import dataclasses from enum import auto, Enum from typing import List, Any, Dict, Union, Tuple import re import base64 from io import BytesIO from PIL import Image from transformers import AutoTokenizer import os if 'EVALUATION' in os.environ: # highresxpatch EVALUATION = True print(f"EVALUATION is set") else: EVALUATION = False class SeparatorStyle(Enum): """Different separator style.""" SINGLE = auto() TWO = auto() MPT = auto() PLAIN = auto() CHATML = auto() LLAMA_2 = auto() LLAMA_3 = auto() QWEN2 = auto() QWEN = 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" tokenizer_id: str = "" tokenizer: Any = 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 skip_next: bool = False def get_prompt(self): messages = self.messages if len(messages) > 0 and type(messages[0][1]) is tuple: messages = self.messages.copy() init_role, init_msg = messages[0].copy() init_msg = init_msg[0] if "mmtag" in self.version: init_msg = init_msg.replace("", "").strip() messages[0] = (init_role, init_msg) messages.insert(0, (self.roles[0], "")) messages.insert(1, (self.roles[1], "Received.")) elif not init_msg.startswith(""): init_msg = init_msg.replace("", "").strip() messages[0] = (init_role, "\n" + init_msg) else: messages[0] = (init_role, init_msg) if self.sep_style == SeparatorStyle.SINGLE: ret = self.system + self.sep for role, message in messages: if message: if type(message) is tuple: message, _, _ = message ret += role + ": " + message + self.sep else: ret += role + ":" elif self.sep_style == SeparatorStyle.TWO: seps = [self.sep, self.sep2] ret = self.system + seps[0] for i, (role, message) in enumerate(messages): if message: if type(message) is tuple: message, _, _ = message ret += role + ": " + message + seps[i % 2] else: ret += role + ":" elif self.sep_style == SeparatorStyle.CHATML: ret = "" if self.system == "" else self.system + self.sep + "\n" for role, message in messages: if message: if type(message) is tuple: message, images = message message = "" * len(images) + message ret += role + "\n" + message + self.sep + "\n" else: ret += role + "\n" return ret elif self.sep_style == SeparatorStyle.LLAMA_3: chat_template_messages = [{"role": "system", "content": self.system}] for role, message in messages: if message: if type(message) is tuple: message, images = message message = "" * len(images) + message chat_template_messages.append({"role": role, "content": message}) if EVALUATION: return self.tokenizer.apply_chat_template(chat_template_messages, tokenize=False, add_generation_prompt=True) else: return self.tokenizer.apply_chat_template(chat_template_messages, tokenize=False, add_generation_prompt=False) elif self.sep_style == SeparatorStyle.MPT: ret = self.system + self.sep for role, message in messages: if message: if type(message) is tuple: message, _, _ = message ret += role + message + self.sep else: ret += role elif self.sep_style == SeparatorStyle.LLAMA_2: wrap_sys = lambda msg: f"<>\n{msg}\n<>\n\n" if len(msg) > 0 else msg wrap_inst = lambda msg: f"[INST] {msg} [/INST]" ret = "" for i, (role, message) in enumerate(messages): if i == 0: assert message, "first message should not be none" assert role == self.roles[0], "first message should come from user" if message: if type(message) is tuple: message, _, _ = message if i == 0: message = wrap_sys(self.system) + message if i % 2 == 0: message = wrap_inst(message) ret += self.sep + message else: ret += " " + message + " " + self.sep2 else: ret += "" ret = ret.lstrip(self.sep) elif self.sep_style == SeparatorStyle.PLAIN: seps = [self.sep, self.sep2] ret = self.system for i, (role, message) in enumerate(messages): if message: if type(message) is tuple: message, _, _ = message ret += message + seps[i % 2] else: ret += "" elif self.sep_style == SeparatorStyle.QWEN2: start = '<|im_start|>' end = '<|im_end|>\n' ret = start + 'system\n' + self.system + end for i, (role, message) in enumerate(messages): if message: if type(message) is tuple: message, _, _ = message if message.endswith('<|endoftext|>'): message = message.replace('<|endoftext|>', '') ret += start + role + "\n" + message + end + '<|endoftext|>' else: assert not '<|endoftext|>' in message, f"Invalid message: {message}" ret += start + role + "\n" + message + end else: ret += start + role + "\n" else: raise ValueError(f"Invalid style: {self.sep_style}") return ret def append_message(self, role, message): self.messages.append([role, message]) def process_image(self, image, image_process_mode, return_pil=False, image_format="PNG"): 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 in ["Default", "Crop"]: pass elif image_process_mode == "Resize": image = image.resize((336, 336)) else: raise ValueError(f"Invalid image_process_mode: {image_process_mode}") if type(image) is not Image.Image: image = Image.open(image).convert("RGB") max_hw, min_hw = max(image.size), min(image.size) aspect_ratio = max_hw / min_hw max_len, min_len = 672, 448 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: return image else: buffered = BytesIO() image.save(buffered, format=image_format) img_b64_str = base64.b64encode(buffered.getvalue()).decode() return img_b64_str def get_images(self, return_pil=False, return_path=False): images = [] for i, (role, msg) in enumerate(self.messages[self.offset :]): if i % 2 == 0: if type(msg) is tuple: msg, image, image_process_mode = msg if type(image) != list: image = [image] for img in image: if not return_path: img = self.process_image(img, image_process_mode, return_pil=return_pil) else: images.append(img) 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: msg, image, image_process_mode = msg if type(image) != list: image = [image] if len(image) == 1: msg = "\n" + msg.replace("", "").strip() else: msg = re.sub(r"()\n(?=)", r"\1 ", msg) for img in image: img_b64_str = self.process_image(img, "Default", return_pil=False, image_format="JPEG") img_str = f'' msg = msg.replace("", img_str, 1).strip() if len(msg) > 0: ret.append([msg, None]) else: 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, version=self.version) 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_vicuna_v0 = 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 = 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="", ) conv_qwen_v1 = Conversation( system="You are a helpful assistant.", roles=("user", "assistant"), version="v1", messages=(), offset=0, sep_style=SeparatorStyle.QWEN2, ) conv_llama_2 = Conversation( 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. 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.""", roles=("USER", "ASSISTANT"), version="llama_v2", messages=[], offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_llava_llama_2 = Conversation( system="You are a helpful language and vision assistant. " "You are able to understand the visual content that the user provides, " "and assist the user with a variety of tasks using natural language.", roles=("USER", "ASSISTANT"), version="llama_v2", messages=[], offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_mistral_instruct = Conversation( system="", roles=("USER", "ASSISTANT"), version="llama_v2", messages=[], offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_llava_llama_2_simple = Conversation( system="Answer the questions about the visual content that the user provides.", roles=("USER", "ASSISTANT"), version="llama_v2", messages=[], offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_llava_llama_2_mmtag = Conversation( system="Answer the questions about the visual content that the user provides." "The visual content will be provided with the following format: visual content.", roles=("USER", "ASSISTANT"), version="llama_v2_mmtag", messages=[], offset=0, sep_style=SeparatorStyle.LLAMA_2, sep="", sep2="", ) conv_mpt = Conversation( system="""<|im_start|>system A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""", roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), version="mpt", messages=[], offset=0, sep_style=SeparatorStyle.MPT, sep="<|im_end|>", ) conv_qwen = Conversation( system="""<|im_start|>system You are a helpful assistant.""", roles=("<|im_start|>user", "<|im_start|>assistant"), version="qwen", messages=[], offset=0, sep_style=SeparatorStyle.CHATML, sep="<|im_end|>", ) conv_llava_plain = Conversation( system="", roles=("", ""), messages=[], offset=0, sep_style=SeparatorStyle.PLAIN, sep="\n", ) conv_llava_v0 = 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=[], offset=0, sep_style=SeparatorStyle.SINGLE, sep="###", ) conv_llava_v0_mmtag = Conversation( system="A chat between a curious user and an artificial intelligence assistant. " "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." "The visual content will be provided with the following format: visual content.", roles=("Human", "Assistant"), messages=[], offset=0, sep_style=SeparatorStyle.SINGLE, sep="###", version="v0_mmtag", ) conv_llava_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=("USER", "ASSISTANT"), version="v1", messages=[], offset=0, sep_style=SeparatorStyle.TWO, sep=" ", sep2="", ) conv_llava_v1_mmtag = Conversation( system="A chat between a curious user and an artificial intelligence assistant. " "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." "The visual content will be provided with the following format: visual content.", roles=("USER", "ASSISTANT"), messages=[], offset=0, sep_style=SeparatorStyle.TWO, sep=" ", sep2="", version="v1_mmtag", ) conv_mistral_orca = Conversation( system="""<|im_start|>system You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!""", roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), version="mpt", messages=[], offset=0, sep_style=SeparatorStyle.MPT, sep="<|im_end|>", ) conv_mistral_zephyr = Conversation( system="""<|system|> You are a helpful AI assistant.""", roles=("<|user|>\n", "<|assistant|>\n"), version="mpt", messages=[], offset=0, sep_style=SeparatorStyle.MPT, sep="", ) conv_mistral_direct = Conversation( system="""<|im_start|>system Answer the questions.""", roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), version="mpt", messages=[], offset=0, sep_style=SeparatorStyle.MPT, sep="<|im_end|>", ) conv_chatml_direct = Conversation( system="""<|im_start|>system Answer the questions.""", roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), version="mpt", messages=[], offset=0, sep_style=SeparatorStyle.MPT, sep="<|im_end|>", ) default_conversation = conv_vicuna_v0 conv_templates = { "default": conv_vicuna_v0, "v0": conv_vicuna_v0, "v1": conv_vicuna_v1, "vicuna_v1": conv_vicuna_v1, 'v1_qwen2': conv_qwen_v1, "llama_2": conv_llama_2, "mistral_instruct": conv_mistral_instruct, "mistral_orca": conv_mistral_orca, "mistral_zephyr": conv_mistral_zephyr, "mistral_direct": conv_mistral_direct, "plain": conv_llava_plain, "v0_plain": conv_llava_plain, "chatml_direct": conv_chatml_direct, "llava_v0": conv_llava_v0, "llava_v0_mmtag": conv_llava_v0_mmtag, "llava_v1": conv_llava_v1, "llava_v1_mmtag": conv_llava_v1_mmtag, "llava_llama_2": conv_llava_llama_2, "llava_llama_2_simple": conv_llava_llama_2_simple, "llava_llama_2_mmtag": conv_llava_llama_2_mmtag, "llava_mistral_instruct": conv_mistral_instruct, "mpt": conv_mpt, "qwen_1_5": conv_qwen, }