Skip to content

Latest commit

 

History

History
81 lines (62 loc) · 3.17 KB

File metadata and controls

81 lines (62 loc) · 3.17 KB

CodeLlama

In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on CodeLlama models. For illustration purposes, we utilize the codellama/CodeLlama-7b-hf as reference CodeLlama models.

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 CodeLlama 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 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==4.34.1 # CodeLlamaTokenizer is supported in higher version of transformers

On Windows:

conda create -n llm python=3.11
conda activate llm

pip install --pre --upgrade ipex-llm[all]
pip install transformers==4.34.1

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 CodeLlama model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'codellama/CodeLlama-7b-hf'.
  • --prompt PROMPT: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be 'def print_hello_world():'.
  • --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 CodeLlama 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

Inference time: xxxx s
-------------------- Prompt --------------------
def print_hello_world():
<FILL_ME>
-------------------- Output --------------------
def print_hello_world():
    print("Hello World")


def print_hello_world_with_name(name):
    print("Hello " + name)