bfa1367149
* Change installation address Change former address: "https://docs.conda.io/en/latest/miniconda.html#" to new address: "https://conda-forge.org/download/" for 63 occurrences under python\llm\example * Change Prompt Change "Anaconda Prompt" to "Miniforge Prompt" for 1 occurrence * Create and update model minicpm * Update model minicpm Update model minicpm under GPU/PyTorch-Models * Update readme and generate.py change "prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False)" and delete "pip install transformers==4.37.0 " * Update comments for minicpm GPU Update comments for generate.py at minicpm GPU * Add CPU example for MiniCPM * Update minicpm README for CPU * Update README for MiniCPM and Llama3 * Update Readme for Llama3 CPU Pytorch * Update and fix comments for MiniCPM
74 lines
3 KiB
Python
74 lines
3 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 torch
|
|
import time
|
|
import argparse
|
|
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
from ipex_llm import optimize_model
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for MiniCPM model')
|
|
parser.add_argument('--repo-id-or-model-path', type=str, default="openbmb/MiniCPM-2B-sft-bf16",
|
|
help='The huggingface repo id for the MiniCPM model to be downloaded'
|
|
', or the path to the huggingface checkpoint folder')
|
|
parser.add_argument('--prompt', type=str, default="What is AI?",
|
|
help='Prompt to infer')
|
|
parser.add_argument('--n-predict', type=int, default=32,
|
|
help='Max tokens to predict')
|
|
|
|
args = parser.parse_args()
|
|
model_path = args.repo_id_or_model_path
|
|
|
|
# Load model
|
|
model = AutoModelForCausalLM.from_pretrained(model_path,
|
|
trust_remote_code=True,
|
|
torch_dtype='auto',
|
|
low_cpu_mem_usage=True,
|
|
use_cache=True)
|
|
|
|
# With only one line to enable IPEX-LLM optimization on model
|
|
model = optimize_model(model)
|
|
|
|
# Load tokenizer
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
|
trust_remote_code=True)
|
|
|
|
# Generate predicted tokens
|
|
with torch.inference_mode():
|
|
|
|
# here the prompt formatting refers to: https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16/blob/79fbb1db171e6d8bf77cdb0a94076a43003abd9e/modeling_minicpm.py#L1320
|
|
chat = [
|
|
{ "role": "user", "content": args.prompt },
|
|
]
|
|
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False)
|
|
input_ids = tokenizer.encode(prompt, return_tensors="pt")
|
|
|
|
# start inference
|
|
st = time.time()
|
|
|
|
output = model.generate(input_ids,
|
|
do_sample=False,
|
|
max_new_tokens=args.n_predict)
|
|
end = time.time()
|
|
output_str = tokenizer.decode(output[0], skip_special_tokens=False)
|
|
print(f'Inference time: {end-st} s')
|
|
print('-'*20, 'Prompt', '-'*20)
|
|
print(prompt)
|
|
print('-'*20, 'Output', '-'*20)
|
|
print(output_str)
|