mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
26 lines
1.1 KiB
Python
26 lines
1.1 KiB
Python
# 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.
|
|
import transformers
|
|
|
|
prompt = "Could you introduce NVIDIA Corporation for me?"
|
|
|
|
# run the original model to export LM
|
|
tokenizer = transformers.AutoTokenizer.from_pretrained("pyTorchModel",
|
|
trust_remote_code=True)
|
|
model = transformers.AutoModel.from_pretrained(
|
|
"pyTorchModel", trust_remote_code=True).half().cuda()
|
|
|
|
response, history = model.chat(tokenizer, prompt, history=[])
|