File size: 3,218 Bytes
2a26d3b |
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 |
# Copyright 2024 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from dataclasses import dataclass
from enum import Enum, unique
from typing import Dict, List, Sequence, Tuple
CHOICES = ["A", "B", "C", "D"]
@unique
class Role(str, Enum):
USER = "user"
ASSISTANT = "assistant"
SYSTEM = "system"
FUNCTION = "function"
OBSERVATION = "observation"
@dataclass
class EvalTemplate:
system: str
choice: str
answer: str
def _parse_example(self, example: Dict[str, str]) -> Tuple[str, str]:
r"""
input: a dict with keys {"question", "A", "B", "C", "D", "answer"}
output: a tuple of (prompt, response)
"""
candidates = [
self.choice.format(choice=ch, content=example[ch])
for ch in CHOICES
if ch in example
]
return (
"".join([example["question"]] + candidates + [self.answer]),
example["answer"],
)
def format_example(
self,
target_data: Dict[str, str],
support_set: Sequence[Dict[str, str]],
subject_name: str,
) -> List[Dict[str, str]]:
r"""
Converts dataset examples to messages.
"""
messages = []
for k in range(len(support_set)):
prompt, response = self._parse_example(support_set[k])
messages.append({"role": Role.USER.value, "content": prompt})
messages.append({"role": Role.ASSISTANT.value, "content": response})
prompt, response = self._parse_example(target_data)
messages.append({"role": Role.USER.value, "content": prompt})
messages.append({"role": Role.ASSISTANT.value, "content": response})
messages[0]["content"] = (
self.system.format(subject=subject_name) + messages[0]["content"]
)
return messages
eval_templates: Dict[str, "EvalTemplate"] = {}
def _register_eval_template(name: str, system: str, choice: str, answer: str) -> None:
eval_templates[name] = EvalTemplate(system=system, choice=choice, answer=answer)
def get_eval_template(name: str) -> "EvalTemplate":
eval_template = eval_templates.get(name, None)
assert eval_template is not None, "Template {} does not exist.".format(name)
return eval_template
_register_eval_template(
name="en",
system="The following are multiple choice questions (with answers) about {subject}.\n\n",
choice="\n{choice}. {content}",
answer="\nAnswer:",
)
_register_eval_template(
name="zh",
system="以下是中国关于{subject}考试的单项选择题，请选出其中的正确答案。\n\n",
choice="\n{choice}. {content}",
answer="\n答案：",
)
|