381d448ee2
* Remove model with optimize_model=False in NPU verified models tables, and remove related example * Remove experimental in run optimized model section title * Unify model table order & example cmd * Move embedding example to separate folder & update quickstart example link * Add Quickstart reference in main NPU readme * Small fix * Small fix * Move save/load examples under NPU/HF-Transformers-AutoModels * Add low-bit and polish arguments for LLM Python examples * Small fix * Add low-bit and polish arguments for Multi-Model examples * Polish argument for Embedding models * Polish argument for LLM CPP examples * Add low-bit and polish argument for Save-Load examples * Add accuracy tuning tips for examples * Update NPU qucikstart accuracy tuning with low-bit optimizations * Add save/load section to qucikstart * Update CPP example sample output to EN * Add installation regarding cmake for CPP examples * Small fix * Small fix * Small fix * Small fix * Small fix * Small fix * Unify max prompt length to 512 * Change recommended low-bit for Qwen2.5-3B-Instruct to asym_int4 * Update based on comments * Small fix
72 lines
2.4 KiB
Python
72 lines
2.4 KiB
Python
#
|
|
# Copyright 2016 The BigDL Authors.
|
|
#
|
|
# 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 os
|
|
import time
|
|
import torch
|
|
import argparse
|
|
from ipex_llm.transformers.npu_model import EmbeddingModel
|
|
from transformers.utils import logging
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser(
|
|
description="Predict Tokens using `generate()` API for npu model"
|
|
)
|
|
parser.add_argument(
|
|
"--repo-id-or-model-path",
|
|
type=str,
|
|
default="maidalun1020/bce-embedding-base_v1",
|
|
help="The huggingface repo id for the bce-embedding model to be downloaded"
|
|
", or the path to the huggingface checkpoint folder.",
|
|
)
|
|
parser.add_argument('--prompt', type=str, default="'sentence_0', 'sentence_1'",
|
|
help='Prompt to infer')
|
|
parser.add_argument("--max-context-len", type=int, default=1024)
|
|
parser.add_argument("--max-prompt-len", type=int, default=512)
|
|
parser.add_argument("--save-directory", type=str,
|
|
required=True,
|
|
help="The path of folder to save converted model, "
|
|
"If path not exists, lowbit model will be saved there. "
|
|
"Else, lowbit model will be loaded.",
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
model_path = args.repo_id_or_model_path
|
|
|
|
model = EmbeddingModel(
|
|
model_path,
|
|
torch_dtype=torch.float16,
|
|
trust_remote_code=True,
|
|
attn_implementation="eager",
|
|
optimize_model=True,
|
|
max_context_len=args.max_context_len,
|
|
max_prompt_len=args.max_prompt_len,
|
|
save_directory=args.save_directory
|
|
)
|
|
|
|
# list of sentences
|
|
split_items = args.prompt.split(',')
|
|
sentences = [item.strip().strip("'") for item in split_items]
|
|
|
|
# extract embeddings
|
|
st = time.time()
|
|
embeddings = model.encode(sentences)
|
|
end = time.time()
|
|
print(f'Inference time: {end-st} s')
|
|
print(embeddings)
|