Skip to content

Latest commit

 

History

History
82 lines (65 loc) · 3.72 KB

README.md

File metadata and controls

82 lines (65 loc) · 3.72 KB
Raw

Baichuan2

In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Baichuan2 models. For illustration purposes, we utilize the baichuan-inc/Baichuan2-13B-Chat as a reference Baichuan 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 Baichuan 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_stream_generator  # additional package required for Baichuan-13B-Chat to conduct generation

On Windows:

onda create -n llm python=3.11
conda activate llm

pip install --pre --upgrade ipex-llm[all]
pip install transformers_stream_generator

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 Baichuan2 model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'baichuan-inc/Baichuan2-13B-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 Baichuan 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

baichuan-inc/Baichuan2-13B-Chat

Inference time: xxxx s
-------------------- Prompt --------------------
<reserved_106> AI是什么？ <reserved_107> 
-------------------- Output --------------------
<reserved_106> AI是什么？ <reserved_107> 人工智能（AI）是指由计算机系统执行的任务，这些任务通常需要人类智能才能完成。AI的目标是使计算机能够模拟人类的思维过程，从而

Inference time: xxxx s
-------------------- Prompt --------------------
<reserved_106> 解释一下“温故而知新” <reserved_107> 
-------------------- Output --------------------
<reserved_106> 解释一下“温故而知新” <reserved_107> 温故而知新是一个成语，出自《论语·为政》篇。这个成语的意思是：通过回顾和了解过去的事情，可以更好地理解新的知识和