File size: 20,301 Bytes
ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e 0fb0588 ba1211e |
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 |
import dataclasses
from enum import auto, Enum
from typing import List, Tuple
import base64
from io import BytesIO
from PIL import Image
VOCAB_IMAGE_W = 1000 # 224
VOCAB_IMAGE_H = 1000 # 224
class SeparatorStyle(Enum):
"""Different separator style."""
SINGLE = auto()
TWO = auto()
MPT = auto()
PLAIN = auto()
LLAMA_2 = auto()
GEMMA = 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):
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].replace("<image>", "").strip()
if 'mmtag' in self.version:
messages[0] = (init_role, init_msg)
messages.insert(0, (self.roles[0], "<Image><image></Image>"))
messages.insert(1, (self.roles[1], "Received."))
else:
messages[0] = (init_role, "<image>\n" + 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.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"<<SYS>>\n{msg}\n<</SYS>>\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.GEMMA:
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 += "<start_of_turn>" + role + "\n" + message + "<end_of_turn>\n" + seps[i % 2]
else:
ret += "<start_of_turn>" + role + "\n"
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 += ""
else:
raise ValueError(f"Invalid style: {self.sep_style}")
return ret
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 in ["Default", "Crop"]:
pass
elif image_process_mode == "Raw+Processor":
pass
elif image_process_mode == "Resize":
image = image.resize((336, 336))
else:
raise ValueError(f"Invalid image_process_mode: {image_process_mode}")
if image_process_mode != "Raw+Processor":
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))
print('Input Image Size:{}'.format(image.size))
if return_pil:
images.append(image)
else:
buffered = BytesIO()
image.save(buffered, format="PNG")
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
if image_process_mode != "Raw+Processor":
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" />'
ret.append([img_str, None])
msg = msg.replace('<image>', '').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="</s>",
)
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="<s>",
sep2="</s>",
)
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="<s>",
sep2="</s>",
)
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_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: <Image>visual content</Image>.",
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="</s>",
)
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: <Image>visual content</Image>.",
roles=("USER", "ASSISTANT"),
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep=" ",
sep2="</s>",
version="v1_mmtag",
)
conv_mistral_instruct = Conversation(
system="",
roles=("USER", "ASSISTANT"),
version="llama_v2",
messages=(),
offset=0,
sep_style=SeparatorStyle.LLAMA_2,
sep="",
sep2="</s>",
)
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|>",
)
conv_llava_llama_3 = Conversation(
system="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou 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=("<|start_header_id|>user<|end_header_id|>\n\n",
"<|start_header_id|>assistant<|end_header_id|>\n\n"),
version="llama3",
messages=[],
offset=0,
sep_style=SeparatorStyle.MPT,
sep="<|eot_id|>",
)
conv_ferret_llama_plain = Conversation(
system="",
roles=("", ""),
messages=(
),
offset=0,
sep_style=SeparatorStyle.PLAIN,
sep="\n",
)
conv_ferret_vicuna_v1 = Conversation(
system="A chat between a human and an AI that understands visuals. "
"In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. "
"Increasing x moves right; y moves down. "
f"Bounding box: [x1, y1, x2, y2]. Image size: {VOCAB_IMAGE_W}x{VOCAB_IMAGE_H}. "
"Follow instructions.",
roles=("USER", "ASSISTANT"),
version="v1",
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep=" ",
sep2="</s>",
)
conv_ferret_llama_3 = Conversation(
system="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nA chat between a human and an AI that understands visuals. "
"In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. "
"Increasing x moves right; y moves down. "
f"Bounding box: [x1, y1, x2, y2]. Image size: {VOCAB_IMAGE_W}x{VOCAB_IMAGE_H}. "
"Follow instructions.",
roles=("<|start_header_id|>user<|end_header_id|>\n\n",
"<|start_header_id|>assistant<|end_header_id|>\n\n"),
version="llama3",
messages=[],
offset=0,
sep_style=SeparatorStyle.MPT,
sep="<|eot_id|>",
)
conv_ferret_gemma_plain = Conversation(
system="",
roles=("user", "model"),
version="gemma",
messages=(),
offset=0,
sep_style=SeparatorStyle.GEMMA,
sep="",
sep2="<eos>",
)
conv_ferret_gemma_instruct = Conversation(
system="A chat between a human and an AI that understands visuals. "
"In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. "
"Increasing x moves right; y moves down. "
f"Bounding box: [x1, y1, x2, y2]. Image size: {VOCAB_IMAGE_W}x{VOCAB_IMAGE_H}. "
"Follow instructions.",
roles=("user", "model"),
version="gemma",
messages=(),
offset=0,
sep_style=SeparatorStyle.GEMMA,
sep="",
sep2="<eos>",
)
conv_ferret_phi3_instruct = Conversation(
system="""<|system|>\nYou are a helpful AI assistant.""",
roles=("\n<|user|>\n", "\n<|assistant|>\n"),
version="phi3",
messages=(),
offset=0,
sep_style=SeparatorStyle.MPT,
sep="<|end|>",
)
default_conversation = conv_vicuna_v1
conv_templates = {
"default": conv_vicuna_v0,
"v0": conv_vicuna_v0,
"v1": conv_vicuna_v1,
"vicuna_v1": conv_vicuna_v1,
"llama_2": conv_llama_2,
"mistral_instruct": conv_mistral_instruct,
"chatml_direct": conv_chatml_direct,
"mistral_direct": conv_chatml_direct,
"plain": conv_llava_plain,
"v0_plain": conv_llava_plain,
"llava_v0": conv_llava_v0,
"v0_mmtag": conv_llava_v0_mmtag,
"llava_v1": conv_llava_v1,
"v1_mmtag": conv_llava_v1_mmtag,
"llava_llama_2": conv_llava_llama_2,
"llava_llama_3": conv_llava_llama_3,
"ferret_llama_plain": conv_ferret_llama_plain,
"ferret_vicuna_v1": conv_ferret_vicuna_v1,
"ferret_llama_3": conv_ferret_llama_3,
"ferret_gemma_plain": conv_ferret_gemma_plain,
"ferret_gemma_instruct": conv_ferret_gemma_instruct,
"ferret_phi3_instruct": conv_ferret_phi3_instruct,
"mpt": conv_mpt,
}
if __name__ == "__main__":
print(default_conversation.get_prompt()) |