Spaces:
Running
on
T4
Running
on
T4
File size: 13,795 Bytes
5920b49 |
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 |
def get_question_text(problem):
question = problem['question']
return question
def get_context_text(problem, use_caption):
txt_context = problem['hint']
img_context = problem['caption'] if use_caption else ""
context = " ".join([txt_context, img_context]).strip()
if context == "":
context = "N/A"
return context
def get_choice_text(probelm, options):
choices = probelm['choices']
choice_list = []
for i, c in enumerate(choices):
choice_list.append("({}) {}".format(options[i], c))
choice_txt = " ".join(choice_list)
#print(choice_txt)
return choice_txt
def get_answer(problem, options):
return options[problem['answer']]
def get_lecture_text(problem):
# \\n: GPT-3 can generate the lecture with more tokens.
lecture = problem['lecture'].replace("\n", "\\n")
return lecture
def get_solution_text(problem):
# \\n: GPT-3 can generate the solution with more tokens
solution = problem['solution'].replace("\n", "\\n")
return solution
def create_one_example_chatbot(format, question, context, choice, answer, lecture, solution, test_example=True):
input_format, output_format = format.split("-")
## Inputs
if input_format == "CQM":
input = f"Context: {context}\nQuestion: {question}\nOptions: {choice}\n"
elif input_format == "QCM":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\n"
# upper bound experiment
elif input_format == "QCML":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture}\n"
elif input_format == "QCME":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {solution}\n"
elif input_format == "QCMLE":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture} {solution}\n"
elif input_format == "QCLM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture}\nOptions: {choice}\n"
elif input_format == "QCEM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {solution}\nOptions: {choice}\n"
elif input_format == "QCLEM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture} {solution}\nOptions: {choice}\n"
# Outputs
if test_example:
output = "Answer:"
elif output_format == 'A':
output = f"Answer: The answer is {answer}."
elif output_format == 'AL':
output = f"Answer: The answer is {answer}. BECAUSE: {solution}"
elif output_format == 'AE':
output = f"Answer: The answer is {answer}. BECAUSE: {lecture}"
elif output_format == 'ALE':
output = f"Answer: The answer is {answer}. BECAUSE: {lecture} {solution}"
elif output_format == 'AEL':
output = f"Answer: The answer is {answer}. BECAUSE: {solution} {lecture}"
elif output_format == 'LA':
output = f"Answer: {lecture} The answer is {answer}."
elif output_format == 'EA':
output = f"Answer: {solution} The answer is {answer}."
elif output_format == 'LEA':
output = f"Answer: {lecture} {solution} The answer is {answer}."
elif output_format == 'ELA':
output = f"Answer: {solution} {lecture} The answer is {answer}."
elif output_format == 'LEPA':
output = ''
if len(lecture.strip()) > 0:
output += f"LECTURE: {lecture}\n"
if len(solution.strip()) > 0:
output += f"SOLUTION: {solution}\n"
output += '###\n'
output += f"ANSWER: {answer}."
input = input.replace(" ", " ").strip()
output = output.replace(" ", " ").strip()
if input.endswith("BECAUSE:"):
input = input.replace("BECAUSE:", "").strip()
if output.endswith("BECAUSE:"):
output = output.replace("BECAUSE:", "").strip()
return input, output
def create_one_example(format, question, context, choice, answer, lecture, solution, test_example=True):
input_format, output_format = format.split("-")
## Inputs
if input_format == "CQM":
input = f"Context: {context}\nQuestion: {question}\nOptions: {choice}\n"
elif input_format == "QCM":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\n"
# upper bound experiment
elif input_format == "QCML":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture}\n"
elif input_format == "QCME":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {solution}\n"
elif input_format == "QCMLE":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture} {solution}\n"
elif input_format == "QCLM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture}\nOptions: {choice}\n"
elif input_format == "QCEM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {solution}\nOptions: {choice}\n"
elif input_format == "QCLEM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture} {solution}\nOptions: {choice}\n"
# Outputs
if test_example:
output = "Answer:"
elif output_format == 'A':
output = f"Answer: The answer is {answer}."
elif output_format == 'AL':
output = f"Answer: The answer is {answer}. BECAUSE: {solution}"
elif output_format == 'AE':
output = f"Answer: The answer is {answer}. BECAUSE: {lecture}"
elif output_format == 'ALE':
output = f"Answer: The answer is {answer}. BECAUSE: {lecture} {solution}"
elif output_format == 'AEL':
output = f"Answer: The answer is {answer}. BECAUSE: {solution} {lecture}"
elif output_format == 'LA':
output = f"Answer: {lecture} The answer is {answer}."
elif output_format == 'EA':
output = f"Answer: {solution} The answer is {answer}."
elif output_format == 'LEA':
output = f"Answer: {lecture} {solution} The answer is {answer}."
elif output_format == 'ELA':
output = f"Answer: {solution} {lecture} The answer is {answer}."
text = input + output
text = text.replace(" ", " ").strip()
if text.endswith("BECAUSE:"):
text = text.replace("BECAUSE:", "").strip()
return text
def create_one_example_gpt4(format, question, context, choice, answer, lecture, solution, test_example=True):
input_format, output_format = format.split("-")
## Inputs
if input_format == "CQM":
input = f"Context: {context}\nQuestion: {question}\nOptions: {choice}\n"
elif input_format == "QCM":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\n"
# upper bound experiment
elif input_format == "QCML":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture}\n"
elif input_format == "QCME":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {solution}\n"
elif input_format == "QCMLE":
input = f"Question: {question}\nContext: {context}\nOptions: {choice}\nBECAUSE: {lecture} {solution}\n"
elif input_format == "QCLM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture}\nOptions: {choice}\n"
elif input_format == "QCEM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {solution}\nOptions: {choice}\n"
elif input_format == "QCLEM":
input = f"Question: {question}\nContext: {context}\nBECAUSE: {lecture} {solution}\nOptions: {choice}\n"
# Outputs
if test_example:
output = "Answer:"
elif output_format == 'A':
output = f"Answer: The answer is {answer}."
elif output_format == 'AL':
output = f"Answer: The answer is {answer}. BECAUSE: {solution}"
elif output_format == 'AE':
output = f"Answer: The answer is {answer}. BECAUSE: {lecture}"
elif output_format == 'ALE':
output = f"Answer: The answer is {answer}. BECAUSE: {lecture} {solution}"
elif output_format == 'AEL':
output = f"Answer: The answer is {answer}. BECAUSE: {solution} {lecture}"
elif output_format == 'LA':
output = f"Answer: {lecture} The answer is {answer}."
elif output_format == 'EA':
output = f"Answer: {solution} The answer is {answer}."
elif output_format == 'LEA':
output = f"Answer: {lecture} {solution} The answer is {answer}."
elif output_format == 'ELA':
output = f"Answer: {solution} {lecture} The answer is {answer}."
input = input.replace(" ", " ").strip()
output = output.replace(" ", " ").strip()
if output.endswith("BECAUSE:"):
output = output.replace("BECAUSE:", "").strip()
user_prompt = {"role": "user", "content": f"Can you explain {input}?"}
assistant_prompt = {"role": "assistant", "content": f"{output}"}
return user_prompt, assistant_prompt
def build_prompt_chatbot(problems, shot_qids, prompt_format, use_caption=False, options=["A", "B", "C", "D", "E"], is_test=False):
examples = {}
for qid in shot_qids:
question = get_question_text(problems[qid])
context = get_context_text(problems[qid], use_caption)
choice = get_choice_text(problems[qid], options)
answer = get_answer(problems[qid], options)
lecture = get_lecture_text(problems[qid]).replace('\\n', '\n')
solution = get_solution_text(problems[qid]).replace('\\n', '\n')
train_example = create_one_example_chatbot(prompt_format,
question,
context,
choice,
answer,
lecture,
solution,
test_example=is_test)
examples[qid] = train_example
return examples
def build_prompt(problems, shot_qids, test_qid, args):
examples = []
# n-shot training examples
for qid in shot_qids:
question = get_question_text(problems[qid])
context = get_context_text(problems[qid], args.use_caption)
choice = get_choice_text(problems[qid], args.options)
answer = get_answer(problems[qid], args.options)
lecture = get_lecture_text(problems[qid])
solution = get_solution_text(problems[qid])
train_example = create_one_example(args.prompt_format,
question,
context,
choice,
answer,
lecture,
solution,
test_example=False)
examples.append(train_example)
# test example
question = get_question_text(problems[test_qid])
context = get_context_text(problems[test_qid], args.use_caption)
choice = get_choice_text(problems[test_qid], args.options)
answer = get_answer(problems[test_qid], args.options)
lecture = get_lecture_text(problems[test_qid])
solution = get_solution_text(problems[test_qid])
test_example = create_one_example(args.prompt_format,
question,
context,
choice,
answer,
lecture,
solution,
test_example=True)
examples.append(test_example)
# create the prompt input
prompt_input = '\n\n'.join(examples)
return prompt_input
def build_prompt_gpt4(problems, shot_qids, test_qid, args):
prompt_array = [{"role": "system", "content": "You are a helpful assistant."}]
# n-shot training examples
for qid in shot_qids:
question = get_question_text(problems[qid])
context = get_context_text(problems[qid], args.use_caption)
choice = get_choice_text(problems[qid], args.options)
answer = get_answer(problems[qid], args.options)
lecture = get_lecture_text(problems[qid])
solution = get_solution_text(problems[qid])
user_prompt, assistant_prompt = create_one_example_gpt4(args.prompt_format,
question,
context,
choice,
answer,
lecture,
solution,
test_example=False)
prompt_array.append(user_prompt)
prompt_array.append(assistant_prompt)
# test example
question = get_question_text(problems[test_qid])
context = get_context_text(problems[test_qid], args.use_caption)
choice = get_choice_text(problems[test_qid], args.options)
answer = get_answer(problems[test_qid], args.options)
lecture = get_lecture_text(problems[test_qid])
solution = get_solution_text(problems[test_qid])
user_prompt, assistant_prompt = create_one_example_gpt4(args.prompt_format,
question,
context,
choice,
answer,
lecture,
solution,
test_example=True)
prompt_array.append(user_prompt)
prompt_array.append(assistant_prompt)
return prompt_array |