mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-09-26 20:41:53 +08:00
c86945ef49
* support pool * update pooling * add pooler_config and check * update * support AutoWeightsLoader load weight * fix * update * delete print * update pre-commit * fix * fix xpu * fix ModelRegistry->model_registry * fix Copilot review * fix pooler.py * delete StepPooler * fix abstract * fix default_loader_v1 * fix Pre Commit * support torch qwen3 dense * add test and fix torch-qwen * fix * fix * adapter ci: * fix review * fix pooling_params.py * fix * fix tasks.py 2025 * fix print and logger * Modefy ModelRegistry and delete AutoWeightsLoader * fix logger * fix test_embedding * fix ci bug * ernie4_5 model_registry * fix test * support Qwen3-Embedding-0.6B tp=1 load * fix extra code * fix * delete fix vocab_size * delete prepare_params_dict * fix:
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# 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 paddleformers.transformers import PretrainedModel
|
|
|
|
from fastdeploy.config import ErnieArchitectures
|
|
from fastdeploy.model_executor.models.model_base import ModelForCasualLM, ModelRegistry
|
|
|
|
|
|
class MyPretrainedModel(PretrainedModel):
|
|
@classmethod
|
|
def arch_names(cls):
|
|
return "MyModelForCasualLM"
|
|
|
|
|
|
class MyModelForCasualLM(ModelForCasualLM):
|
|
|
|
def __init__(self, fd_config):
|
|
"""
|
|
Args:
|
|
fd_config : Configurations for the LLM model.
|
|
"""
|
|
super().__init__(fd_config)
|
|
print("init done")
|
|
|
|
@classmethod
|
|
def name(cls):
|
|
return "MyModelForCasualLM"
|
|
|
|
def compute_logits(self, logits):
|
|
logits[:, 0] += 1.0
|
|
return logits
|
|
|
|
|
|
def register():
|
|
if "MyModelForCasualLM" not in ModelRegistry.get_supported_archs():
|
|
if MyModelForCasualLM.name().startswith("Ernie"):
|
|
ErnieArchitectures.register_ernie_model_arch(MyModelForCasualLM)
|
|
ModelRegistry.register_model_class(MyModelForCasualLM)
|
|
ModelRegistry.register_pretrained_model(MyPretrainedModel)
|