440cfe18ed
* modify aquila * modify aquila2 * add baichuan * modify baichuan2 * modify blue-lm * modify chatglm3 * modify chinese-llama2 * modiy codellama * modify distil-whisper * modify dolly-v1 * modify dolly-v2 * modify falcon * modify flan-t5 * modify gpt-j * modify internlm * modify llama2 * modify mistral * modify mixtral * modify mpt * modify phi-1_5 * modify qwen * modify qwen-vl * modify replit * modify solar * modify starcoder * modify vicuna * modify voiceassistant * modify whisper * modify yi * modify aquila2 * modify baichuan * modify baichuan2 * modify blue-lm * modify chatglm2 * modify chatglm3 * modify codellama * modify distil-whisper * modify dolly-v1 * modify dolly-v2 * modify flan-t5 * modify llama2 * modify llava * modify mistral * modify mixtral * modify phi-1_5 * modify qwen-vl * modify replit * modify solar * modify starcoder * modify yi * correct the comments * remove cpu_embedding in code for whisper and distil-whisper * remove comment * remove cpu_embedding for voice assistant * revert modify voice assistant * modify for voice assistant * add comment for voice assistant * fix comments * fix comments
101 lines
4 KiB
Python
101 lines
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 argparse
|
|
import os
|
|
|
|
import torch
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
from transformers.generation import GenerationConfig
|
|
|
|
from bigdl.llm import optimize_model
|
|
|
|
torch.manual_seed(1234)
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(description='Predict Tokens using `chat()` API for Qwen-VL model')
|
|
parser.add_argument('--repo-id-or-model-path', type=str, default="Qwen/Qwen-VL-Chat",
|
|
help='The huggingface repo id for the Qwen-VL model to be downloaded'
|
|
', or the path to the huggingface checkpoint folder')
|
|
parser.add_argument('--n-predict', type=int, default=32, help='Max tokens to predict')
|
|
|
|
current_path = os.path.dirname(os.path.abspath(__file__))
|
|
args = parser.parse_args()
|
|
model_path = args.repo_id_or_model_path
|
|
|
|
# Load model
|
|
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cpu", trust_remote_code=True)
|
|
|
|
# With only one line to enable BigDL-LLM optimization on model
|
|
# For successful BigDL-LLM optimization on Qwen-VL-Chat, skip the 'c_fc' and 'out_proj' modules during optimization
|
|
# When running LLMs on Intel iGPUs for Windows users, we recommend setting `cpu_embedding=True` in the optimize_model function.
|
|
# This will allow the memory-intensive embedding layer to utilize the CPU instead of iGPU.
|
|
model = optimize_model(model,
|
|
low_bit='sym_int4',
|
|
modules_to_not_convert=['c_fc', 'out_proj'])
|
|
model = model.to('xpu')
|
|
# Due to issue https://github.com/intel/intel-extension-for-pytorch/issues/454,
|
|
# currently put interpolation execution into cpu
|
|
def to_cpu(module, input, output):
|
|
return output.to("cpu")
|
|
|
|
def to_xpu(module, input):
|
|
return (input[0].to("xpu"),)
|
|
|
|
model.transformer.visual.ln_pre.register_forward_hook(to_cpu)
|
|
model.transformer.visual.transformer.register_forward_pre_hook(to_xpu)
|
|
|
|
# Specify hyperparameters for generation (No need to do this if you are using transformers>=4.32.0)
|
|
model.generation_config = GenerationConfig.from_pretrained(model_path, trust_remote_code=True)
|
|
|
|
# Load tokenizer
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
|
|
# Session ID
|
|
session_id = 1
|
|
|
|
while True:
|
|
print('-'*20, 'Session %d' % session_id, '-'*20)
|
|
image_input = input(f' Please input a picture: ')
|
|
if image_input.lower() == 'exit' : # type 'exit' to quit the dialouge
|
|
break
|
|
|
|
text_input = input(f' Please enter the text: ')
|
|
if text_input.lower() == 'exit' : # type 'exit' to quit the dialouge
|
|
break
|
|
|
|
if session_id == 1:
|
|
history = None
|
|
|
|
all_input = [{'image': image_input}, {'text': text_input}]
|
|
input_list = [_input for _input in all_input if list(_input.values())[0] != '']
|
|
|
|
if len(input_list) == 0:
|
|
print("Input list should not be empty. Please try again with valid input.")
|
|
continue
|
|
|
|
query = tokenizer.from_list_format(input_list)
|
|
response, history = model.chat(tokenizer, query = query, history = history)
|
|
torch.xpu.synchronize()
|
|
|
|
print('-'*10, 'Response', '-'*10)
|
|
print(response, '\n')
|
|
|
|
image = tokenizer.draw_bbox_on_latest_picture(response, history)
|
|
if image is not None:
|
|
image.save(os.path.join(current_path, f'Session_{session_id}.png'), )
|
|
|
|
session_id += 1
|