ipex-llm/python/llm/example/CPU/PyTorch-Models/Model/qwen1.5/README.md

Qwen1.5

In this directory, you will find examples on how you could use IPEX-LLM optimize_model API to accelerate Qwen1.5 models. For illustration purposes, we utilize the Qwen/Qwen1.5-7B-Chat as reference Qwen1.5 model.

Requirements

To run these examples with IPEX-LLM, we have some recommended requirements for your machine, please refer to here for more information.

Example: Predict Tokens using generate() API

In the example generate.py, we show a basic use case for a Qwen1.5 model to predict the next N tokens using generate() API, with IPEX-LLM INT4 optimizations.

1. Install

We suggest using conda to manage the Python environment. For more information about conda installation, please refer to here.

After installing conda, create a Python environment for IPEX-LLM:

On Linux:

conda create -n llm python=3.11 # recommend to use Python 3.11
conda activate llm

# install the latest ipex-llm nightly build with 'all' option
pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
pip install transformers==4.37.0 # install transformers which supports Qwen2

# only for Qwen1.5-MoE-A2.7B
pip install transformers==4.40.0
pip install trl==0.8.1

On Windows:

conda create -n llm python=3.11
conda activate llm

pip install --pre --upgrade ipex-llm[all]
pip install transformers==4.37.0

REM for Qwen1.5-MoE-A2.7B
pip install transformers==4.40.0
pip install trl==0.8.1

2. Run

After setting up the Python environment, you could run the example by following steps.

2.1 Client

On client Windows machines, it is recommended to run directly with full utilization of all cores:

python ./generate.py --prompt 'What is AI?'

More information about arguments can be found in Arguments Info section. The expected output can be found in Sample Output section.

2.2 Server

For optimal performance on server, it is recommended to set several environment variables (refer to here for more information), and run the example with all the physical cores of a single socket.

E.g. on Linux,

# set IPEX-LLM env variables
source ipex-llm-init

# e.g. for a server with 48 cores per socket
export OMP_NUM_THREADS=48
numactl -C 0-47 -m 0 python ./generate.py --prompt 'What is AI?'

More information about arguments can be found in Arguments Info section. The expected output can be found in Sample Output section.

2.3 Arguments Info

In the example, several arguments can be passed to satisfy your requirements:

• --repo-id-or-model-path REPO_ID_OR_MODEL_PATH: argument defining the huggingface repo id for the Qwen1.5 to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'Qwen/Qwen1.5-7B-Chat'.
• --prompt PROMPT: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be 'AI是什么？'.
• --n-predict N_PREDICT: argument defining the max number of tokens to predict. It is default to be 32.

2.3 Sample Output

Qwen/Qwen1.5-7B-Chat

Inference time: xxxx s
-------------------- Prompt --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
AI是什么？<|im_end|>
<|im_start|>assistant
-------------------- Output --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
AI是什么？<|im_end|>
<|im_start|>assistant
AI（Artificial Intelligence）是指由计算机程序实现的智能，它使机器能够模拟人类的思考、学习和决策过程，从而解决各种复杂

Inference time: xxxx s
-------------------- Prompt --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
What is AI?<|im_end|>
<|im_start|>assistant
-------------------- Output --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
What is AI?<|im_end|>
<|im_start|>assistant
AI, or artificial intelligence, refers to the simulation of human intelligence in machines that are programmed to think, learn, and make decisions like humans. It involves the