ipex-llm/python/llm/example/GPU/HF-Transformers-AutoModels/Model/phi-1_5
Mingyu Wei bc9cff51a8 LLM GPU Example Update for Windows Support (#9902)
* Update README in LLM GPU Examples

* Update reference of Intel GPU

* add cpu_embedding=True in comment

* small fixes

* update GPU/README.md and add explanation for cpu_embedding=True

* address comments

* fix small typos

* add backtick for cpu_embedding=True

* remove extra backtick in the doc

* add period mark

* update readme
2024-01-24 13:42:27 +08:00
..
generate.py [LLM] IPEX auto importer set on by default (#9832) 2024-01-04 13:33:29 +08:00
README.md LLM GPU Example Update for Windows Support (#9902) 2024-01-24 13:42:27 +08:00

phi-1_5

In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on phi-1_5 models on Intel GPUs. For illustration purposes, we utilize the microsoft/phi-1_5 as a reference phi-1_5 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 a phi-1_5 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==2.1.10+xpu as default
pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
pip install einops # additional package required for phi-1_5 to conduct generation

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 'What is AI?'

Arguments info:

  • --repo-id-or-model-path REPO_ID_OR_MODEL_PATH: argument defining the huggingface repo id for the phi-1_5 model (e.g. microsoft/phi-1_5) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'microsoft/phi-1_5'.
  • --prompt PROMPT: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be 'What is AI?'.
  • --n-predict N_PREDICT: argument defining the max number of tokens to predict. It is default to be 32.

Sample Output

microsoft/phi-1_5

Inference time: xxxx s
-------------------- Prompt --------------------
Question: What is AI?

 Answer:
-------------------- Output --------------------
Question: What is AI?

 Answer: AI stands for Artificial Intelligence, which refers to the development of computer systems that can perform tasks that typically require human intelligence, such as visual perception, speech recognition,