qwen1.5

Qwen1.5

In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Qwen1.5 models. For illustration purposes, we utilize the Qwen/Qwen1.5-7B-Chat as a reference Qwen1.5 model.

0. 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 Qwen model to predict the next N tokens using generate() API, with IPEX-LLM INT4 optimizations.

1. Install

We suggest using conda to manage environment:

On Linux:

conda create -n llm python=3.11
conda activate llm

# install ipex-llm 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 the transformers which support 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

python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT

Arguments info:

• --repo-id-or-model-path REPO_ID_OR_MODEL_PATH: argument defining the huggingface repo id for the Qwen model 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.

Note: When loading the model in 4-bit, IPEX-LLM converts linear layers in the model into INT4 format. In theory, a XB model saved in 16-bit will requires approximately 2X GB of memory for loading, and ~0.5X GB memory for further inference.

Please select the appropriate size of the Qwen model based on the capabilities of your machine.

2.1 Client

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

python ./generate.py 

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

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
人工智能（AI）是指计算机科学的一个分支，旨在开发能够执行通常需要人类智能的任务的算法和系统。这些任务包括但不限于理解自然语言、

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 designed to perform tasks that typically require human cognition, such as learning, reasoning