starcoder

StarCoder

In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on StarCoder models on Intel GPUs. For illustration purposes, we utilize the bigcode/starcoder as a reference StarCoder model.

0. 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 an 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 environment:

conda create -n llm python=3.9
conda activate llm
# below command will install intel_extension_for_pytorch==2.0.110+xpu as default
# you can install specific ipex/torch version for your need
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 --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 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.

Sample Output

bigcode/starcoder

Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [02:07<00:00, 18.23s/it]
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:0 for open-end generation.
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:0 for open-end generation.
Inference time: xxxx s
-------------------- Prompt --------------------
def print_hello_world():
-------------------- Output --------------------
def print_hello_world():
    print("Hello World!")


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


def print_