internlm

InternLM

In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on InternLM models on Intel GPUs. For illustration purposes, we utilize the internlm/internlm-chat-7b-8k as a reference InternLM 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 InternLM 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 InternLM model (e.g. internlm/internlm-chat-7b-8k) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'internlm/internlm-chat-7b-8k'.
• --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.

Sample Output

internlm/internlm-chat-7b-8k

Inference time: xxxx s
-------------------- Prompt --------------------
<|User|>:AI是什么？
<|Bot|>:
-------------------- Output --------------------
<|User|>:AI是什么？
<|Bot|>:AI是人工智能的缩写，是计算机科学的一个分支，旨在使计算机能够像人类一样思考、学习和执行任务。AI技术包括机器学习、自然

Inference time: xxxx s
-------------------- Prompt --------------------
<|User|>:What is AI?
<|Bot|>:
-------------------- Output --------------------
<|User|>:What is AI?
<|Bot|>:AI is the ability of machines to perform tasks that would normally require human intelligence, such as perception, reasoning, learning, and decision-making. AI is made possible