SOLAR-10.7B

In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on SOLAR-10.7B models. For illustration purposes, we utilize the upstage/SOLAR-10.7B-Instruct-v1.0 as a reference SOLAR-10.7B model.

0. Requirements

To run these examples with BigDL-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 SOLAR-10.7B model to predict the next N tokens using generate() API, with BigDL-LLM INT4 optimizations.

1. Install

We suggest using conda to manage environment:

conda create -n llm python=3.9
conda activate llm

pip install --pre --upgrade bigdl-llm[all] # install the latest bigdl-llm nightly build with 'all' option
pip install transformers==4.35.2 # required by SOLAR-10.7B

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 SOLAR-10.7B model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'upstage/SOLAR-10.7B-Instruct-v1.0'.
--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.

Note

: When loading the model in 4-bit, BigDL-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 SOLAR-10.7B 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 BigDL-LLM env variables
source bigdl-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

upstage/SOLAR-10.7B-Instruct-v1.0

Inference time: XXXX s
-------------------- Prompt --------------------
<s>### User:
What is AI?
### Assistant:

-------------------- Output --------------------
### User:
What is AI?
### Assistant:
 AI, or Artificial Intelligence, refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. It involves the development of

Inference time: XXXX s
-------------------- Prompt --------------------
<s>### User:
AI是什么？
### Assistant:

-------------------- Output --------------------
### User:
AI是什么？
### Assistant:
AI, 全称为人工智能(Artificial Intelligence)，是计算机科学、心理学、语言学、逻

3.4 KiB Raw Blame History Unescape Escape