mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
a75618df24
* Update TensorRT-LLM --------- Co-authored-by: 0xymoro <jerrymeng100@gmail.com> Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
64 lines
2.1 KiB
Python
Executable File
64 lines
2.1 KiB
Python
Executable File
# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
# 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 .baichuan.model import BaichuanForCausalLM
|
|
from .bert.model import BertForQuestionAnswering, BertModel
|
|
from .bloom.model import BloomForCausalLM, BloomModel
|
|
from .chatglm.model import ChatGLMHeadModel, ChatGLMModel
|
|
from .enc_dec.model import DecoderModel, EncoderModel, WhisperEncoder
|
|
from .falcon.model import FalconForCausalLM, FalconModel
|
|
from .gpt.model import GPTLMHeadModel, GPTModel
|
|
from .gptj.model import GPTJForCausalLM, GPTJModel
|
|
from .gptneox.model import GPTNeoXForCausalLM, GPTNeoXModel
|
|
from .llama.model import LLaMAForCausalLM, LLaMAModel
|
|
from .modeling_utils import PretrainedConfig, PretrainedModel
|
|
from .opt.model import OPTForCausalLM, OPTModel
|
|
from .qwen.model import QWenForCausalLM
|
|
|
|
from .quantized.quant import quantize_model # noqa # isort:skip
|
|
|
|
__all__ = [
|
|
'BertModel',
|
|
'BertForQuestionAnswering',
|
|
'BloomModel',
|
|
'BloomForCausalLM',
|
|
'FalconForCausalLM',
|
|
'FalconModel',
|
|
'GPTModel',
|
|
'GPTLMHeadModel',
|
|
'OPTForCausalLM',
|
|
'OPTModel',
|
|
'LLaMAForCausalLM',
|
|
'LLaMAModel',
|
|
'GPTJModel',
|
|
'GPTJForCausalLM',
|
|
'GPTNeoXModel',
|
|
'GPTNeoXForCausalLM',
|
|
'quantize_model',
|
|
'ChatGLMHeadModel',
|
|
'ChatGLMModel',
|
|
'BaichuanForCausalLM',
|
|
'QWenForCausalLM',
|
|
'EncoderModel',
|
|
'DecoderModel',
|
|
'PretrainedConfig',
|
|
'PretrainedModel',
|
|
'WhisperEncoder',
|
|
]
|
|
|
|
MODEL_MAP = {
|
|
'OPTForCausalLM': OPTForCausalLM,
|
|
'BloomForCausalLM': BloomForCausalLM,
|
|
}
|