| import dataclasses |
| from enum import auto, Enum |
| from typing import List, Tuple |
|
|
|
|
| class SeparatorStyle(Enum): |
| """Different separator style.""" |
| SINGLE = auto() |
| TWO = auto() |
|
|
|
|
| @dataclasses.dataclass |
| 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 |
| version: str = "Unknown" |
|
|
| skip_next: bool = False |
|
|
| def get_prompt(self): |
| if self.sep_style == SeparatorStyle.SINGLE: |
| ret = self.system + 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 |
| 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: |
| if type(message) is tuple: |
| message, _, _ = message |
| ret += role + ": " + message + seps[i % 2] |
| else: |
| ret += role + ":" |
| return ret |
| else: |
| raise ValueError(f"Invalid style: {self.sep_style}") |
|
|
| def append_message(self, role, message): |
| self.messages.append([role, message]) |
|
|
| def get_images(self, return_pil=False): |
| images = [] |
| for i, (role, msg) in enumerate(self.messages[self.offset:]): |
| if i % 2 == 0: |
| if type(msg) is tuple: |
| import base64 |
| from io import BytesIO |
| from PIL import Image |
| msg, image, image_process_mode = msg |
| if image_process_mode == "Pad": |
| def expand2square(pil_img, background_color=(122, 116, 104)): |
| width, height = pil_img.size |
| if width == height: |
| return pil_img |
| elif width > height: |
| result = Image.new( |
| pil_img.mode, (width, width), background_color) |
| result.paste( |
| pil_img, (0, (width - height) // 2)) |
| return result |
| else: |
| result = Image.new( |
| pil_img.mode, (height, height), background_color) |
| result.paste( |
| pil_img, ((height - width) // 2, 0)) |
| return result |
| image = expand2square(image) |
| elif image_process_mode == "Crop": |
| pass |
| elif image_process_mode == "Resize": |
| image = image.resize((224, 224)) |
| else: |
| raise ValueError( |
| f"Invalid image_process_mode: {image_process_mode}") |
| max_hw, min_hw = max(image.size), min(image.size) |
| aspect_ratio = max_hw / min_hw |
| max_len, min_len = 800, 400 |
| shortest_edge = int( |
| min(max_len / aspect_ratio, min_len, min_hw)) |
| longest_edge = int(shortest_edge * aspect_ratio) |
| W, H = image.size |
| if H > W: |
| H, W = longest_edge, shortest_edge |
| else: |
| H, W = shortest_edge, longest_edge |
| image = image.resize((W, H)) |
| if return_pil: |
| images.append(image) |
| else: |
| buffered = BytesIO() |
| image.save(buffered, format="JPEG") |
| img_b64_str = base64.b64encode( |
| buffered.getvalue()).decode() |
| images.append(img_b64_str) |
| return images |
|
|
| def to_gradio_chatbot(self): |
| ret = [] |
| for i, (role, msg) in enumerate(self.messages[self.offset:]): |
| if i % 2 == 0: |
| if type(msg) is tuple: |
| import base64 |
| from io import BytesIO |
| msg, image, image_process_mode = msg |
| max_hw, min_hw = max(image.size), min(image.size) |
| aspect_ratio = max_hw / min_hw |
| max_len, min_len = 800, 400 |
| shortest_edge = int( |
| min(max_len / aspect_ratio, min_len, min_hw)) |
| longest_edge = int(shortest_edge * aspect_ratio) |
| W, H = image.size |
| if H > W: |
| H, W = longest_edge, shortest_edge |
| else: |
| H, W = shortest_edge, longest_edge |
| image = image.resize((W, H)) |
| |
| buffered = BytesIO() |
| image.save(buffered, format="JPEG") |
| img_b64_str = base64.b64encode( |
| buffered.getvalue()).decode() |
| img_str = f'<img src="data:image/png;base64,{img_b64_str}" alt="user upload image" />' |
| msg = msg.replace('<image>', img_str) |
| 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) |
|
|
| def dict(self): |
| if len(self.get_images()) > 0: |
| return { |
| "system": self.system, |
| "roles": self.roles, |
| "messages": [[x, y[0] if type(y) is tuple else y] for x, y in self.messages], |
| "offset": self.offset, |
| "sep": self.sep, |
| "sep2": self.sep2, |
| } |
| return { |
| "system": self.system, |
| "roles": self.roles, |
| "messages": self.messages, |
| "offset": self.offset, |
| "sep": self.sep, |
| "sep2": self.sep2, |
| } |
|
|
|
|
| conv_v1 = 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", "Give three tips for staying healthy."), |
| ("Assistant", |
| "Sure, here are three tips for staying healthy:\n" |
| "1. Exercise regularly: Regular physical activity can help improve your overall health and wellbeing. " |
| "It can also help reduce your risk of chronic conditions such as obesity, diabetes, heart disease, " |
| "and certain cancers. Aim for at least 150 minutes of moderate-intensity aerobic exercise or " |
| "75 minutes of vigorous-intensity aerobic exercise per week, along with muscle-strengthening " |
| "activities at least two days per week.\n" |
| "2. Eat a balanced diet: Eating a balanced diet that is rich in fruits, " |
| "vegetables, whole grains, lean proteins, and healthy fats can help support " |
| "your overall health. Try to limit your intake of processed and high-sugar foods, " |
| "and aim to drink plenty of water throughout the day.\n" |
| "3. Get enough sleep: Getting enough quality sleep is essential for your physical " |
| "and mental health. Adults should aim for seven to nine hours of sleep per night. " |
| "Establish a regular sleep schedule and try to create a relaxing bedtime routine to " |
| "help improve the quality of your sleep.") |
| ), |
| offset=2, |
| sep_style=SeparatorStyle.SINGLE, |
| sep="###", |
| ) |
|
|
| conv_v1_2 = 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.\n") |
| ), |
| 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"), |
| version="v1", |
| messages=(), |
| offset=0, |
| sep_style=SeparatorStyle.TWO, |
| sep=" ", |
| sep2="</s>", |
| ) |
|
|
| conv_bair_v1 = Conversation( |
| system="BEGINNING OF CONVERSATION:", |
| roles=("USER", "GPT"), |
| messages=(), |
| offset=0, |
| sep_style=SeparatorStyle.TWO, |
| sep=" ", |
| sep2="</s>", |
| ) |
|
|
| simple_conv = Conversation( |
| system="You are LLaVA, a large language model trained by UW Madison WAIV Lab, based on LLaMA architecture." |
| "You are designed to assist human with a variety of tasks using natural language." |
| "Follow the instructions carefully.", |
| roles=("Human", "Assistant"), |
| messages=( |
| ("Human", "Hi!"), |
| ("Assistant", "Hi there! How can I help you today?\n") |
| ), |
| offset=2, |
| sep_style=SeparatorStyle.SINGLE, |
| sep="###", |
| ) |
|
|
| simple_conv_multimodal = 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=("Human", "Assistant"), |
| messages=( |
| ), |
| offset=0, |
| sep_style=SeparatorStyle.SINGLE, |
| sep="###", |
| ) |
|
|
| simple_conv_legacy = Conversation( |
| system="You are LLaVA, a large language model trained by UW Madison WAIV Lab." |
| "You are designed to assist human with a variety of tasks using natural language." |
| "Follow the instructions carefully.", |
| roles=("Human", "Assistant"), |
| messages=( |
| ("Human", "Hi!\n\n### Response:"), |
| ("Assistant", "Hi there! How can I help you today?\n") |
| ), |
| offset=2, |
| sep_style=SeparatorStyle.SINGLE, |
| sep="###", |
| ) |
|
|
| conv_llava_v1 = Conversation( |
| system="You are LLaVA, a large language and vision assistant trained by UW Madison WAIV Lab." |
| "You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." |
| "Follow the instructions carefully and explain your answers in detail.", |
| roles=("USER", "ASSISTANT"), |
| version="v1", |
| messages=(), |
| offset=0, |
| sep_style=SeparatorStyle.TWO, |
| sep=" ", |
| sep2="</s>", |
| ) |
|
|
| default_conversation = conv_v1_2 |
| conv_templates = { |
| "default": conv_v1_2, |
| "simple": simple_conv, |
| "simple_legacy": simple_conv_legacy, |
| "multimodal": simple_conv_multimodal, |
| "llava_v1": conv_llava_v1, |
|
|
| |
| "v1": conv_v1_2, |
| "bair_v1": conv_bair_v1, |
| "vicuna_v1_1": conv_vicuna_v1_1, |
| } |
|
|
|
|
| if __name__ == "__main__": |
| print(default_conversation.get_prompt()) |
|
|