File size: 2,938 Bytes
bc55b34 |
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 abc import ABC, abstractmethod
from dataclasses import dataclass
from typing import TYPE_CHECKING, Any, AsyncGenerator, Dict, List, Literal, Optional, Sequence, Union
if TYPE_CHECKING:
from transformers import PreTrainedModel, PreTrainedTokenizer
from vllm import AsyncLLMEngine
from ..data import Template
from ..data.mm_plugin import ImageInput, VideoInput
from ..hparams import DataArguments, FinetuningArguments, GeneratingArguments, ModelArguments
@dataclass
class Response:
response_text: str
response_length: int
prompt_length: int
finish_reason: Literal["stop", "length"]
class BaseEngine(ABC):
r"""
Base class for inference engine of chat models.
Must implements async methods: chat(), stream_chat() and get_scores().
"""
model: Union["PreTrainedModel", "AsyncLLMEngine"]
tokenizer: "PreTrainedTokenizer"
can_generate: bool
template: "Template"
generating_args: Dict[str, Any]
@abstractmethod
def __init__(
self,
model_args: "ModelArguments",
data_args: "DataArguments",
finetuning_args: "FinetuningArguments",
generating_args: "GeneratingArguments",
) -> None:
r"""
Initializes an inference engine.
"""
...
@abstractmethod
async def chat(
self,
messages: Sequence[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
image: Optional["ImageInput"] = None,
video: Optional["VideoInput"] = None,
**input_kwargs,
) -> List["Response"]:
r"""
Gets a list of responses of the chat model.
"""
...
@abstractmethod
async def stream_chat(
self,
messages: Sequence[Dict[str, str]],
system: Optional[str] = None,
tools: Optional[str] = None,
image: Optional["ImageInput"] = None,
video: Optional["VideoInput"] = None,
**input_kwargs,
) -> AsyncGenerator[str, None]:
r"""
Gets the response token-by-token of the chat model.
"""
...
@abstractmethod
async def get_scores(
self,
batch_input: List[str],
**input_kwargs,
) -> List[float]:
r"""
Gets a list of scores of the reward model.
"""
...
|