juliensimon's picture
juliensimon HF staff
Upload quantize.yml
13e9bc7
#
# Copyright (c) 2021 Intel Corporation
#
# 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.
version: 1.0
model: # mandatory.
name: bert_prune
framework: pytorch # mandatory. possible values are pytorch and pytorch_fx.
device: cpu
quantization: # optional.
approach: post_training_dynamic_quant
tuning:
accuracy_criterion:
relative: 0.03 # optional. default value is relative, other value is absolute. this example allows relative accuracy loss: 3%.
exit_policy:
timeout: 0 # optional. tuning timeout (seconds). default value is 0 which means early stop. combine with max_trials field to decide when to exit.
max_trials: 30
random_seed: 9527 # optional. random seed for deterministic tuning.