: bool = False | |
| model_name: str = None | |
| def get_prompt(self): | |
| if self.sep_style == SeparatorStyle.SINGLE: | |
| ret = self.system | |
| for role, message in self.messages: | |
| if message: | |
| ret += self.sep + " " + role + ": " + message | |
| else: | |
| ret += self.sep + " " + role + ":" | |
| return ret | |
| elif self.sep_style == SeparatorStyle.TWO: | |
| seps = [self.sep, self.sep2] | |
| ret = self.system + 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.DOLLY: | |
| seps = [self.sep, self.sep2] | |
| ret = self.system | |
| 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.OASST_PYTHIA: | |
| ret = self.system | |
| for role, message in self.messages: | |
| if message: | |
| ret += role + message + self.sep | |
| else: | |
| ret += role | |
| return ret | |
| elif self.sep_style == SeparatorStyle.BAIZE: | |
| ret = self.system | |
| for role, message in self.messages: | |
| if message: | |
| ret += "\n" + role + message | |
| else: | |
| ret += "\n" + role | |
| return ret | |
| else: | |
| raise ValueError(f"Invalid style: {self.sep_style}") | |
| def append_message(self, role, message): | |
| self.messages.append([role, message]) | |
| def to_gradio_chatbot(self): | |
| 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 copy(self): | |
| return Conversation( | |
| system=self.system, | |
| 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, | |
| conv_id=self.conv_id, | |
| model_name=self.model_name, | |
| ) | |
| def dict(self): | |
| return { | |
| "system": self.system, | |
| "roles": self.roles, | |
| "messages": self.messages, | |
| "offset": self.offset, | |
| "sep": self.sep, | |
| "sep2": self.sep2, | |
| "conv_id": self.conv_id, | |
| "model_name": self.model_name, | |
| } | |
| conv_one_shot = Conversation( | |
| 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.", | |
| roles=("Human", "Assistant"), | |
| messages=( | |
| ( | |
| "Human", | |
| "What are the key differences between renewable and non-renewable energy sources?", | |
| ), | |
| ( | |
| "Assistant", | |
| "Renewable energy sources are those that can be replenished naturally in a relatively " | |
| "short amount of time, such as solar, wind, hydro, geothermal, and biomass. " | |
| "Non-renewable energy sources, on the other hand, are finite and will eventually be " | |
| "depleted, such as coal, oil, and natural gas. Here are some key differences between " | |
| "renewable and non-renewable energy sources:\n" | |
| "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable " | |
| "energy sources are finite and will eventually run out.\n" | |
| "2. Environmental impact: Renewable energy sources have a much lower environmental impact " | |
| "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, " | |
| "and other negative effects.\n" | |
| "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically " | |
| "have lower operational costs than non-renewable sources.\n" | |
| "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote " | |
| "locations than non-renewable sources.\n" | |
| "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different " | |
| "situations and needs, while non-renewable sources are more rigid and inflexible.\n" | |
| "6. Sustainability: Renewable energy sources are more sustainable over the long term, while " | |
| "non-renewable sources are not, and their depletion can lead to economic and social instability.", | |
| ), | |
| ), | |
| offset=2, | |
| sep_style=SeparatorStyle.SINGLE, | |
| sep="###", | |
| ) | |
| conv_vicuna_v1_1 = Conversation( | |
| 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.", | |
| roles=("USER", "ASSISTANT"), | |
| messages=(), | |
| offset=0, | |
| sep_style=SeparatorStyle.TWO, | |
| sep=" ", | |
| sep2="</s>", | |
| ) | |
| conv_koala_v1 = Conversation( | |
| system="BEGINNING OF CONVERSATION:", | |
| roles=("USER", "GPT"), | |
| messages=(), | |
| offset=0, | |
| sep_style=SeparatorStyle.TWO, | |
| sep=" ", | |
| sep2="</s>", | |
| ) | |
| conv_dolly = Conversation( | |
| system="Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n", | |
| roles=("### Instruction", "### Response"), | |
| messages=(), | |
| offset=0, | |
| sep_style=SeparatorStyle.DOLLY, | |
| sep="\n\n", | |
| sep2="### End", | |
| ) | |
| conv_oasst = Conversation( | |
| system="", | |
| roles=("<|prompter|>", "<|assistant|>"), | |
| messages=(), | |
| offset=0, | |
| sep_style=SeparatorStyle.OASST_PYTHIA, | |
| sep="<|endoftext|>", | |
| ) | |
| conv_stablelm = Conversation( | |
| system="""<|SYSTEM|># StableLM Tuned (Alpha version) | |
| - StableLM is a helpful and harmless open-source AI language model developed by StabilityAI. | |
| - StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user. | |
| - StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes. | |
| - StableLM will refuse to participate in anything that could harm a human. | |
| """, | |
| roles=("<|USER|>", "<|ASSISTANT|>"), | |
| messages=(), | |
| offset=0, | |
| sep_style=SeparatorStyle.OASST_PYTHIA, | |
| sep="", | |
| ) | |
| conv_baize = Conversation( | |
| system="The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.", | |
| roles=("[|Human|]", "[|AI|]"), | |
| messages=( | |
| ("[|Human|]", "Hello!"), | |
| ("[|AI|]", "Hi!"), | |
| ), | |
| offset=2, | |
| sep_style=SeparatorStyle.BAIZE, | |
| sep="[|Human|]", | |
| ) | |
| conv_templates = { | |
| "conv_one_shot": conv_one_shot, | |
| "vicuna_v1.1": conv_vicuna_v1_1, | |
| "koala_v1": conv_koala_v1, | |
| "dolly": conv_dolly, | |
| "oasst": conv_oasst, | |
| "baize": conv_baize, | |
| } | |
| def get_default_conv_template(model_name): | |
| model_name = model_name.lower() | |
| if "vicuna" in model_name or "output" in model_name: | |
| return conv_vicuna_v1_1 | |
| elif "koala" in model_name: | |
| return conv_koala_v1 | |
| elif "dolly-v2" in model_name: | |
| return conv_dolly | |
| elif "oasst" in model_name and "pythia" in model_name: | |
| return conv_oasst | |
| elif "baize" in model_name: | |
| return conv_baize | |
| elif "stablelm" in model_name: | |
| return conv_stablelm | |
| return conv_one_shot | |
| def compute_skip_echo_len(model_name, conv, prompt): | |
| model_name = model_name.lower() | |
| if "chatglm" in model_name: | |
| skip_echo_len = len(conv.messages[-2][1]) + 1 | |
| elif "dolly-v2" in model_name: | |
| special_toks = ["### Instruction:", "### Response:", "### End"] | |
| skip_echo_len = len(prompt) | |
| for tok in special_toks: | |
| skip_echo_len -= prompt.count(tok) * len(tok) | |
| elif "oasst" in model_name and "pythia" in model_name: | |
| special_toks = ["<|prompter|>", "<|assistant|>", "<|endoftext|>"] | |
| skip_echo_len = len(prompt) | |
| for tok in special_toks: | |
| skip_echo_len -= prompt.count(tok) * len(tok) | |
| elif "stablelm" in model_name: | |
| special_toks = ["<|SYSTEM|>", "<|USER|>", "<|ASSISTANT|>"] | |
| skip_echo_len = len(prompt) | |
| for tok in special_toks: | |
| skip_echo_len -= prompt.count(tok) * len(tok) | |
| elif "baize" in model_name: | |
| skip_echo_len = len(prompt) | |
| else: | |
| skip_echo_len = len(prompt) + 1 - prompt.count("</s>") * 3 | |
| return skip_echo_len | |
| if __name__ == "__main__": | |
| default_conversation = conv_templates["vicuna_v1.1"] | |
| print(default_conversation.get_prompt()) | |