ipex-llm/python/llm/example/GPU/PyTorch-Models/Model/starcoder

StarCoder

In this directory, you will find examples on how you could use BigDL-LLM optimize_model API to accelerate StarCoder models. For illustration purposes, we utilize the bigcode/starcoder as reference StarCoder models.

Requirements

To run these examples with BigDL-LLM on Intel GPUs, 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 StarCoder model to predict the next N tokens using generate() API, with BigDL-LLM INT4 optimizations on Intel GPUs.

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 BigDL-LLM:

conda create -n llm python=3.9 # recommend to use Python 3.9
conda activate llm

# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu

2. Configures OneAPI environment variables

source /opt/intel/oneapi/setvars.sh

3. Run

For optimal performance on Arc, it is recommended to set several environment variables.

export USE_XETLA=OFF
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1

python ./generate.py --prompt 'def print_hello_world():'

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 StarCoder model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'bigcode/starcoder'.
• --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.

2.3 Sample Output

bigcode/starcoder

Inference time: xxxx s
-------------------- Output --------------------
def print_hello_world():
    print("Hello World!")


def print_hello_name(name):
    print(f"Hello {name}!")


def print_